# Best Non-Reasoning LLMs (2026)

> Top standard AI models (no chain-of-thought reasoning) ranked by benchmark performance. Faster and cheaper than reasoning models.

Canonical page: https://benchlm.ai/best/non-reasoning-models

Last updated: September 22, 2026

## Rankings

| Rank | Model | Creator | Type | Context | Score |
|------|-------|---------|------|---------|-------|
| 1 | [Claude Opus 4.7](/models/claude-opus-4-7) | Anthropic | Proprietary | 1M | 66.4 |
| 2 | [Claude Opus 4.6](/models/claude-opus-4-6) | Anthropic | Proprietary | 1M | 64.3 |
| 3 | [Gemini 3 Pro](/models/gemini-3-pro) | Google | Proprietary | 2M | 61.3 |
| 4 | [Claude Sonnet 4.6](/models/claude-sonnet-4-6) | Anthropic | Proprietary | 200K | 56.7 |
| 5 | [Inkling-Small](/models/inkling-small) | Thinking Machines Lab | Open Weight | 1M | 55.9 |
| 6 | [Claude Opus 4.5](/models/claude-opus-4-5) | Anthropic | Proprietary | 200K | 55.9 |
| 7 | [Gemini 3 Flash](/models/gemini-3-flash) | Google | Proprietary | 1M | 55.6 |
| 8 | [GLM-5](/models/glm-5) | Z.AI | Open Weight | 200K | 55.4 |
| 9 | [MiniMax M3](/models/minimax-m3) | MiniMax | Open Weight | 1M | 55.3 |
| 10 | [Inkling](/models/inkling) | Thinking Machines Lab | Open Weight | 1M | 54.4 |
| 11 | [Kimi K2.5](/models/kimi-k2-5) | Moonshot AI | Open Weight | 256K | 53.8 |
| 12 | [Grok 4](/models/grok-4) | xAI | Proprietary | 128K | 52.7 |
| 13 | [Gemini 2.5 Pro](/models/gemini-2-5-pro) | Google | Proprietary | 1M | 50.4 |
| 14 | [DeepSeek V3.2](/models/deepseek-v3-2) | DeepSeek | Open Weight | 128K | 50.2 |
| 15 | [MiniMax M2.5](/models/minimax-m2-5) | MiniMax | Proprietary | 128K | 49.9 |
| 16 | [GLM-5V-Turbo](/models/glm-5v-turbo) | Z.AI | Proprietary | 200K | 48.9 |
| 17 | [MiniMax M2.7](/models/minimax-m2-7) | MiniMax | Open Weight | 200K | 48.5 |
| 18 | [Claude Sonnet 4.5](/models/claude-sonnet-4-5) | Anthropic | Proprietary | 200K | 47.9 |
| 19 | [Gemini 3.1 Flash-Lite](/models/gemini-3-1-flash-lite) | Google | Proprietary | 1M | 47.5 |
| 20 | [Grok 3 [Beta]](/models/grok-3-beta) | xAI | Proprietary | 128K | 45 |
| 21 | [Gemini 2.5 Flash](/models/gemini-2-5-flash) | Google | Proprietary | 1M | 43 |
| 22 | [Claude Haiku 4.5](/models/claude-haiku-4-5) | Anthropic | Proprietary | 200K | 41.6 |
| 23 | [DeepSeek V3.1](/models/deepseek-v3-1) | DeepSeek | Open Weight | 128K | 41.2 |
| 24 | [Step 3.5 Flash](/models/step-3-5-flash) | StepFun | Open Weight | 256K | 41.1 |
| 25 | [GPT-4.1](/models/gpt-4-1) | OpenAI | Proprietary | 1M | 40 |
| 26 | [Claude 4.1 Opus](/models/claude-4-1-opus) | Anthropic | Proprietary | 200K | 38.5 |
| 27 | [GPT-OSS 120B](/models/gpt-oss-120b) | OpenAI | Open Weight | 128K | 37.7 |
| 28 | [Grok 4.1 Fast](/models/grok-4-1-fast) | xAI | Proprietary | 1M | 36.3 |
| 29 | [Claude 4 Sonnet](/models/claude-4-sonnet) | Anthropic | Proprietary | 200K | 36.1 |
| 30 | [GLM-4.5-Air](/models/glm-4-5-air) | Z.AI | Proprietary | 128K | 34.6 |
| 31 | [Mistral Small 4](/models/mistral-small-4) | Mistral | Open Weight | 256K | 34.3 |
| 32 | [Mistral Large 3](/models/mistral-large-3) | Mistral | Proprietary | 128K | 34.1 |
| 33 | [Ling 2.6 Flash](/models/ling-2-6-flash) | InclusionAI | Open Weight | 262K | 33.7 |
| 34 | [GPT-OSS 20B](/models/gpt-oss-20b) | OpenAI | Open Weight | 128K | 33.6 |
| 35 | [Grok Code Fast 1](/models/grok-code-fast-1) | xAI | Proprietary | 256K | 32 |
| 36 | [DeepSeek V3](/models/deepseek-v3) | DeepSeek | Open Weight | 128K | 31.8 |
| 37 | [Qwen2.5-72B](/models/qwen2-5-72b) | Alibaba | Open Weight | 128K | 31.3 |
| 38 | [Qwen3-Omni-30B-A3B-Instruct](/models/qwen3-omni-30b-a3b-instruct) | Alibaba | Open Weight | N/A | 31.1 |
| 39 | [Llama 3.1 405B](/models/llama-3-1-405b) | Meta | Open Weight | 128K | 30.8 |
| 40 | [GPT-4o](/models/gpt-4o) | OpenAI | Proprietary | 128K | 30.7 |
| 41 | [Exaone 4.0 1.2B](/models/exaone-4-0-1-2b) | LG AI Research | Open Weight | 128K | 30.5 |
| 42 | [Granite-4.0-H-1B](/models/granite-4-0-h-1b) | IBM | Open Weight | 128K | 30.5 |
| 43 | [Granite-4.0-350M](/models/granite-4-0-350m) | IBM | Open Weight | 32K | 30.2 |
| 44 | [Granite-4.0-H-350M](/models/granite-4-0-h-350m) | IBM | Open Weight | 32K | 30.2 |
| 45 | [Claude 3.5 Sonnet](/models/claude-3-5-sonnet) | Anthropic | Proprietary | 200K | 29.8 |
| 46 | [Llama 4 Scout](/models/llama-4-scout) | Meta | Open Weight | 10M | 29.3 |
| 47 | [Mistral Large 2](/models/mistral-large-2) | Mistral | Proprietary | 128K | 29 |
| 48 | [Gemma 3 27B](/models/gemma-3-27b) | Google | Open Weight | 32K | 28.7 |
| 49 | [GPT-4.1 mini](/models/gpt-4-1-mini) | OpenAI | Proprietary | 1M | 28.7 |
| 50 | [Claude 3 Opus](/models/claude-3-opus) | Anthropic | Proprietary | 200K | 28.6 |
| 51 | [Mistral Medium 3](/models/mistral-medium-3) | Mistral | Proprietary | 128K | 28.3 |
| 52 | [Gemini 1.5 Pro](/models/gemini-1-5-pro) | Google | Proprietary | 2M | 27.9 |
| 53 | [Qwen2.5 Coder 32B Instruct](/models/qwen2-5-coder-32b-instruct) | Alibaba | Open Weight | 128K | 27.1 |
| 54 | [GPT-4o mini](/models/gpt-4o-mini) | OpenAI | Proprietary | 128K | 26.8 |
| 55 | [Kimi K2](/models/kimi-k2) | Moonshot AI | Proprietary | 128K | 26.4 |
| 56 | [Phi-4](/models/phi-4) | Microsoft | Open Weight | 16K | 25.9 |
| 57 | [Ministral 3 14B](/models/ministral-3-14b) | Mistral | Open Weight | 128K | 25.2 |
| 58 | [MiniMax M1 80k](/models/minimax-m1-80k) | MiniMax | Proprietary | 80K | 24.9 |
| 59 | [GPT-4.1 nano](/models/gpt-4-1-nano) | OpenAI | Proprietary | 1M | 24.3 |
| 60 | [Llama 3 70B](/models/llama-3-70b) | Meta | Open Weight | 128K | 23.6 |
| 61 | [Llama 4 Maverick](/models/llama-4-maverick) | Meta | Open Weight | 1M | 22.9 |
| 62 | [GPT-4 Turbo](/models/gpt-4-turbo) | OpenAI | Proprietary | 128K | 21.6 |
| 63 | [Mixtral 8x22B Instruct v0.1](/models/mixtral-8x22b-instruct-v0-1) | Mistral | Open Weight | 64K | 21.1 |
| 64 | [Nova Pro](/models/nova-pro) | Amazon | Proprietary | 128K | 20.8 |
| 65 | [LFM2-24B-A2B](/models/lfm2-24b-a2b) | LiquidAI | Proprietary | 32K | 19.9 |
| 66 | [Ministral 3 8B](/models/ministral-3-8b) | Mistral | Open Weight | 128K | 19.3 |
| 67 | [LFM2.5-1.2B-Instruct](/models/lfm2-5-1-2b-instruct) | LiquidAI | Proprietary | 32K | 18.3 |
| 68 | [Ministral 3 3B](/models/ministral-3-3b) | Mistral | Open Weight | 128K | 18 |
| 69 | [Claude 3 Haiku](/models/claude-3-haiku) | Anthropic | Proprietary | 200K | 14.7 |
| 70 | [Gemini 1.0 Pro](/models/gemini-1-0-pro) | Google | Proprietary | 32K | 12.9 |
| 71 | [Nemotron-4 15B](/models/nemotron-4-15b) | NVIDIA | Open Weight | 32K | 11.4 |
| 72 | [Mistral 7B v0.3](/models/mistral-7b-v0-3) | Mistral | Open Weight | 32K | 8.1 |

## Key Takeaways

- Top model: [Claude Opus 4.7](/models/claude-opus-4-7) with a score of 66.4
- Best open-weight option: [Inkling-Small](/models/inkling-small) at #5
- Models included: 72

## Compare the Leaders

- [Claude Opus 4.7 vs Claude Opus 4.6](/compare/claude-opus-4-6-vs-claude-opus-4-7)