# LLM Pricing Deep Dive

> Server-readable mirror of https://benchlm.ai/llm-pricing. Compare token prices, benchmark scores, and value ratios without relying on client-side rendering. Prices last updated: September 30, 2026.

## Key Takeaways

- As of September 30, 2026, the cheapest LLM API is Qwen3.7 Flash at $0.03/$0.13 per million input/output tokens, of 169 paid models across 30 providers. The cheapest production-grade model (score 70+) is MiMo-V2.6-Pro at $0.43/$0.87. The cheapest frontier-tier model (score 80+) is Claude Sonnet 5.5 at $2.00/$10.00.
- Best benchmark score per dollar: [Qwen3.7 Flash](/models/qwen3-7-flash) at 377.3 Score/$.

## Pricing Table

| Model | Creator | Input $/1M | Output $/1M | Score | Score/$ | Confidence |
|-------|---------|-----------|------------|-------|---------|------------|
| [Ministral 3 3B](/models/ministral-3-3b) | Mistral | $0.10 | $0.10 | ~19.27 | 192.7 | Estimated |
| [Ministral 3 3B (Reasoning)](/models/ministral-3-3b-reasoning) | Mistral | $0.10 | $0.10 | — | — | Estimated |
| [Qwen3.7 Flash](/models/qwen3-7-flash) | Alibaba | $0.03 | $0.13 | ~49.05 | 377.3 | Estimated |
| [Mercury 2.5](/models/mercury-2-5) | Inception | $0.04 | $0.15 | 35.18 | 234.5 | Limited |
| [Ministral 3 8B](/models/ministral-3-8b) | Mistral | $0.15 | $0.15 | ~20.46 | 136.4 | Estimated |
| [Ministral 3 8B (Reasoning)](/models/ministral-3-8b-reasoning) | Mistral | $0.15 | $0.15 | — | — | Estimated |
| [Laguna S 2.1](/models/laguna-s-2-1) | Poolside | $0.10 | $0.20 | — | — | Estimated |
| [Laguna XS 2.1](/models/laguna-xs-2-1) | Poolside | $0.10 | $0.20 | — | — | Estimated |
| [Ministral 3 14B](/models/ministral-3-14b) | Mistral | $0.20 | $0.20 | ~25.39 | 127 | Estimated |
| [Ministral 3 14B (Reasoning)](/models/ministral-3-14b-reasoning) | Mistral | $0.20 | $0.20 | — | — | Estimated |
| [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) | DeepSeek | $0.14 | $0.28 | — | — | Good |
| [MiMo-V2.6-Flash](/models/mimo-v2-6-flash) | Xiaomi | $0.14 | $0.28 | 66.36 | 237 | Good |
| [Step 3.5 Flash](/models/step-3-5-flash) | StepFun | $0.10 | $0.30 | ~42.66 | 142.2 | Estimated |
| [Gemini 2.5 Flash-Lite](/models/gemini-2-5-flash-lite) | Google | $0.10 | $0.40 | — | — | N/A |
| [GPT-4.1 nano](/models/gpt-4-1-nano) | OpenAI | $0.10 | $0.40 | 26.42 | 66.1 | Good |
| [GPT-5 nano](/models/gpt-5-nano) | OpenAI | $0.05 | $0.40 | ~37.08 | 92.7 | Estimated |
| [Qwen3.5 Flash](/models/qwen3-5-flash) | Alibaba | $0.10 | $0.40 | ~45.07 | 112.7 | Estimated |
| [DeepSeek V3.2](/models/deepseek-v3-2) | DeepSeek | $0.28 | $0.42 | 50.93 | 121.3 | Good |
| [GPT-6 Luna](/models/gpt-6-luna) | OpenAI | $0.10 | $0.50 | 64.95 | 129.9 | Good |
| [Grok 3 Mini](/models/grok-3-mini) | xAI | $0.30 | $0.50 | ~44.13 | 88.3 | Estimated |
| [Grok 4.1 Fast](/models/grok-4-1-fast) | xAI | $0.20 | $0.50 | ~36.69 | 73.4 | Estimated |
| [GPT-4o mini](/models/gpt-4o-mini) | OpenAI | $0.15 | $0.60 | ~27.57 | 46 | Estimated |
| [GPT-4o mini Audio](/models/gpt-4o-mini-audio) | OpenAI | $0.15 | $0.60 | — | — | Estimated |
| [Mistral Small 4](/models/mistral-small-4) | Mistral | $0.15 | $0.60 | 35.08 | 58.5 | Limited |
| [Mistral Small 4 (Reasoning)](/models/mistral-small-4-reasoning) | Mistral | $0.15 | $0.60 | — | — | Estimated |
| [Solar Pro 3](/models/solar-pro-3) | Upstage | $0.15 | $0.60 | 30.38 | 50.6 | Limited |
| [Celeris-1](/models/celeris-1) | Celeris | $0.20 | $0.70 | ~28.9 | 41.3 | Estimated |
| [Toast 1](/models/toast-1) | Mixedbread | $0.30 | $0.72 | — | — | Estimated |
| [Mercury 2](/models/mercury-2) | Inception | $0.25 | $0.75 | ~35.82 | 47.8 | Estimated |
| [Mercury Edit 2](/models/mercury-edit-2) | Inception | $0.25 | $0.75 | — | — | Estimated |
| [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) | Xiaomi | $0.43 | $0.87 | 75.49 | 86.8 | Limited |
| [Trinity-Large-Thinking](/models/trinity-large-thinking) | Arcee AI | $0.25 | $0.90 | 34.86 | 38.7 | Limited |
| [Pokee-Isaac 28B](/models/pokee-isaac-28b) | Pokee AI | $0.15 | $1.00 | — | — | Estimated |
| [Trinity-Large-Preview](/models/trinity-large-preview) | Arcee AI | $0.25 | $1.00 | — | — | Estimated |
| [DeepSeek V3](/models/deepseek-v3) | DeepSeek | $0.27 | $1.10 | 32.58 | 29.6 | Limited |
| [GLM-4.5-Air](/models/glm-4-5-air) | Z.AI | $0.20 | $1.10 | ~35.3 | 32.1 | Estimated |
| [Step 3.7 Flash](/models/step-3-7-flash) | StepFun | $0.20 | $1.15 | 44.84 | 39 | Good |
| [DeepSeek V4.1 Flash](/models/deepseek-v4-1-flash) | DeepSeek | $0.30 | $1.20 | 64.63 | 53.9 | Limited |
| [GPT-5.6 Luna](/models/gpt-5-6-luna) | OpenAI | $0.20 | $1.20 | 66.2 | 55.2 | Good |
| [MiniMax M2.5](/models/minimax-m2-5) | MiniMax | $0.30 | $1.20 | ~50.38 | 42 | Estimated |
| [MiniMax M2.7](/models/minimax-m2-7) | MiniMax | $0.30 | $1.20 | 48.55 | 40.5 | Good |
| [MiniMax M3](/models/minimax-m3) | MiniMax | $0.30 | $1.20 | 55.16 | 46 | Good |
| [Solar Pro 4](/models/solar-pro-4) | Upstage | $0.30 | $1.20 | — | — | Estimated |
| [Claude 3 Haiku](/models/claude-3-haiku) | Anthropic | $0.25 | $1.25 | ~15.61 | 12.5 | Estimated |
| [GPT-5.4 nano](/models/gpt-5-4-nano) | OpenAI | $0.20 | $1.25 | 51.44 | 41.2 | Full |
| [Inkling-Small](/models/inkling-small) | Thinking Machines Lab | $0.58 | $1.44 | 55.09 | 38.3 | Full |
| [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite) | Google | $0.25 | $1.50 | 49.49 | 33 | Limited |
| [Grok Code Fast 1](/models/grok-code-fast-1) | xAI | $0.20 | $1.50 | ~34.57 | 23.1 | Estimated |
| [Mercury Voice](/models/mercury-voice) | Inception | $0.40 | $1.50 | — | — | Estimated |
| [Mistral Large 3](/models/mistral-large-3) | Mistral | $0.50 | $1.50 | 33.63 | 22.4 | Limited |
| [Aion-2.0](/models/aion-2-0) | Aion Labs | $0.80 | $1.60 | — | — | Estimated |
| [GPT-4.1 mini](/models/gpt-4-1-mini) | OpenAI | $0.40 | $1.60 | 31.12 | 19.5 | Good |
| [Holo3.1-35B-A3B](/models/holo3-1-35b-a3b) | H Company | $0.25 | $1.80 | — | — | Estimated |
| [Quasar 438B](/models/quasar-438b) | Multiverse Computing | $0.60 | $1.80 | ~49.83 | 27.7 | Estimated |
| [GPT-5 mini](/models/gpt-5-mini) | OpenAI | $0.25 | $2.00 | ~44.75 | 22.4 | Estimated |
| [Grok Build 0.1](/models/grok-build-0-1) | xAI | $1.00 | $2.00 | — | — | Estimated |
| [Mistral Medium 3](/models/mistral-medium-3) | Mistral | $0.40 | $2.00 | ~30.11 | 15.1 | Estimated |
| [DeepSeek R1](/models/deepseek-r1) | DeepSeek | $0.55 | $2.19 | ~43.34 | 19.8 | Estimated |
| [DeepSeek V3.2 (Thinking)](/models/deepseek-v3-2-thinking) | DeepSeek | $0.55 | $2.19 | — | — | Estimated |
| [GLM-4.5](/models/glm-4-5) | Z.AI | $0.60 | $2.20 | — | — | Estimated |
| [GPT Realtime 2.1 Mini](/models/gpt-realtime-2-1-mini) | OpenAI | $0.60 | $2.40 | — | — | Estimated |
| [GPT Realtime mini](/models/gpt-realtime-mini) | OpenAI | $0.60 | $2.40 | — | — | Estimated |
| [Qwen3.5 Plus](/models/qwen3-5-plus) | Alibaba | $0.40 | $2.40 | ~49.44 | 20.6 | Estimated |
| [Composer 2](/models/composer-2) | Cursor | $0.50 | $2.50 | — | — | Estimated |
| [Composer 2.5](/models/composer-2-5) | Cursor | $0.50 | $2.50 | — | — | Estimated |
| [Gemini 2.5 Flash](/models/gemini-2-5-flash) | Google | $0.30 | $2.50 | 43.73 | 17.5 | Limited |
| [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | Google | $0.30 | $2.50 | 51.53 | 20.6 | Good |
| [Grok 4.20](/models/grok-4-20-beta) | xAI | $1.25 | $2.50 | 59.18 | 23.7 | Good |
| [Grok 4.3](/models/grok-4-3) | xAI | $1.25 | $2.50 | 55.33 | 22.1 | Good |
| [Kimi K2](/models/kimi-k2) | Moonshot AI | $0.60 | $2.50 | 29.64 | 11.9 | Limited |
| [Step 5 Preview](/models/step-5-preview) | StepFun | $1.00 | $2.70 | 70.35 | 26.1 | Good |
| [Gemini 3 Flash](/models/gemini-3-flash) | Google | $0.50 | $3.00 | 56.29 | 18.8 | Good |
| [Holo3-122B-A10B](/models/holo3-122b-a10b) | H Company | $0.40 | $3.00 | — | — | Estimated |
| [Kimi K2.5](/models/kimi-k2-5) | Moonshot AI | $0.60 | $3.00 | 53.65 | 17.9 | Full |
| [Kimi K2.5 (Reasoning)](/models/kimi-k2-5-reasoning) | Moonshot AI | $0.60 | $3.00 | — | — | Limited |
| [GLM-5](/models/glm-5) | Z.AI | $1.00 | $3.20 | 55.04 | 17.2 | Full |
| [GLM-5 (Reasoning)](/models/glm-5-reasoning) | Z.AI | $1.00 | $3.20 | — | — | Estimated |
| [Interfaze Beta](/models/interfaze-beta) | Interfaze | $1.50 | $3.50 | — | — | Estimated |
| [Qwen3.5 397B](/models/qwen3-5-397b) | Alibaba | $0.60 | $3.60 | — | — | Full |
| [Qwen3.5 397B (Reasoning)](/models/qwen3-5-397b-reasoning) | Alibaba | $0.60 | $3.60 | — | — | Estimated |
| [Gemini 3.6 Flash](/models/gemini-3-6-flash) | Google | $0.75 | $3.75 | 65.15 | 17.4 | Good |
| [Gemini 3.7 Flash](/models/gemini-3-7-flash) | Google | $0.75 | $3.75 | 67.94 | 18.1 | Good |
| [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | $0.75 | $3.75 | 73.92 | 19.7 | Good |
| [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | DeepSeek | $1.32 | $3.96 | 64.95 | 16.4 | Good |
| [GLM-5-Turbo](/models/glm-5-turbo) | Z.AI | $1.20 | $4.00 | ~54.65 | 13.7 | Estimated |
| [GLM-5V-Turbo](/models/glm-5v-turbo) | Z.AI | $1.20 | $4.00 | 50.48 | 12.6 | Limited |
| [Kimi 2.6](/models/kimi-2-6) | Moonshot AI | $0.95 | $4.00 | 60.17 | 15 | Good |
| [Kimi K2.7 Code](/models/kimi-k2-7-code) | Moonshot AI | $0.95 | $4.00 | 54.59 | 13.7 | Good |
| [Sakana Namazu](/models/sakana-namazu) | Sakana AI | $0.95 | $4.00 | — | — | Estimated |
| [Muse Spark 1.2](/models/muse-spark-1-2) | Meta | $1.25 | $4.25 | 65.7 | 15.5 | Limited |
| [Muse Spark 1.3](/models/muse-spark-1-3) | Meta | $1.25 | $4.25 | — | — | Limited |
| [GLM-5.1](/models/glm-5-1) | Z.AI | $1.40 | $4.40 | 57.74 | 13.1 | Good |
| [GLM-5.2](/models/glm-5-2) | Z.AI | $1.40 | $4.40 | 63.15 | 14.4 | Good |
| [o3-mini](/models/o3-mini) | OpenAI | $1.10 | $4.40 | ~40.84 | 9.3 | Estimated |
| [o4-mini](/models/o4-mini-high) | OpenAI | $1.10 | $4.40 | — | — | N/A |
| [Gemini 3.8 Live](/models/gemini-3-8-live) | Google | $0.75 | $4.50 | — | — | Estimated |
| [Gemini 3.8 Live Extended Thinking](/models/gemini-3-8-live-extended-thinking) | Google | $0.75 | $4.50 | — | — | Estimated |
| [GPT-5.4 mini](/models/gpt-5-4-mini) | OpenAI | $0.75 | $4.50 | 55.63 | 12.4 | Full |
| [Inkling](/models/inkling) | Thinking Machines Lab | $1.87 | $4.68 | 54.78 | 11.7 | Full |
| [Claude Haiku 4.5](/models/claude-haiku-4-5) | Anthropic | $1.00 | $5.00 | 42.4 | 8.5 | Limited |
| [Gemini 1.5 Pro](/models/gemini-1-5-pro) | Google | $1.25 | $5.00 | ~28.15 | 5.6 | Estimated |
| [GPT-5.2 Instant](/models/gpt-5-2-instant) | OpenAI | $1.50 | $6.00 | — | — | Estimated |
| [Grok 4.5](/models/grok-4-5) | xAI | $2.00 | $6.00 | 65.63 | 10.9 | Good |
| [Grok 4.6](/models/grok-4-6) | xAI | $2.00 | $6.00 | 69.38 | 11.6 | Limited |
| [Grok 4.7](/models/grok-4-7) | xAI | $2.00 | $6.00 | — | — | Limited |
| [Mistral Medium 3.5 128B](/models/mistral-medium-3-5-128b) | Mistral | $1.50 | $7.50 | 36.17 | 4.8 | Good |
| [Pareto 26.9](/models/pareto-26-9) | Unbiased | $2.50 | $7.50 | — | — | Estimated |
| [GPT-4.1](/models/gpt-4-1) | OpenAI | $2.00 | $8.00 | 39.28 | 4.9 | Good |
| [o3](/models/o3) | OpenAI | $2.00 | $8.00 | 47.72 | 6 | Limited |
| [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | $1.50 | $9.00 | 63.93 | 7.1 | Full |
| [Claude Sonnet 5](/models/claude-sonnet-5) | Anthropic | $2.00 | $10.00 | 67.35 | 6.7 | Good |
| [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | $2.00 | $10.00 | 83.28 | 8.3 | Good |
| [Command A+](/models/command-a-plus) | Cohere | $2.50 | $10.00 | 36.6 | 3.7 | Limited |
| [Gemini 2.5 Pro](/models/gemini-2-5-pro) | Google | $1.25 | $10.00 | 50.96 | 5.1 | Good |
| [Gemini 4 Argon](/models/gemini-4-argon) | Google | $2.00 | $10.00 | 77.18 | 7.7 | Limited |
| [GPT Audio 1.5](/models/gpt-audio-1-5) | OpenAI | $2.50 | $10.00 | — | — | Estimated |
| [GPT-4o](/models/gpt-4o) | OpenAI | $2.50 | $10.00 | 30.04 | 3 | Limited |
| [GPT-4o Audio](/models/gpt-4o-audio) | OpenAI | $2.50 | $10.00 | — | — | Estimated |
| [GPT-5 (high)](/models/gpt-5-high) | OpenAI | $1.25 | $10.00 | — | — | Estimated |
| [GPT-5.1](/models/gpt-5-1) | OpenAI | $1.25 | $10.00 | 58.95 | 5.9 | Limited |
| [GPT-5.1-Codex](/models/gpt-5-1-codex) | OpenAI | $1.25 | $10.00 | 51 | 5.1 | Limited |
| [GPT-5.1-Codex-Max](/models/gpt-5-1-codex-max) | OpenAI | $1.25 | $10.00 | — | — | Estimated |
| [GPT-6 Sol](/models/gpt-6-sol) | OpenAI | $2.00 | $10.00 | 79.16 | 7.9 | Good |
| [GPT-6.1 Sol](/models/gpt-6-1-sol) | OpenAI | $2.00 | $10.00 | 77.55 | 7.8 | Limited |
| [Gemini 3 Pro](/models/gemini-3-pro) | Google | $2.00 | $12.00 | 61.55 | 5.1 | Good |
| [Gemini 3.1 Pro](/models/gemini-3-1-pro) | Google | $2.00 | $12.00 | 65.05 | 5.4 | Good |
| [GPT-4o mini TTS](/models/gpt-4o-mini-tts) | OpenAI | $0.60 | $12.00 | — | — | Estimated |
| [GPT-5.6 Terra](/models/gpt-5-6-terra) | OpenAI | $2.00 | $12.00 | 73.18 | 6.1 | Full |
| [GPT-5.2](/models/gpt-5-2) | OpenAI | $1.75 | $14.00 | 61.92 | 4.4 | Full |
| [GPT-5.2-Codex](/models/gpt-5-2-codex) | OpenAI | $1.75 | $14.00 | 56.74 | 4.1 | Limited |
| [GPT-5.3 Codex](/models/gpt-5-3-codex) | OpenAI | $1.75 | $14.00 | 62.46 | 4.5 | Good |
| [GPT-5.3 Instant](/models/gpt-5-3-instant) | OpenAI | $1.75 | $14.00 | — | — | Estimated |
| [Claude 3.5 Sonnet](/models/claude-3-5-sonnet) | Anthropic | $3.00 | $15.00 | ~29.6 | 2 | Estimated |
| [Claude 4 Sonnet](/models/claude-4-sonnet) | Anthropic | $3.00 | $15.00 | 38.6 | 2.6 | Limited |
| [Claude Sonnet 4.5](/models/claude-sonnet-4-5) | Anthropic | $3.00 | $15.00 | 49.13 | 3.3 | Limited |
| [Claude Sonnet 4.6](/models/claude-sonnet-4-6) | Anthropic | $3.00 | $15.00 | 56.86 | 3.8 | Full |
| [Ember-1](/models/ember-1) | Fireworks | $3.00 | $15.00 | — | — | Estimated |
| [GPT-5.4](/models/gpt-5-4) | OpenAI | $2.50 | $15.00 | 68.89 | 4.6 | Full |
| [Kimi K3](/models/kimi-k3) | Moonshot AI | $3.00 | $15.00 | 72.12 | 4.8 | Good |
| [GPT Realtime](/models/gpt-realtime) | OpenAI | $4.00 | $16.00 | — | — | Estimated |
| [GPT Realtime 1.5](/models/gpt-realtime-1-5) | OpenAI | $4.00 | $16.00 | — | — | Estimated |
| [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | $4.00 | $20.00 | 87.68 | 4.4 | Good |
| [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | $4.00 | $20.00 | 78.91 | 4 | Full |
| [GPT Realtime 2](/models/gpt-realtime-2) | OpenAI | $4.00 | $24.00 | — | — | Estimated |
| [GPT Realtime 2.1](/models/gpt-realtime-2-1) | OpenAI | $4.00 | $24.00 | — | — | Estimated |
| [Claude Opus 4.5](/models/claude-opus-4-5) | Anthropic | $5.00 | $25.00 | 55.64 | 2.2 | Full |
| [Claude Opus 4.6](/models/claude-opus-4-6) | Anthropic | $5.00 | $25.00 | 64.25 | 2.6 | Full |
| [Claude Opus 4.7](/models/claude-opus-4-7) | Anthropic | $5.00 | $25.00 | 65.81 | 2.6 | Limited |
| [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) | Anthropic | $5.00 | $25.00 | 69.63 | 2.8 | Good |
| [Claude Opus 4.8](/models/claude-opus-4-8) | Anthropic | $5.00 | $25.00 | 70.8 | 2.8 | Full |
| [Claude Opus 5](/models/claude-opus-5) | Anthropic | $5.00 | $25.00 | 79.89 | 3.2 | Good |
| [GPT-4 Turbo](/models/gpt-4-turbo) | OpenAI | $10.00 | $30.00 | ~22.31 | 0.7 | Estimated |
| [GPT-5.5](/models/gpt-5-5) | OpenAI | $5.00 | $30.00 | 69.38 | 2.3 | Full |
| [Sakana Fugu-Ultra v1.1](/models/sakana-fugu-ultra-v1-1) | Sakana AI | $5.00 | $30.00 | — | — | Estimated |
| [Fugu Cyber](/models/sakana-fugu-cyber) | Sakana AI | $6.00 | $36.00 | — | — | Estimated |
| [Claude Fable 5](/models/claude-fable) | Anthropic | $10.00 | $50.00 | 79.41 | 1.6 | Good |
| [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | $10.00 | $50.00 | 82.82 | 1.7 | Limited |
| [Claude Mythos 5](/models/claude-mythos-5) | Anthropic | $10.00 | $50.00 | — | — | Limited |
| [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | $10.00 | $50.00 | 88.69 | 1.8 | Good |
| [o1](/models/o1) | OpenAI | $15.00 | $60.00 | 40.06 | 0.7 | Limited |
| [o1-preview](/models/o1-preview) | OpenAI | $15.00 | $60.00 | ~36.97 | 0.6 | Estimated |
| [Claude 3 Opus](/models/claude-3-opus) | Anthropic | $15.00 | $75.00 | ~29.32 | 0.4 | Estimated |
| [Claude 4.1 Opus](/models/claude-4-1-opus) | Anthropic | $15.00 | $75.00 | ~40.85 | 0.5 | Estimated |
| [o3-pro](/models/o3-pro) | OpenAI | $20.00 | $80.00 | ~47.88 | 0.6 | Estimated |
| [Claude Mythos Preview](/models/claude-mythos-preview) | Anthropic | $25.00 | $125.00 | — | — | Estimated |
| [GPT-5.2 Pro](/models/gpt-5-2-pro) | OpenAI | $21.00 | $168.00 | ~68.23 | 0.4 | Estimated |
| [GPT-5.4 Pro](/models/gpt-5-4-pro) | OpenAI | $30.00 | $180.00 | 70.72 | 0.4 | Limited |
| [GPT-5.5 Pro](/models/gpt-5-5-pro) | OpenAI | $30.00 | $180.00 | 74.62 | 0.4 | Limited |
| [o1-pro](/models/o1-pro) | OpenAI | $150.00 | $600.00 | ~36 | 0.1 | Estimated |
| [Qwen3.8 Max](/models/qwen3-8-max) | Alibaba | N/A | N/A | 72.1 | — | Good |
| [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | N/A | N/A | 63.44 | — | Full |
| [Qwen3.6 Plus](/models/qwen3-6-plus) | Alibaba | N/A | N/A | 55.19 | — | Full |
| [Grok 4](/models/grok-4) | xAI | N/A | N/A | 53.37 | — | Limited |
| [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) | Xiaomi | N/A | N/A | 52.62 | — | Good |
| [Apodex 1.1](/models/apodex-1-1) | Apodex | N/A | N/A | 52.18 | — | Limited |
| [GPT-5 (medium)](/models/gpt-5-medium) | OpenAI | N/A | N/A | ~47.05 | — | Estimated |
| [Ling 3.0 Flash](/models/ling-3-0-flash) | InclusionAI | N/A | N/A | 46.38 | — | Good |
| [Grok 3 [Beta]](/models/grok-3-beta) | xAI | N/A | N/A | ~44.5 | — | Estimated |
| [Claude 4.1 Opus Thinking](/models/claude-4-1-opus-thinking) | Anthropic | N/A | N/A | ~40.46 | — | Estimated |
| [Ling 2.6 Flash](/models/ling-2-6-flash) | InclusionAI | N/A | N/A | 32.83 | — | Limited |
| [Mistral Large 2](/models/mistral-large-2) | Mistral | N/A | N/A | ~28.9 | — | Estimated |
| [Qwen3-Omni-30B-A3B-Instruct](/models/qwen3-omni-30b-a3b-instruct) | Alibaba | N/A | N/A | ~28.57 | — | Estimated |
| [MiniMax M1 80k](/models/minimax-m1-80k) | MiniMax | N/A | N/A | ~27.81 | — | Estimated |
| [Nova Pro](/models/nova-pro) | Amazon | N/A | N/A | ~22.15 | — | Estimated |
| [Gemini 1.0 Pro](/models/gemini-1-0-pro) | Google | N/A | N/A | ~13.93 | — | Estimated |
| [Alibaba GTE Reranker ModernBERT-base](/models/jevbench-gte-reranker-modernbert-base) | Alibaba-NLP | N/A | N/A | — | — | Estimated |
| [Amazon Nova 2 Lite](/models/nova-2-lite) | Amazon | N/A | N/A | — | — | Estimated |
| [Amazon Nova 2 Pro](/models/nova-2-pro) | Amazon | N/A | N/A | — | — | Estimated |
| [Amazon Nova 2 Sonic](/models/amazon-nova-2-sonic) | Amazon | N/A | N/A | — | — | Estimated |
| [Audio Flamingo 3 7B](/models/audio-flamingo-3-7b) | NVIDIA | N/A | N/A | — | — | Estimated |
| [AuK](/models/tencent-auk) | Tencent | N/A | N/A | — | — | Estimated |
| [AutoJev-27B (denis-pplx, Qwen3.8-27B)](/models/jevbench-autojev-27b) | unknown | N/A | N/A | — | — | Estimated |
| [AutoJev-27B (RTX PRO 6000)](/models/jevbench-autojev-27b-rtxpro6000-a2) | unknown | N/A | N/A | — | — | Estimated |
| [Autoloops – Gemma 4 31B IT](/models/jevbench-kushal-gemma4-31b-it-autoloops) | Autoloops | N/A | N/A | — | — | Estimated |
| [BAAI bge-reranker-v2-m3](/models/jevbench-bge-reranker-v2-m3) | BAAI | N/A | N/A | — | — | Estimated |
| [Baichuan-Audio](/models/baichuan-audio) | Baichuan | N/A | N/A | — | — | Estimated |
| [Baichuan-Omni 1.5](/models/baichuan-omni-1-5) | Baichuan | N/A | N/A | — | — | Estimated |
| [Bespoke Nimble 9B (Bespoke Labs)](/models/jevbench-nimble-9b) | Bespoke Labs | N/A | N/A | — | — | Estimated |
| [Bev / Bonsai 27B](/models/jevbench-bev-bonsai-27b) | Reza Sayar | N/A | N/A | — | — | Estimated |
| [BLSP 7B](/models/blsp-7b) | BLSP authors | N/A | N/A | — | — | Estimated |
| [Bosun v3.1 0.6B](/models/jevbench-bosun-v31-0-6b) | Clause Logic | N/A | N/A | — | — | Estimated |
| [BR-Voice-Reasoner](/models/br-voice-reasoner) | Bairong Xdynamics | N/A | N/A | — | — | Estimated |
| [Canary 180M Flash](/models/canary-180m-flash) | NVIDIA | N/A | N/A | — | — | Estimated |
| [Cartesia Ink-Whisper](/models/cartesia-ink-whisper) | Cartesia | N/A | N/A | — | — | Estimated |
| [Cartesia Sonic 3](/models/cartesia-sonic-3) | Cartesia | N/A | N/A | — | — | Estimated |
| [Cartesia Sonic 3.6](/models/cartesia-sonic-3-6) | Cartesia | N/A | N/A | — | — | Estimated |
| [Certo v1 (AltSlate Labs)](/models/jevbench-certo) | AltSlate Labs | N/A | N/A | — | — | Estimated |
| [classifier.dev (fast tier)](/models/jevbench-classifier-dev-fast) | mrmps (@michael_chomsky) | N/A | N/A | — | — | Estimated |
| [Claude Mythos 5.1](/models/claude-mythos-5-1) | Anthropic | N/A | N/A | — | — | Estimated |
| [CLM-8B (Contrastive-LM, clm-latest)](/models/jevbench-clm-8b) | Contrastive-LM (Kwok, Kang, Suresh, Saad-Falcon, Pavone, Ré, Mirhoseini) | N/A | N/A | — | — | Estimated |
| [Cohere Transcribe 03-2026](/models/cohere-transcribe-03-2026) | Cohere | N/A | N/A | — | — | Estimated |
| [Cohere Transcribe Arabic 07-2026](/models/cohere-transcribe-arabic-07-2026) | Cohere | N/A | N/A | — | — | Estimated |
| [Cygnet (blockbrain, frozen Gemma-4-12B-it)](/models/jevbench-cygnet) | blockbrain | N/A | N/A | — | — | Estimated |
| [decider-2b (Mapika)](/models/jevbench-decider-2b) | Mapika | N/A | N/A | — | — | Estimated |
| [decider-35b-a3b (Mapika)](/models/jevbench-decider-35b-a3b) | Mapika | N/A | N/A | — | — | Estimated |
| [decider-4b v2 (Mapika)](/models/jevbench-decider-4b-v2) | Mapika | N/A | N/A | — | — | Estimated |
| [Decision 2B (FlyMy.AI, v59)](/models/jevbench-decision-2b) | FlyMy.AI (@denti) | N/A | N/A | — | — | Estimated |
| [Decision 4B v1.1 (FlyMyJev, Qwen3.5-4B + LoRA)](/models/jevbench-decision-4b-v11) | unknown | N/A | N/A | — | — | Estimated |
| [Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA)](/models/jevbench-decision-4b-v12) | unknown | N/A | N/A | — | — | Estimated |
| [Decision Fast (FlyMy.AI, v53a)](/models/jevbench-decision-fast) | FlyMy.AI (@denti) | N/A | N/A | — | — | Estimated |
| [Decision-4B (Eval Engine / Chromia)](/models/jevbench-evalengine-decision-4b) | Eval Engine / Chromia | N/A | N/A | — | — | Estimated |
| [decision-machine-1 (milliseconds.ai)](/models/jevbench-decision-machine-1) | milliseconds.ai (Baptiste Laget) | N/A | N/A | — | — | Estimated |
| [Deem 0.8B v1](/models/jevbench-deem-0-8-v1) | LibertAI | N/A | N/A | — | — | Estimated |
| [Deepgram Aura-2](/models/deepgram-aura-2) | Deepgram | N/A | N/A | — | — | Estimated |
| [Deepgram Flux](/models/deepgram-flux) | Deepgram | N/A | N/A | — | — | Estimated |
| [Deepgram Flux Multilingual](/models/deepgram-flux-multilingual) | Deepgram | N/A | N/A | — | — | Estimated |
| [Deepgram Nova-3](/models/deepgram-nova-3) | Deepgram | N/A | N/A | — | — | Estimated |
| [DeepSeek Coder 2.0](/models/deepseek-coder-2-0) | DeepSeek | N/A | N/A | — | — | Estimated |
| [DeepSeek V3 0324](/models/deepseek-v3-0324) | DeepSeek | N/A | N/A | — | — | Estimated |
| [DiVA Llama 3 8B](/models/diva-llama-3-v0-8b) | DiVA authors | N/A | N/A | — | — | Estimated |
| [djev (Maisa, diffusion-gemma)](/models/jevbench-djev) | Maisa (David Villalón) | N/A | N/A | — | — | Estimated |
| [djev (thinking)](/models/jevbench-djev-thinking) | David Villalon / Maisa | N/A | N/A | — | — | Estimated |
| [Eikos-27B (caiovicentino1, Qwen3.8-27B)](/models/jevbench-eikos-27b) | unknown | N/A | N/A | — | — | Estimated |
| [ElevenLabs Eleven v3 Conversational](/models/elevenlabs-eleven-v3-conversational) | ElevenLabs | N/A | N/A | — | — | Estimated |
| [ElevenLabs Eleven v4](/models/elevenlabs-eleven-v4) | ElevenLabs | N/A | N/A | — | — | Estimated |
| [ElevenLabs Eleven v4 Turbo](/models/elevenlabs-eleven-v4-turbo) | ElevenLabs | N/A | N/A | — | — | Estimated |
| [Fish Audio S2.1 Pro](/models/fish-audio-s2-1-pro) | Fish Audio | N/A | N/A | — | — | Estimated |
| [Freya TTS Adam V1](/models/freya-tts-adam-v1) | Freya | N/A | N/A | — | — | Estimated |
| [Gemini 2.5 Flash Native Audio Preview (12-2025)](/models/gemini-2-5-flash-native-audio-preview-12-2025) | Google | N/A | N/A | — | — | Estimated |
| [Gemini 3 Pro Deep Think](/models/gemini-3-pro-deep-think) | Google | N/A | N/A | — | — | Estimated |
| [Gemini 3.1 Flash Live Preview](/models/gemini-3-1-flash-live-preview) | Google | N/A | N/A | — | — | Estimated |
| [Gemini 3.5 Flash Cyber](/models/gemini-3-5-flash-cyber) | Google | N/A | N/A | — | — | Estimated |
| [Gemini 3.5 Transcribe](/models/gemini-3-5-transcribe) | Google | N/A | N/A | — | — | Estimated |
| [Gemini 3.8 Flash Cyber](/models/gemini-3-8-flash-cyber) | Google | N/A | N/A | — | — | Estimated |
| [Gemini 3.8 Flash TTS](/models/gemini-3-8-flash-tts) | Google | N/A | N/A | — | — | Estimated |
| [Gemini 3.8 Flash-Lite TTS](/models/gemini-3-8-flash-lite-tts) | Google | N/A | N/A | — | — | Estimated |
| [GLiNER2 (Fastino, gliner2.5-base)](/models/jevbench-gliner2) | Fastino | N/A | N/A | — | — | Estimated |
| [GLiNER2 large (Fastino)](/models/jevbench-gliner2-large) | Fastino | N/A | N/A | — | — | Estimated |
| [GLiNER2.5 multi (Fastino, 287M)](/models/jevbench-gliner2-5-multi) | Fastino | N/A | N/A | — | — | Estimated |
| [GLiNER2.5 small (Fastino, 74M)](/models/jevbench-gliner2-5-small) | Fastino | N/A | N/A | — | — | Estimated |
| [GLM Realtime Air](/models/glm-realtime-air) | Zhipu AI | N/A | N/A | — | — | Estimated |
| [GLM Realtime Flash](/models/glm-realtime-flash) | Zhipu AI | N/A | N/A | — | — | Estimated |
| [GLM-4-Voice](/models/glm-4-voice) | Zhipu AI | N/A | N/A | — | — | Estimated |
| [GPT Live Transcribe](/models/gpt-live-transcribe) | OpenAI | N/A | N/A | — | — | Estimated |
| [GPT Transcribe](/models/gpt-transcribe) | OpenAI | N/A | N/A | — | — | Estimated |
| [GPT-5.3-Codex-Spark](/models/gpt-5-3-codex-spark) | OpenAI | N/A | N/A | — | — | Estimated |
| [GPT-5.6 Cyber](/models/gpt-5-6-cyber) | OpenAI | N/A | N/A | — | — | Estimated |
| [GPT-5.6 Luna (low reasoning effort)](/models/jevbench-gpt-5-6-luna) | OpenAI | N/A | N/A | — | — | Estimated |
| [GPT-6 Luna (default medium reasoning effort)](/models/jevbench-gpt-6-luna) | OpenAI | N/A | N/A | — | — | Estimated |
| [GPT-6 Luna (low reasoning effort)](/models/jevbench-gpt-6-luna-low) | OpenAI | N/A | N/A | — | — | Estimated |
| [GPT-Live-1](/models/gpt-live-1) | OpenAI | N/A | N/A | — | — | Estimated |
| [Granite Speech 5.0 470M TurboCTC](/models/granite-speech-5-0-470m-turboctc) | IBM | N/A | N/A | — | — | Estimated |
| [Grok 4.1](/models/grok-4-1) | xAI | N/A | N/A | — | — | Estimated |
| [Grok 4.20 Multi-agent](/models/grok-4-20-multi-agent-beta) | xAI | N/A | N/A | — | — | Estimated |
| [Grok Realtime](/models/grok-realtime) | xAI | N/A | N/A | — | — | Estimated |
| [Grok Voice Think Fast 1.0](/models/grok-voice-think-fast-1-0) | xAI | N/A | N/A | — | — | Estimated |
| [Grok Voice Think Fast 2.0](/models/grok-voice-think-fast-2-0) | xAI | N/A | N/A | — | — | Estimated |
| [Grok Voice Transcribe 2.0](/models/grok-voice-transcribe-2) | xAI | N/A | N/A | — | — | Estimated |
| [Hark Handoff](/models/hark-handoff) | Hark | N/A | N/A | — | — | Estimated |
| [Holo3-35B-A3B](/models/holo3-35b-a3b) | H Company | N/A | N/A | — | — | Estimated |
| [Hopper](/models/jevbench-hopper) | HopitAI | N/A | N/A | — | — | Estimated |
| [Hy ASR 3.0 preview](/models/hy-asr-3-0-preview) | Tencent | N/A | N/A | — | — | Estimated |
| [Ichigo](/models/ichigo) | Jan | N/A | N/A | — | — | Estimated |
| [Imajev-4B](/models/jevbench-imajev-4b) | mohit67890 | N/A | N/A | — | — | Estimated |
| [Imajev-4B (RTX 5090)](/models/jevbench-imajev-4b-rtx5090-a2) | unknown | N/A | N/A | — | — | Estimated |
| [Instinct (ZooWork, Qwen3.8-27B)](/models/jevbench-instinct) | rayrain-srp (ZooWork) | N/A | N/A | — | — | Estimated |
| [Instinct Dual 4B](/models/jevbench-instinct-dual-4b) | ZooWork / pierre-srp | N/A | N/A | — | — | Estimated |
| [Inworld Realtime TTS-2](/models/inworld-tts-2) | Inworld | N/A | N/A | — | — | Estimated |
| [Inworld Realtime TTS-2 Flash](/models/inworld-tts-2-flash) | Inworld | N/A | N/A | — | — | Estimated |
| [jeff (Logan Markewich, GLiFormer 400M)](/models/jevbench-jeff) | Logan Markewich | N/A | N/A | — | — | Estimated |
| [Jev 1.13.0 (TypeSafe AI)](/models/jevbench-jev-1-13-0) | TypeSafe AI | N/A | N/A | — | — | Estimated |
| [JEV Qwen3.5-9B Base NVFP4](/models/jevbench-jev-qwen3-5-9b-base-nvfp4) | WilfLin | N/A | N/A | — | — | Estimated |
| [jev-local (Qwen3.5-9B)](/models/jevbench-jev-local) | us (GitHub) | N/A | N/A | — | — | Estimated |
| [Jev-Omni (akhilaaa3, Gemma-4-12B merged)](/models/jevbench-jev-omni) | akhilaaa3 | N/A | N/A | — | — | Estimated |
| [JevAct (einptein, jev1-2b-v2)](/models/jevbench-jevact) | einptein | N/A | N/A | — | — | Estimated |
| [JevK5 v0.2.0](/models/jevbench-jevk5-v02) | allebee | N/A | N/A | — | — | Estimated |
| [JevK5 v0.3 (4B)](/models/jevbench-jevk5-v0-3-4b) | unknown | N/A | N/A | — | — | Estimated |
| [JevOne](/models/jevbench-jevone) | Juspay | N/A | N/A | — | — | Estimated |
| [Jobe Qwen3.5-4B (frozen)](/models/jevbench-jobe-qwen3-5-4b) | MantisShrimpdev | N/A | N/A | — | — | Estimated |
| [jqv (Qwen3-32B zero-shot)](/models/jevbench-jqv) | hjmurmur (Octalab) | N/A | N/A | — | — | Estimated |
| [Kalpa TTS Beta v0.1](/models/kalpa-tts-beta-v0-1) | Kalpa Labs | N/A | N/A | — | — | Estimated |
| [kev 0.5B](/models/jevbench-kev-0-5b) | Jared Palmer | N/A | N/A | — | — | Estimated |
| [kev 0.6B (research preview)](/models/jevbench-kev-0-6b) | Jared Palmer | N/A | N/A | — | — | Estimated |
| [kev 4B (research preview)](/models/jevbench-kev-4b) | Jared Palmer | N/A | N/A | — | — | Estimated |
| [kev 8B (research preview)](/models/jevbench-kev-8b) | Jared Palmer | N/A | N/A | — | — | Estimated |
| [Kimi-Audio 7B](/models/kimi-audio-7b) | Moonshot AI | N/A | N/A | — | — | Estimated |
| [Kokoro 82M](/models/kokoro-82m) | hexgrad | N/A | N/A | — | — | Estimated |
| [Kyutai Pocket TTS](/models/kyutai-pocket-tts) | Kyutai | N/A | N/A | — | — | Estimated |
| [Laguna M.1](/models/laguna-m-1) | Poolside | N/A | N/A | — | — | Limited |
| [Laya (Convai Innovations, ModernBERT-large 421M)](/models/jevbench-laya) | Convai Innovations | N/A | N/A | — | — | Estimated |
| [Laya multilingual](/models/jevbench-laya-multilingual) | Convai Innovations | N/A | N/A | — | — | Estimated |
| [Laya typed-decisions](/models/jevbench-laya-typed-decisions) | Convai Innovations | N/A | N/A | — | — | Estimated |
| [lev-350m (Franck Verrot, LFM2.5-350M)](/models/jevbench-lev-350m) | Franck Verrot (franckverrot) | N/A | N/A | — | — | Estimated |
| [LFG-1](/models/lfg-1) | glenn2 | N/A | N/A | — | — | Estimated |
| [LFG-2](/models/lfg-2) | glenn2 | N/A | N/A | — | — | Estimated |
| [LFG-3](/models/lfg-3) | glenn2 | N/A | N/A | — | — | Estimated |
| [Ling 3.0 Flash Fin](/models/ling-3-0-flash-fin) | InclusionAI | N/A | N/A | — | — | Estimated |
| [Ling 3.0 Flash FP8](/models/ling-3-0-flash-fp8) | InclusionAI | N/A | N/A | — | — | Estimated |
| [Ling 3.1 Flash](/models/ling-3-1-flash) | InclusionAI | N/A | N/A | — | — | Estimated |
| [LitJev (Qwen3.8-27B)](/models/jevbench-litjev) | Zhengxu Yu | N/A | N/A | — | — | Estimated |
| [LLaMA-Omni](/models/llama-omni) | ICTNLP | N/A | N/A | — | — | Estimated |
| [local-jev Qwen3.5-4B](/models/jevbench-localjev-qwen3-5-4b) | Amith Chandrappa (amithgc) | N/A | N/A | — | — | Estimated |
| [Lyra Base](/models/lyra-base) | DVL Lab | N/A | N/A | — | — | Estimated |
| [Lyra Mini](/models/lyra-mini) | DVL Lab | N/A | N/A | — | — | Estimated |
| [MAI-Code-1.1-Flash](/models/mai-code-1-1-flash) | Microsoft | N/A | N/A | — | — | Estimated |
| [MAI-Cyber-1-Flash](/models/mai-cyber-1-flash) | Microsoft | N/A | N/A | — | — | Estimated |
| [MAI-Transcribe-1.5](/models/mai-transcribe-1-5) | Microsoft | N/A | N/A | — | — | Estimated |
| [MAI-Transcribe-2](/models/mai-transcribe-2) | Microsoft | N/A | N/A | — | — | Estimated |
| [MAI-Voice-2-Flash](/models/mai-voice-2-flash) | Microsoft | N/A | N/A | — | — | Estimated |
| [Mair-hub 0.5B Omni](/models/mair-hub-0-5b-omni) | Mair Hub | N/A | N/A | — | — | Estimated |
| [Malkuth-2B (newfull5, Kev post-train)](/models/jevbench-malkuth-2b) | newfull5 (dhtocks) | N/A | N/A | — | — | Estimated |
| [Malkuth-4B (newfull5, Kev post-train)](/models/jevbench-malkuth-4b) | newfull5 (dhtocks) | N/A | N/A | — | — | Estimated |
| [Manchego v2.1](/models/jevbench-manchego-v21-v15) | oraculumai | N/A | N/A | — | — | Estimated |
| [Megrez-3B-Omni](/models/megrez-3b-omni) | Infinigence AI | N/A | N/A | — | — | Estimated |
| [MERaLiON-AudioLLM](/models/meralion-audiollm) | AI Singapore | N/A | N/A | — | — | Estimated |
| [Mercury 2.5 Preview](/models/mercury-2-5-preview) | Inception | N/A | N/A | — | — | Estimated |
| [metask-jev-4b](/models/jevbench-metask-jev-4b) | Wayfind (metask-ai) | N/A | N/A | — | — | Estimated |
| [mica-v01-4b](/models/jevbench-mica-v01-4b) | unknown | N/A | N/A | — | — | Estimated |
| [MiMo-V2.5](/models/mimo-v2-5) | Xiaomi | N/A | N/A | — | — | Limited |
| [Mini-Omni 0.5B](/models/mini-omni) | gpt-omni | N/A | N/A | — | — | Estimated |
| [Mini-Omni2](/models/mini-omni2) | gpt-omni | N/A | N/A | — | — | Estimated |
| [MiniCPM-o 2.6](/models/minicpm-o-2-6) | OpenBMB | N/A | N/A | — | — | Estimated |
| [MiniMax M3.1 Flash Preview](/models/minimax-m3-1-flash-preview) | MiniMax | N/A | N/A | — | — | Estimated |
| [MiniMax Speech 2.8 HD](/models/minimax-speech-2-8-hd) | MiniMax | N/A | N/A | — | — | Estimated |
| [Mirror](/models/jevbench-mirror) | Bluusun | N/A | N/A | — | — | Estimated |
| [Mixedbread mxbai-rerank-base-v2](/models/jevbench-mxbai-rerank-base-v2) | Mixedbread | N/A | N/A | — | — | Estimated |
| [Moonshine Tiny](/models/moonshine-tiny) | Useful Sensors | N/A | N/A | — | — | Estimated |
| [Moonshot v1](/models/moonshot-v1) | Moonshot AI | N/A | N/A | — | — | Estimated |
| [Moshi 7B](/models/moshi-7b) | Kyutai | N/A | N/A | — | — | Estimated |
| [Murf Falcon 2](/models/murf-falcon-2) | Murf AI | N/A | N/A | — | — | Estimated |
| [Muse Voice Transcribe](/models/muse-voice-transcribe) | Meta | N/A | N/A | — | — | Estimated |
| [Needle 3 (Cactus, 2-bit, local CPU)](/models/jevbench-needle-3) | Cactus Compute | N/A | N/A | — | — | Estimated |
| [Needle 3, options as tools (post-hoc adapter mode)](/models/jevbench-needle-3-tools) | Cactus Compute | N/A | N/A | — | — | Estimated |
| [Nemotron 3.5 ASR Streaming 0.6B](/models/nemotron-3-5-asr-streaming-0-6b) | NVIDIA | N/A | N/A | — | — | Estimated |
| [Nemotron Diffusion 8B (pst2154, optimized vLLM)](/models/jevbench-nemotron-diffusion-8b) | pst2154 | N/A | N/A | — | — | Estimated |
| [NExT-GPT 7B](/models/next-gpt-7b) | NExT-GPT authors | N/A | N/A | — | — | Estimated |
| [NInfer Qwen3.8-27B NVFP4](/models/jevbench-ninfer-qwen3-8-27b) | Igor L. / NInfer contributors | N/A | N/A | — | — | Estimated |
| [NInfer Qwen3.8-27B NVFP4 (T=1.5)](/models/jevbench-ninfer-qwen3-8-27b-t1-5) | Igor L. / NInfer contributors | N/A | N/A | — | — | Estimated |
| [NInfer Qwen3.8-Flash-Next mixed](/models/jevbench-ninfer-qwen3-8-flash-next) | Igor L. / NInfer contributors | N/A | N/A | — | — | Estimated |
| [North Small Translate](/models/north-small-translate-1-0) | Cohere | N/A | N/A | — | — | Estimated |
| [o4-mini (high)](/models/o4-mini-high) | OpenAI | N/A | N/A | — | — | Estimated |
| [Ola](/models/ola-omni) | Ola-Omni | N/A | N/A | — | — | Estimated |
| [Open Jev JSON Canvas (JoshuaSP)](/models/jevbench-open-jev-json-canvas-joshuasp) | JoshuaSP | N/A | N/A | — | — | Estimated |
| [open-alternative-jev (Qwen3.5-4B, IkerMoel)](/models/jevbench-open-alternative-jev) | IkerMoel | N/A | N/A | — | — | Estimated |
| [Open-Jev 2B (Zefan Cai)](/models/jevbench-open-jev-zefan-2b) | Zefan Cai (@Zefan_Cai) | N/A | N/A | — | — | Estimated |
| [Open-Jev 9B (Zefan Cai)](/models/jevbench-open-jev-zefan-9b) | Zefan Cai (@Zefan_Cai) | N/A | N/A | — | — | Estimated |
| [open-jev-deberta-v3-large (local CPU)](/models/jevbench-open-jev-deberta-v3-large) | Kotoba Labs | N/A | N/A | — | — | Estimated |
| [OpenDecision (ModernBERT-large zero-shot)](/models/jevbench-opendecision) | Deepan Wadhwa | N/A | N/A | — | — | Estimated |
| [OpenJev (DiffusionGemma 26B-A4B NVFP4, razorback16)](/models/jevbench-openjev-razorback16) | razorback16 / Codiv | N/A | N/A | — | — | Estimated |
| [OpenJev (thinking, BF16)](/models/jevbench-openjev-thinking) | razorback16 | N/A | N/A | — | — | Estimated |
| [openJev Verdict (heman10x, ModernBERT-base 151M)](/models/jevbench-openjev-verdict) | Hemant (heman10x) | N/A | N/A | — | — | Estimated |
| [openJev Verdict 1.4](/models/jevbench-openjev-verdict-1-4) | Hemant (heman10x) | N/A | N/A | — | — | Estimated |
| [openjev-sglang (Qwen3.6-35B-A3B on SGLang)](/models/jevbench-openjev-sglang) | ekzhang | N/A | N/A | — | — | Estimated |
| [OpenSourceJev (Qwen3.5-4B Q4_K_M, native llama.cpp)](/models/jevbench-opensourcejev-qwen35-4b-q4km) | sabeel111 | N/A | N/A | — | — | Estimated |
| [PandaGPT 7B](/models/pandagpt-7b) | PandaGPT authors | N/A | N/A | — | — | Estimated |
| [Parakeet CTC 1.1B](/models/parakeet-ctc-1-1b) | NVIDIA | N/A | N/A | — | — | Estimated |
| [Parakeet Redux](/models/parakeet-redux) | Moondream | N/A | N/A | — | — | Estimated |
| [Parakeet TDT 0.6B v3](/models/parakeet-tdt-0-6b-v3) | NVIDIA | N/A | N/A | — | — | Estimated |
| [Phi-4 Multimodal Instruct](/models/phi-4-multimodal-instruct) | Microsoft | N/A | N/A | — | — | Estimated |
| [Phonon-1](/models/phonon-1) | Fermion Research | N/A | N/A | — | — | Estimated |
| [Phonon-2](/models/phonon-2) | Fermion Research | N/A | N/A | — | — | Estimated |
| [Plumb-4B (crh225, JevK5 v0.2 + LoRA)](/models/jevbench-plumb-4b) | crh225 | N/A | N/A | — | — | Estimated |
| [Qwen-Audio 7B](/models/qwen-audio-7b) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen-Audio-Chat 7B](/models/qwen-audio-chat-7b) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen2-Audio 7B Instruct](/models/qwen2-audio-7b-instruct) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen2.5-Omni 7B](/models/qwen2-5-omni-7b) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen3-ASR 0.6B](/models/qwen3-asr-0-6b) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen3-ASR 1.7B](/models/qwen3-asr-1-7b) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen3-Omni-30B-A3B-Thinking](/models/qwen3-omni-30b-a3b-thinking) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen3-Reranker-4B](/models/jevbench-qwen3-reranker-4b) | Qwen | N/A | N/A | — | — | Estimated |
| [Qwen3.5-0.8B Decision Model (Mourad Ghafiri)](/models/jevbench-mghafiri-qwen3-5-0-8b-decision-model) | Mourad Ghafiri | N/A | N/A | — | — | Estimated |
| [Qwen3.5-9B Jev-like data-mix v2](/models/jevbench-qwen35-9b-jev-data-mix-v2) | jsaurabh | N/A | N/A | — | — | Estimated |
| [Qwen3.8 27B (Chutes TEE)](/models/jevbench-qwen3-8-27b) | Qwen / Chutes | N/A | N/A | — | — | Estimated |
| [Qwen3.8 Max Preview](/models/qwen3-8-max-preview) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen3.8-Omni-Flash](/models/qwen3-8-omni-flash) | Alibaba | N/A | N/A | — | — | Limited |
| [Qwen4 27B](/models/qwen4-27b) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen4 Flash & Plus](/models/qwen4-flash-plus) | Alibaba | N/A | N/A | — | — | Estimated |
| [Qwen4 Max](/models/qwen4-max) | Alibaba | N/A | N/A | — | — | Estimated |
| [Raw Phi-4 mini direct logits](/models/jevbench-raw-phi-4-mini) | Microsoft / neutral reproduction | N/A | N/A | — | — | Estimated |
| [Raw Qwen3 0.6B direct logits](/models/jevbench-raw-qwen3-0-6b) | Alibaba Qwen / neutral reproduction | N/A | N/A | — | — | Estimated |
| [Raw Qwen3 1.7B direct logits](/models/jevbench-raw-qwen3-1-7b) | Alibaba Qwen / neutral reproduction | N/A | N/A | — | — | Estimated |
| [Raw Qwen3 4B Instruct 2507 direct logits](/models/jevbench-raw-qwen3-4b-instruct-2507) | Alibaba Qwen / neutral reproduction | N/A | N/A | — | — | Estimated |
| [Raw Qwen3 8B direct logits](/models/jevbench-raw-qwen3-8b) | Alibaba Qwen / neutral reproduction | N/A | N/A | — | — | Estimated |
| [reflex 4B (kshetrajna12)](/models/jevbench-reflex-4b) | kshetrajna12 | N/A | N/A | — | — | Estimated |
| [reflex-27b (Qwen3.8-27B)](/models/jevbench-reflex-27b) | kshetrajna12 | N/A | N/A | — | — | Estimated |
| [Sakana Fugu](/models/sakana-fugu) | Sakana AI | N/A | N/A | — | — | Limited |
| [Sakana Fugu-Ultra](/models/sakana-fugu-ultra) | Sakana AI | N/A | N/A | — | — | Limited |
| [SALMONN 13B](/models/salmonn-13b) | SALMONN authors | N/A | N/A | — | — | Estimated |
| [SALMONN 7B](/models/salmonn-7b) | SALMONN authors | N/A | N/A | — | — | Estimated |
| [Scribe v2.2 Realtime](/models/scribe-v2-2-realtime) | ElevenLabs | N/A | N/A | — | — | Estimated |
| [Seed 1.6](/models/seed-1-6) | ByteDance | N/A | N/A | — | — | Estimated |
| [Seed 1.6 Flash](/models/seed-1-6-flash) | ByteDance | N/A | N/A | — | — | Estimated |
| [Seed 2.1 Pro](/models/seed-2-1-pro) | ByteDance | N/A | N/A | — | — | Estimated |
| [Seed 2.1 Turbo](/models/seed-2-1-turbo) | ByteDance | N/A | N/A | — | — | Estimated |
| [Seed-2.0-Lite](/models/seed-2-0-lite) | ByteDance | N/A | N/A | — | — | Estimated |
| [Seed-2.0-Mini](/models/seed-2-0-mini) | ByteDance | N/A | N/A | — | — | Estimated |
| [SeedRealtime](/models/seedrealtime) | ByteDance | N/A | N/A | — | — | Estimated |
| [SemIf, formerly OpenJev (Qwen3.5-4B, TheoLeeCJ)](/models/jevbench-semif-qwen3-5-4b) | Theodore Lee (TheoLeeCJ) | N/A | N/A | — | — | Estimated |
| [SimpleJev (Qwen3.5-0.8B, CPU)](/models/jevbench-simplejev-qwen3-5-0-8b) | sabeel111 / Featherless AI | N/A | N/A | — | — | Estimated |
| [SimpleJev Qwen3.6-35B-A3B](/models/jevbench-simplejev-qwen3-6-35b-a3b) | Featherless AI | N/A | N/A | — | — | Estimated |
| [SimpleJev Qwen3.8-27B](/models/jevbench-simplejev-qwen3-8-27b) | Featherless AI | N/A | N/A | — | — | Estimated |
| [SLAM-Omni](/models/slam-omni) | X-LANCE | N/A | N/A | — | — | Estimated |
| [smalljev semantic-v9](/models/jevbench-smalljev) | Aditya (isHeSatoshi) | N/A | N/A | — | — | Estimated |
| [spark-s1-4b-v6 (Open Spark Jev, abhishek085)](/models/jevbench-spark-s1-4b-v6) | Abhishek Rai (abhishek085) | N/A | N/A | — | — | Estimated |
| [SpeechGPT 7B](/models/speechgpt-7b) | OpenMOSS | N/A | N/A | — | — | Estimated |
| [Standard One 8B (Standard Thinking)](/models/jevbench-standardone-8b) | Standard Thinking (myeongho12) | N/A | N/A | — | — | Estimated |
| [Step-Audio](/models/step-audio) | StepFun | N/A | N/A | — | — | Estimated |
| [Step-Audio-Chat 130B](/models/step-audio-chat-130b) | StepFun | N/A | N/A | — | — | Estimated |
| [Surogate Rune 26B-A4B v3 (RTX PRO 6000)](/models/jevbench-surogate-rune-26b-a4b-v3-rtxpro6000-a2) | unknown | N/A | N/A | — | — | Estimated |
| [swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4)](/models/jevbench-swanone) | blockbrain | N/A | N/A | — | — | Estimated |
| [SWE-2](/models/swe-2) | Cognition | N/A | N/A | — | — | Estimated |
| [system-one (Qwen3-8B, Sean Goedecke)](/models/jevbench-system-one-sg) | Sean Goedecke | N/A | N/A | — | — | Estimated |
| [system-one-open (Gemma 4 E2B LoRA on an L4)](/models/jevbench-system-one-open) | mithalouni | N/A | N/A | — | — | Estimated |
| [typecastlm (Mikhail Gribov, Qwen3.5-4B computed head)](/models/jevbench-typecastlm) | Mikhail Gribov | N/A | N/A | — | — | Estimated |
| [Ultravox GLM-4P6](/models/ultravox-glm-4p6) | Fixie AI | N/A | N/A | — | — | Estimated |
| [Ultravox GLM-4P7](/models/ultravox-glm-4p7) | Fixie AI | N/A | N/A | — | — | Estimated |
| [Ultravox v0.4.1 Llama 3.1 8B](/models/ultravox-v0-4-1-llama-3-1-8b) | Fixie AI | N/A | N/A | — | — | Estimated |
| [Ultravox v0.5 Llama 3.1 8B](/models/ultravox-v0-5-llama-3-1-8b) | Fixie AI | N/A | N/A | — | — | Estimated |
| [Ultravox v0.5 Llama 3.2 1B](/models/ultravox-v0-5-llama-3-2-1b) | Fixie AI | N/A | N/A | — | — | Estimated |
| [Ultravox v0.6 Llama 3.3 70B](/models/ultravox-v0-6-llama-3-3-70b) | Fixie AI | N/A | N/A | — | — | Estimated |
| [Ultravox v0.7](/models/ultravox-v0-7) | Fixie AI | N/A | N/A | — | — | Estimated |
| [verdict-small (Manavarya09, multilingual-e5-small 118M)](/models/jevbench-verdict-small) | Manavarya09 (Manav) | N/A | N/A | — | — | Estimated |
| [VibeVoice-ASR-Streaming 1.5B](/models/vibevoice-asr-streaming-1-5b) | Microsoft | N/A | N/A | — | — | Estimated |
| [VibeVoice-ASR-Streaming 7B](/models/vibevoice-asr-streaming-7b) | Microsoft | N/A | N/A | — | — | Estimated |
| [VITA 1.0](/models/vita-1-0) | VITA-MLLM | N/A | N/A | — | — | Estimated |
| [VITA 1.5](/models/vita-1-5) | VITA-MLLM | N/A | N/A | — | — | Estimated |
| [Von (wfzyx, Option-Marker 395M)](/models/jevbench-von-395m) | wfzyx (Victor Hugo) | N/A | N/A | — | — | Estimated |
| [Voxtral 4B TTS 2603](/models/voxtral-4b-tts-2603) | Mistral AI | N/A | N/A | — | — | Estimated |
| [Voxtral Mini 4B Realtime 2602](/models/voxtral-mini-4b-realtime-2602) | Mistral AI | N/A | N/A | — | — | Estimated |
| [Whisper large-v3-turbo](/models/whisper-large-v3-turbo) | OpenAI | N/A | N/A | — | — | Estimated |
| [Winnow-12B Q8](/models/jevbench-winnow-12b) | Eldan Ring | N/A | N/A | — | — | Estimated |
| [Wispr Canto](/models/wispr-canto) | Wispr | N/A | N/A | — | — | Estimated |
| [Z-1](/models/z-1) | Z | N/A | N/A | — | — | Estimated |
| [ZeroEntropy zerank-2](/models/jevbench-zerank-2) | ZeroEntropy | N/A | N/A | — | — | Estimated |
| [Zonos 2](/models/zonos-2) | Zyphra | N/A | N/A | — | — | Estimated |
| [GLM-5.3](/models/glm-5-3) | Z.AI | Free* | Free* | 65.66 | — | Limited |
| [Qwen3.8-Flash-Next](/models/qwen3-8-flash-next) | Alibaba | Free* | Free* | 64.49 | — | Good |
| [dots3-note Preview](/models/dots3-note-preview) | Dots Studio | Free* | Free* | 63.59 | — | Good |
| [Ornith-1.5-397B](/models/ornith-1-5-397b) | Ornith AI | Free* | Free* | 62.7 | — | Limited |
| [Hy4 preview](/models/hy4-preview) | Tencent | Free* | Free* | 61.09 | — | Limited |
| [GLM-5.3-Flash](/models/glm-5-3-flash) | Z.AI | Free* | Free* | 58.57 | — | Good |
| [Qwen3.8-27B](/models/qwen3-8-27b) | Alibaba | Free* | Free* | 57.56 | — | Good |
| [Ternary Bonsai 2 27B](/models/ternary-bonsai-2-27b) | Prism ML | Free* | Free* | 53.23 | — | Good |
| [Hy3](/models/hy3) | Tencent | Free* | Free* | ~53.22 | — | Estimated |
| [Hy3 Preview](/models/hy3-preview) | Tencent | Free* | Free* | 51.37 | — | Limited |
| [GLM-4.7](/models/glm-4-7) | Z.AI | Free* | Free* | 49.83 | — | Good |
| [Qwen3.6-27B](/models/qwen3-6-27b) | Alibaba | Free* | Free* | 49.3 | — | Full |
| [Qwen3.5-27B](/models/qwen3-5-27b) | Alibaba | Free* | Free* | 48.31 | — | Full |
| [Ling 3.0 Flash VL](/models/ling-3-0-flash-vl) | InclusionAI | Free* | Free* | 47.67 | — | Limited |
| [Qwen3.5-35B-A3B](/models/qwen3-5-35b-a3b) | Alibaba | Free* | Free* | 47.63 | — | Full |
| [Gemma 4 26B A4B](/models/gemma-4-26b-a4b) | Google | Free* | Free* | 46.88 | — | Limited |
| [Nemotron 3 Ultra](/models/nemotron-3-ultra) | NVIDIA | Free* | Free* | 45.35 | — | Good |
| [Muse Glimmer 30B](/models/muse-glimmer-30b) | Meta | Free* | Free* | 42.27 | — | Full |
| [DeepSeek V3.1](/models/deepseek-v3-1) | DeepSeek | Free* | Free* | ~41.88 | — | Estimated |
| [Qwen3.5-122B-A10B](/models/qwen3-5-122b-a10b) | Alibaba | Free* | Free* | 41.65 | — | Full |
| [MiMo-V2-Flash](/models/mimo-v2-flash) | Xiaomi | Free* | Free* | 41.61 | — | Limited |
| [Gemma 4 31B](/models/gemma-4-31b) | Google | Free* | Free* | 41.07 | — | Good |
| [GLM-4.7-Flash](/models/glm-4-7-flash) | Z.AI | Free* | Free* | ~39.78 | — | Estimated |
| [DeepSeek V3.1 (Reasoning)](/models/deepseek-v3-1-reasoning) | DeepSeek | Free* | Free* | ~39.24 | — | Estimated |
| [GPT-OSS 120B](/models/gpt-oss-120b) | OpenAI | Free* | Free* | 38.37 | — | Limited |
| [GPT-OSS 20B](/models/gpt-oss-20b) | OpenAI | Free* | Free* | 34.27 | — | Limited |
| [Ornith-1.5-35B-A3B](/models/ornith-1-5-35b-a3b) | Ornith AI | Free* | Free* | 32.56 | — | Limited |
| [DeepSeek R1 Distill Qwen 32B](/models/deepseek-r1-distill-qwen-32b) | DeepSeek | Free* | Free* | ~32.35 | — | Estimated |
| [Granite 4.2 8B](/models/granite-4-2-8b) | IBM | Free* | Free* | 32.13 | — | Limited |
| [ZAYA1-8B](/models/zaya1-8b) | Zyphra | Free* | Free* | 31.61 | — | Limited |
| [Gemma 4 E4B](/models/gemma-4-e4b) | Google | Free* | Free* | 31.47 | — | Limited |
| [Sarvam 105B](/models/sarvam-105b) | Sarvam | Free* | Free* | ~31.34 | — | Estimated |
| [Nemotron 3 Nano Omni 30B A3B](/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | Free* | Free* | 31.28 | — | Good |
| [LFM2.5-2.6B](/models/lfm2-5-2-6b) | LiquidAI | Free* | Free* | 30.95 | — | Limited |
| [Qwen2.5-72B](/models/qwen2-5-72b) | Alibaba | Free* | Free* | ~30.36 | — | Estimated |
| [Gemma 4 E2B](/models/gemma-4-e2b) | Google | Free* | Free* | 30.34 | — | Limited |
| [Llama 4 Scout](/models/llama-4-scout) | Meta | Free* | Free* | 30.09 | — | Limited |
| [Llama 3.1 405B](/models/llama-3-1-405b) | Meta | Free* | Free* | ~29.81 | — | Estimated |
| [LFM2.5-8B-A1B](/models/lfm2-5-8b-a1b) | LiquidAI | Free* | Free* | 29.76 | — | Limited |
| [Gemma 3 27B](/models/gemma-3-27b) | Google | Free* | Free* | 29.46 | — | Limited |
| [Sarvam 30B](/models/sarvam-30b) | Sarvam | Free* | Free* | ~29.11 | — | Estimated |
| [Ornith-1.5-9B](/models/ornith-1-5-9b) | Ornith AI | Free* | Free* | 28.6 | — | Limited |
| [Granite-4.0-H-1B](/models/granite-4-0-h-1b) | IBM | Free* | Free* | ~27.77 | — | Estimated |
| [Granite-4.0-350M](/models/granite-4-0-350m) | IBM | Free* | Free* | ~27.42 | — | Estimated |
| [Granite-4.0-H-350M](/models/granite-4-0-h-350m) | IBM | Free* | Free* | ~27.42 | — | Estimated |
| [Qwen2.5 Coder 32B Instruct](/models/qwen2-5-coder-32b-instruct) | Alibaba | Free* | Free* | ~27.09 | — | Estimated |
| [Phi-4](/models/phi-4) | Microsoft | Free* | Free* | ~26.37 | — | Estimated |
| [Llama 4 Maverick](/models/llama-4-maverick) | Meta | Free* | Free* | 23.58 | — | Limited |
| [Llama 3 70B](/models/llama-3-70b) | Meta | Free* | Free* | ~22.78 | — | Estimated |
| [LFM2-24B-A2B](/models/lfm2-24b-a2b) | LiquidAI | Free* | Free* | ~21.1 | — | Estimated |
| [Nemotron 3.5 Lightning 30B A3B NVFP4](/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | Free* | Free* | 20.13 | — | Good |
| [LFM2.5-1.2B-Thinking](/models/lfm2-5-1-2b-thinking) | LiquidAI | Free* | Free* | ~19.84 | — | Estimated |
| [Mixtral 8x22B Instruct v0.1](/models/mixtral-8x22b-instruct-v0-1) | Mistral | Free* | Free* | ~19.78 | — | Estimated |
| [LFM2.5-1.2B-Instruct](/models/lfm2-5-1-2b-instruct) | LiquidAI | Free* | Free* | ~19.59 | — | Estimated |
| [Nemotron-4 15B](/models/nemotron-4-15b) | NVIDIA | Free* | Free* | ~10.05 | — | Estimated |
| [Mistral 7B v0.3](/models/mistral-7b-v0-3) | Mistral | Free* | Free* | ~7.24 | — | Estimated |
| [1-bit Bonsai 1.7B](/models/bonsai-1-7b) | Prism ML | Free* | Free* | — | — | Estimated |
| [1-bit Bonsai 27B](/models/bonsai-27b) | Prism ML | Free* | Free* | — | — | Estimated |
| [1-bit Bonsai 4B](/models/bonsai-4b) | Prism ML | Free* | Free* | — | — | Estimated |
| [1-bit Bonsai 8B](/models/bonsai-8b) | Prism ML | Free* | Free* | — | — | Estimated |
| [A.X K2](/models/a-x-k2) | SK Telecom | Free* | Free* | — | — | Estimated |
| [Agents-A1-4B](/models/agents-a1-4b) | InternScience | Free* | Free* | — | — | Estimated |
| [Apodex 1.1 Mini](/models/apodex-1-1-mini) | Apodex | Free* | Free* | — | — | Estimated |
| [Atria Dawn Preview](/models/atria-dawn-preview) | Shanghai Artificial Intelligence Laboratory | Free* | Free* | — | — | Estimated |
| [BTL-3](/models/btl-3) | Bad Theory Labs | Free* | Free* | — | — | Estimated |
| [BTL-4](/models/btl-4) | Bad Theory Labs | Free* | Free* | — | — | Estimated |
| [BTL-4 Compact](/models/btl-4-compact) | Bad Theory Labs | Free* | Free* | — | — | Estimated |
| [Cosmos3-Edge](/models/cosmos3-edge) | NVIDIA | Free* | Free* | — | — | Estimated |
| [DBRX Instruct](/models/dbrx-instruct) | Databricks | Free* | Free* | — | — | Estimated |
| [DeepSeek LLM 2.0](/models/deepseek-llm-2-0) | DeepSeek | Free* | Free* | — | — | Estimated |
| [DeepSeekMath V2](/models/deepseekmath-v2) | DeepSeek | Free* | Free* | — | — | Estimated |
| [Fara1.5-27B](/models/fara-1-5-27b) | Microsoft | Free* | Free* | — | — | Estimated |
| [Fara1.5-4B](/models/fara-1-5-4b) | Microsoft | Free* | Free* | — | — | Estimated |
| [Granite 4.2 30B](/models/granite-4-2-30b) | IBM | Free* | Free* | — | — | Estimated |
| [Granite 4.2 3B](/models/granite-4-2-3b) | IBM | Free* | Free* | — | — | Estimated |
| [Granite-4.0-1B](/models/granite-4-0-1b) | IBM | Free* | Free* | — | — | Estimated |
| [Holo3.1-0.8B](/models/holo3-1-0-8b) | H Company | Free* | Free* | — | — | Estimated |
| [Holo3.1-35B-A3B-FP8](/models/holo3-1-35b-a3b-fp8) | H Company | Free* | Free* | — | — | Estimated |
| [Holo3.1-35B-A3B-GGUF](/models/holo3-1-35b-a3b-gguf) | H Company | Free* | Free* | — | — | Estimated |
| [Holo3.1-35B-A3B-NVFP4](/models/holo3-1-35b-a3b-nvfp4) | H Company | Free* | Free* | — | — | Estimated |
| [Holo3.1-4B](/models/holo3-1-4b) | H Company | Free* | Free* | — | — | Estimated |
| [Holo3.1-9B](/models/holo3-1-9b) | H Company | Free* | Free* | — | — | Estimated |
| [Hy-MT2-1.8B](/models/hy-mt2-1-8b) | Tencent | Free* | Free* | — | — | Estimated |
| [Hy-MT2-30B-A3B](/models/hy-mt2-30b-a3b) | Tencent | Free* | Free* | — | — | Estimated |
| [K-EXAONE 2.0](/models/k-exaone-2-0) | LG AI Research | Free* | Free* | — | — | Estimated |
| [Kanana-2 1.3B Instruct](/models/kanana-2-1-3b-instruct) | Kakao | Free* | Free* | — | — | Estimated |
| [Kanana-2 3B Instruct](/models/kanana-2-3b-instruct) | Kakao | Free* | Free* | — | — | Estimated |
| [Laguna XS.2](/models/laguna-xs-2) | Poolside | Free* | Free* | — | — | Limited |
| [Leanstral](/models/leanstral) | Mistral | Free* | Free* | — | — | Estimated |
| [Leanstral 1.5](/models/leanstral-1-5) | Mistral | Free* | Free* | — | — | Estimated |
| [LFM2.5-230M](/models/lfm2-5-230m) | LiquidAI | Free* | Free* | — | — | Estimated |
| [LFM2.5-350M](/models/lfm2-5-350m) | LiquidAI | Free* | Free* | — | — | Estimated |
| [LFM2.5-ColBERT-350M](/models/lfm2-5-colbert-350m) | LiquidAI | Free* | Free* | — | — | Estimated |
| [LFM2.5-Embedding-350M](/models/lfm2-5-embedding-350m) | LiquidAI | Free* | Free* | — | — | Estimated |
| [LFM2.5-VL-3B](/models/lfm2-5-vl-3b) | LiquidAI | Free* | Free* | — | — | Estimated |
| [LFM2.5-VL-450M](/models/lfm2-5-vl-450m) | LiquidAI | Free* | Free* | — | — | Estimated |
| [Ling 3.0 Tiny](/models/ling-3-0-tiny) | InclusionAI | Free* | Free* | — | — | Estimated |
| [LLaDA2.2-flash](/models/llada2-2-flash) | InclusionAI | Free* | Free* | — | — | Estimated |
| [LLaDA2.2-mini](/models/llada2-2-mini) | InclusionAI | Free* | Free* | — | — | Estimated |
| [Llama 4 Behemoth](/models/llama-4-behemoth) | Meta | Free* | Free* | — | — | Estimated |
| [LongCat-2.0](/models/longcat-2-0) | Meituan | Free* | Free* | — | — | Estimated |
| [LongCat-Flash-Lite-Sparse](/models/longcat-flash-lite-sparse) | Meituan | Free* | Free* | — | — | Estimated |
| [Macaw](/models/macaw-v1) | Bad Theory Labs | Free* | Free* | — | — | Estimated |
| [MiniCPM5-2B](/models/minicpm5-2b) | OpenBMB | Free* | Free* | — | — | Estimated |
| [Mistral 8x7B](/models/mistral-8x7b) | Mistral | Free* | Free* | — | — | Estimated |
| [Mistral 8x7B v0.2](/models/mistral-8x7b-v0-2) | Mistral | Free* | Free* | — | — | Estimated |
| [Nemotron 3 Nano 30B](/models/nemotron-3-nano-30b) | NVIDIA | Free* | Free* | — | — | Estimated |
| [Nemotron 3 Super 100B](/models/nemotron-3-super-100b) | NVIDIA | Free* | Free* | — | — | Estimated |
| [Nemotron 3 Super 120B A12B](/models/nemotron-3-super-120b-a12b) | NVIDIA | Free* | Free* | — | — | Estimated |
| [Nemotron Ultra 253B](/models/nemotron-ultra-253b) | NVIDIA | Free* | Free* | — | — | Estimated |
| [North Micro Vision Instruct](/models/north-micro-vision-instruct) | Cohere | Free* | Free* | — | — | Estimated |
| [North Mini Code](/models/north-mini-code-1-0) | Cohere | Free* | Free* | — | — | Estimated |
| [Ornith-1.0-35B](/models/ornith-1-0-35b) | DeepReinforce AI | Free* | Free* | — | — | Estimated |
| [Ornith-1.0-397B](/models/ornith-1-0-397b) | DeepReinforce AI | Free* | Free* | — | — | Estimated |
| [Ornith-1.0-9B](/models/ornith-1-0-9b) | DeepReinforce AI | Free* | Free* | — | — | Estimated |
| [Qwen-AgentWorld-35B-A3B](/models/qwen-agentworld-35b-a3b) | Alibaba | Free* | Free* | — | — | Estimated |
| [Qwen2.5-1M](/models/qwen2-5-1m) | Alibaba | Free* | Free* | — | — | Estimated |
| [Qwen2.5-VL-32B](/models/qwen2-5-vl-32b) | Alibaba | Free* | Free* | — | — | Estimated |
| [Qwen3 235B 2507](/models/qwen3-235b-2507) | Alibaba | Free* | Free* | — | — | Estimated |
| [Qwen3 235B 2507 (Reasoning)](/models/qwen3-235b-2507-reasoning) | Alibaba | Free* | Free* | — | — | Estimated |
| [Solar Open 2](/models/solar-open-2) | Upstage | Free* | Free* | — | — | Estimated |
| [Soofi S 30B-A3B](/models/soofi-s-30b-a3b) | Soofi Project | Free* | Free* | — | — | Estimated |
| [Ternary Bonsai 1.7B](/models/ternary-bonsai-1-7b) | Prism ML | Free* | Free* | — | — | Estimated |
| [Ternary Bonsai 27B](/models/ternary-bonsai-27b) | Prism ML | Free* | Free* | — | — | Estimated |
| [Ternary Bonsai 4B](/models/ternary-bonsai-4b) | Prism ML | Free* | Free* | — | — | Estimated |
| [Ternary Bonsai 8B](/models/ternary-bonsai-8b) | Prism ML | Free* | Free* | — | — | Estimated |
| [UI-Mate-27B](/models/ui-mate-27b) | Tencent | Free* | Free* | — | — | Estimated |
| [UI-Mate-9B](/models/ui-mate-9b) | Tencent | Free* | Free* | — | — | Estimated |
| [ZAYA1-74B-Preview](/models/zaya1-74b-preview) | Zyphra | Free* | Free* | — | — | Estimated |
| [ZAYA1-VL-8B](/models/zaya1-vl-8b) | Zyphra | Free* | Free* | — | — | Estimated |

*Free/open-weight rows still require self-hosted or third-party infrastructure.*


Canonical page: https://benchlm.ai/llm-pricing