# Best Proprietary LLMs (2026)

> Top proprietary/closed-source AI models ranked by benchmark performance.

Canonical page: https://benchlm.ai/best/proprietary

Last updated: September 29, 2026

## Rankings

| Rank | Model | Creator | Type | Context | Score |
|------|-------|---------|------|---------|-------|
| 1 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | Proprietary | 1.05M | 88.2 |
| 2 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | Proprietary | 1M | 86.9 |
| 3 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | Proprietary | 1M | 82.5 |
| 4 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | Proprietary | 1M | 80.9 |
| 5 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | Proprietary | null | 79.2 |
| 6 | [Claude Fable 5](/models/claude-fable) | Anthropic | Proprietary | 1M+ | 78.6 |
| 7 | [GPT-6 Sol](/models/gpt-6-sol) | OpenAI | Proprietary | 1.05M | 78.6 |
| 8 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | Proprietary | 1.05M | 78.2 |
| 9 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | Proprietary | 1M | 73.3 |
| 10 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | OpenAI | Proprietary | 1.05M | 72.4 |
| 11 | [GPT-5.5 Pro](/models/gpt-5-5-pro) | OpenAI | Proprietary | 1M | 72.2 |
| 12 | [GPT-5.4 Pro](/models/gpt-5-4-pro) | OpenAI | Proprietary | 1.05M | 70.7 |
| 13 | [Claude Opus 4.8](/models/claude-opus-4-8) | Anthropic | Proprietary | 1M | 70.2 |
| 14 | [Grok 4.6](/models/grok-4-6) | xAI | Proprietary | 500K | 68.8 |
| 15 | [GPT-5.5](/models/gpt-5-5) | OpenAI | Proprietary | 1M | 68.8 |
| 16 | [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) | Anthropic | Proprietary | 1M | 68.5 |
| 17 | [GPT-5.4](/models/gpt-5-4) | OpenAI | Proprietary | 1.05M | 68.2 |
| 18 | [Gemini 3.7 Flash](/models/gemini-3-7-flash) | Google | Proprietary | 1M | 67.3 |
| 19 | [GPT-6.1 Sol](/models/gpt-6-1-sol) | OpenAI | Proprietary | 1.05M | 66.9 |
| 20 | [GPT-5.2 Pro](/models/gpt-5-2-pro) | OpenAI | Proprietary | 400K | 66.7 |
| 21 | [Claude Sonnet 5](/models/claude-sonnet-5) | Anthropic | Proprietary | 1M | 66.7 |
| 22 | [Claude Opus 4.7](/models/claude-opus-4-7) | Anthropic | Proprietary | 1M | 66.3 |
| 23 | [GPT-6 Luna](/models/gpt-6-luna) | OpenAI | Proprietary | 1.05M | 66.1 |
| 24 | [Muse Spark 1.1](/models/muse-spark-1-1) | Meta | Proprietary | 1M | 65.8 |
| 25 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | OpenAI | Proprietary | 1.05M | 65.4 |
| 26 | [Grok 4.5](/models/grok-4-5) | xAI | Proprietary | 500K | 64.9 |
| 27 | [Muse Spark 1.2](/models/muse-spark-1-2) | Meta | Proprietary | 1M | 64.6 |
| 28 | [Gemini 3.1 Pro](/models/gemini-3-1-pro) | Google | Proprietary | 1M | 64.4 |
| 29 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | Google | Proprietary | 1M | 64.4 |
| 30 | [Claude Opus 4.6](/models/claude-opus-4-6) | Anthropic | Proprietary | 1M | 63.5 |
| 31 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | Proprietary | 1M | 63.2 |
| 32 | [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | Proprietary | 1M | 63.2 |
| 33 | [GPT-5.3 Codex](/models/gpt-5-3-codex) | OpenAI | Proprietary | 400K | 61.8 |
| 34 | [GPT-5.2](/models/gpt-5-2) | OpenAI | Proprietary | 400K | 61.2 |
| 35 | [Gemini 3 Pro](/models/gemini-3-pro) | Google | Proprietary | 2M | 60.8 |
| 36 | [Muse Spark](/models/muse-spark) | Meta | Proprietary | 262K | 60.6 |
| 37 | [Grok 4.20](/models/grok-4-20-beta) | xAI | Proprietary | 2M | 59.7 |
| 38 | [GPT-5.1](/models/gpt-5-1) | OpenAI | Proprietary | 200K | 58.2 |
| 39 | [Claude Sonnet 4.6](/models/claude-sonnet-4-6) | Anthropic | Proprietary | 200K | 56.1 |
| 40 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | Proprietary | 1M | 55.7 |
| 41 | [Gemini 3 Flash](/models/gemini-3-flash) | Google | Proprietary | 1M | 55.5 |
| 42 | [Qwen 3.6 Max (preview)](/models/qwen3-6-max-preview) | Alibaba | Proprietary | 256K | 55 |
| 43 | [Claude Opus 4.5](/models/claude-opus-4-5) | Anthropic | Proprietary | 200K | 54.9 |
| 44 | [GPT-5.4 mini](/models/gpt-5-4-mini) | OpenAI | Proprietary | 400K | 54.9 |
| 45 | [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) | Anthropic | Proprietary | 200K | 54.7 |
| 46 | [Grok 4.3](/models/grok-4-3) | xAI | Proprietary | 1M | 54.6 |
| 47 | [Qwen3.6 Plus](/models/qwen3-6-plus) | Alibaba | Proprietary | 1M | 54.4 |
| 48 | [Grok 4](/models/grok-4) | xAI | Proprietary | 128K | 52.6 |
| 49 | [GLM-5-Turbo](/models/glm-5-turbo) | Z.AI | Proprietary | 200K | 52.4 |
| 50 | [MiMo-V2-Pro](/models/mimo-v2-pro) | Xiaomi | Proprietary | 1M | 52.2 |
| 51 | [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) | Xiaomi | Proprietary | 1M | 51.8 |
| 52 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | Google | Proprietary | 1M | 50.9 |
| 53 | [GPT-5.4 nano](/models/gpt-5-4-nano) | OpenAI | Proprietary | 400K | 50.7 |
| 54 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | Google | Proprietary | 1M | 50.2 |
| 55 | [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite) | Google | Proprietary | 1M | 50 |
| 56 | [GPT-5.2-Codex](/models/gpt-5-2-codex) | OpenAI | Proprietary | 400K | 49.9 |
| 57 | [MiniMax M2.5](/models/minimax-m2-5) | MiniMax | Proprietary | 128K | 49.7 |
| 58 | [MiMo-V2-Omni](/models/mimo-v2-omni) | Xiaomi | Proprietary | 262K | 49 |
| 59 | [Qwen3.5 Plus](/models/qwen3-5-plus) | Alibaba | Proprietary | 1M | 48.9 |
| 60 | [GLM-5V-Turbo](/models/glm-5v-turbo) | Z.AI | Proprietary | 200K | 48.6 |
| 61 | [Claude Sonnet 4.5](/models/claude-sonnet-4-5) | Anthropic | Proprietary | 200K | 47.9 |
| 62 | [Qwen3.7 Flash](/models/qwen3-7-flash) | Alibaba | Proprietary | 1M | 47.5 |
| 63 | [o3-pro](/models/o3-pro) | OpenAI | Proprietary | 200K | 47.1 |
| 64 | [o3](/models/o3) | OpenAI | Proprietary | 200K | 47 |
| 65 | [Quasar 438B](/models/quasar-438b) | Multiverse Computing | Proprietary | 1M | 46.1 |
| 66 | [Apodex 1.1](/models/apodex-1-1) | Apodex | Proprietary | N/A | 45.9 |
| 67 | [Qwen3.5 Flash](/models/qwen3-5-flash) | Alibaba | Proprietary | 1M | 45.5 |
| 68 | [Grok 4.1 Fast (Reasoning)](/models/grok-4-1-fast-reasoning) | xAI | Proprietary | 2M | 45.4 |
| 69 | [Grok 3 [Beta]](/models/grok-3-beta) | xAI | Proprietary | 128K | 45.1 |
| 70 | [GPT-5 (medium)](/models/gpt-5-medium) | OpenAI | Proprietary | 128K | 44.6 |
| 71 | [GPT-5.1-Codex](/models/gpt-5-1-codex) | OpenAI | Proprietary | 400K | 44.4 |
| 72 | [GPT-5 mini](/models/gpt-5-mini) | OpenAI | Proprietary | 128K | 44 |
| 73 | [Grok 3 Mini](/models/grok-3-mini) | xAI | Proprietary | 128K | 43.8 |
| 74 | [Gemini 2.5 Flash](/models/gemini-2-5-flash) | Google | Proprietary | 1M | 43 |
| 75 | [Claude Haiku 4.5](/models/claude-haiku-4-5) | Anthropic | Proprietary | 200K | 42.5 |
| 76 | [Grok 4 Fast (Reasoning)](/models/grok-4-fast-reasoning) | xAI | Proprietary | 2M | 42.2 |
| 77 | [o3-mini](/models/o3-mini) | OpenAI | Proprietary | 200K | 40.1 |
| 78 | [GPT-4.1](/models/gpt-4-1) | OpenAI | Proprietary | 1M | 39.7 |
| 79 | [Qwen3 Max](/models/qwen3-max) | Alibaba | Proprietary | 1M | 39 |
| 80 | [Claude 4.1 Opus](/models/claude-4-1-opus) | Anthropic | Proprietary | 200K | 38.3 |
| 81 | [o1](/models/o1) | OpenAI | Proprietary | 200K | 37.5 |
| 82 | [K-Exaone](/models/k-exaone) | LG AI Research | Proprietary | 256K | 37.1 |
| 83 | [Claude 4.1 Opus Thinking](/models/claude-4-1-opus-thinking) | Anthropic | Proprietary | 200K | 36.4 |
| 84 | [o1-preview](/models/o1-preview) | OpenAI | Proprietary | 200K | 36.3 |
| 85 | [Grok 4.1 Fast](/models/grok-4-1-fast) | xAI | Proprietary | 1M | 36.3 |
| 86 | [Claude 4 Sonnet](/models/claude-4-sonnet) | Anthropic | Proprietary | 200K | 35.9 |
| 87 | [o1-pro](/models/o1-pro) | OpenAI | Proprietary | 200K | 35.7 |
| 88 | [GPT-5 nano](/models/gpt-5-nano) | OpenAI | Proprietary | 400K | 35 |
| 89 | [GLM-4.5-Air](/models/glm-4-5-air) | Z.AI | Proprietary | 128K | 34.6 |
| 90 | [Mercury 2.5](/models/mercury-2-5) | Inception | Proprietary | 260K | 34.3 |
| 91 | [Mercury 2](/models/mercury-2) | Inception | Proprietary | 128K | 34.2 |
| 92 | [Mistral Large 3](/models/mistral-large-3) | Mistral | Proprietary | 128K | 34.1 |
| 93 | [Solar Pro 3](/models/solar-pro-3) | Upstage | Proprietary | 128K | 32.4 |
| 94 | [Grok Code Fast 1](/models/grok-code-fast-1) | xAI | Proprietary | 256K | 31.9 |
| 95 | [Solar Pro 2](/models/solar-pro-2) | Upstage | Proprietary | 128K | 31.8 |
| 96 | [Celeris-1](/models/celeris-1) | Celeris | Proprietary | 128K | 31.4 |
| 97 | [GPT-4o](/models/gpt-4o) | OpenAI | Proprietary | 128K | 30.7 |
| 98 | [Claude 3.5 Sonnet](/models/claude-3-5-sonnet) | Anthropic | Proprietary | 200K | 30 |
| 99 | [GPT-4.1 mini](/models/gpt-4-1-mini) | OpenAI | Proprietary | 1M | 29.1 |
| 100 | [Mistral Large 2](/models/mistral-large-2) | Mistral | Proprietary | 128K | 29 |
| 101 | [Claude 3 Opus](/models/claude-3-opus) | Anthropic | Proprietary | 200K | 28.6 |
| 102 | [Mistral Medium 3](/models/mistral-medium-3) | Mistral | Proprietary | 128K | 28.3 |
| 103 | [Gemini 1.5 Pro](/models/gemini-1-5-pro) | Google | Proprietary | 2M | 27.9 |
| 104 | [GPT-4o mini](/models/gpt-4o-mini) | OpenAI | Proprietary | 128K | 26.9 |
| 105 | [Kimi K2](/models/kimi-k2) | Moonshot AI | Proprietary | 128K | 26.3 |
| 106 | [GPT-4.1 nano](/models/gpt-4-1-nano) | OpenAI | Proprietary | 1M | 24.9 |
| 107 | [MiniMax M1 80k](/models/minimax-m1-80k) | MiniMax | Proprietary | 80K | 24.8 |
| 108 | [GPT-4 Turbo](/models/gpt-4-turbo) | OpenAI | Proprietary | 128K | 21.6 |
| 109 | [Nova Pro](/models/nova-pro) | Amazon | Proprietary | 128K | 20.8 |
| 110 | [LFM2-24B-A2B](/models/lfm2-24b-a2b) | LiquidAI | Proprietary | 32K | 19.9 |
| 111 | [LFM2.5-1.2B-Thinking](/models/lfm2-5-1-2b-thinking) | LiquidAI | Proprietary | 32K | 18.7 |
| 112 | [LFM2.5-1.2B-Instruct](/models/lfm2-5-1-2b-instruct) | LiquidAI | Proprietary | 32K | 18.3 |
| 113 | [Claude 3 Haiku](/models/claude-3-haiku) | Anthropic | Proprietary | 200K | 14.8 |
| 114 | [Gemini 1.0 Pro](/models/gemini-1-0-pro) | Google | Proprietary | 32K | 13 |

## Key Takeaways

- Top model: [GPT-6 Astra](/models/gpt-6-astra) with a score of 88.2
- Models included: 114

## Compare the Leaders

- [GPT-6 Astra vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-gpt-6-astra)