# Best Reasoning AI Models (2026)

> Top AI models with dedicated reasoning capabilities, ranked by benchmark performance.

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

Last updated: October 19, 2026

## Rankings

| Rank | Model | Creator | Type | Context | Score |
|------|-------|---------|------|---------|-------|
| 1 | [Claude Opus 5.5](/models/claude-opus-5-5) | Anthropic | Proprietary | 1M | 86.6 |
| 2 | [GPT-6.1 Sol](/models/gpt-6-1-sol) | OpenAI | Proprietary | 1.05M | 84.1 |
| 3 | [GPT-6 Astra](/models/gpt-6-astra) | OpenAI | Proprietary | 1.05M | 84 |
| 4 | [Claude Fable 5.1](/models/claude-fable-5-1) | Anthropic | Proprietary | 1M | 83.2 |
| 5 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | Anthropic | Proprietary | 1M | 82.2 |
| 6 | [Claude Fable 5](/models/claude-fable) | Anthropic | Proprietary | 1M+ | 81.3 |
| 7 | [Gemini 4 Argon](/models/gemini-4-argon) | Google | Proprietary | 1M | 80.9 |
| 8 | [Claude Opus 5](/models/claude-opus-5) | Anthropic | Proprietary | null | 79.6 |
| 9 | [GPT-6 Sol](/models/gpt-6-sol) | OpenAI | Proprietary | 1.05M | 78.5 |
| 10 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | OpenAI | Proprietary | 1.05M | 75.3 |
| 11 | [Muse Wonder Full](/models/muse-wonder-full) | Meta | Proprietary | 1M | 74.4 |
| 12 | [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) | Xiaomi | Open Weight | 1M | 73.6 |
| 13 | [GPT-5.5 Pro](/models/gpt-5-5-pro) | OpenAI | Proprietary | 1M | 73.3 |
| 14 | [Muse Wonder](/models/muse-wonder) | Meta | Proprietary | 1M | 71.3 |
| 15 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | OpenAI | Proprietary | 1.05M | 70.2 |
| 16 | [Claude Haiku 5.5](/models/claude-haiku-5-5) | Anthropic | Proprietary | 1M | 70.1 |
| 17 | [Claude Opus 4.8](/models/claude-opus-4-8) | Anthropic | Proprietary | 1M | 70 |
| 18 | [Kimi K3](/models/kimi-k3) | Moonshot AI | Pending | 1.05M | 69.9 |
| 19 | [Qwen3.8 Max](/models/qwen3-8-max) | Alibaba | Open Weight | 1M | 69.7 |
| 20 | [Step 5 Preview](/models/step-5-preview) | StepFun | Open Weight | 1M | 69.3 |
| 21 | [GPT-5.5](/models/gpt-5-5) | OpenAI | Proprietary | 1M | 69.3 |
| 22 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | Google | Proprietary | 1M | 69.1 |
| 23 | [Claude Opus 4.7 (Adaptive)](/models/claude-opus-4-7-adaptive) | Anthropic | Proprietary | 1M | 69 |
| 24 | [GPT-5.4 Pro](/models/gpt-5-4-pro) | OpenAI | Proprietary | 1.05M | 68.6 |
| 25 | [Ling 3.1 Flash](/models/ling-3-1-flash) | InclusionAI | Open Weight | 262K | 68.1 |
| 26 | [GLM-5.3](/models/glm-5-3) | Z.AI | Open Weight | 1M | 67.9 |
| 27 | [Grok 4.6](/models/grok-4-6) | xAI | Proprietary | 500K | 67.1 |
| 28 | [Gemini 3.7 Flash](/models/gemini-3-7-flash) | Google | Proprietary | 1M | 66.8 |
| 29 | [GPT-5.4](/models/gpt-5-4) | OpenAI | Proprietary | 1.05M | 66.7 |
| 30 | [GPT-5.2 Pro](/models/gpt-5-2-pro) | OpenAI | Proprietary | 400K | 66.7 |
| 31 | [GPT-6 Luna](/models/gpt-6-luna) | OpenAI | Proprietary | 1.05M | 66.6 |
| 32 | [Muse Spark 1.1](/models/muse-spark-1-1) | Meta | Proprietary | 1M | 66.1 |
| 33 | [Muse Spark 1.2](/models/muse-spark-1-2) | Meta | Proprietary | 1M | 65.9 |
| 34 | [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) | DeepSeek | Open Weight | 1M | 65.6 |
| 35 | [Claude Sonnet 5](/models/claude-sonnet-5) | Anthropic | Proprietary | 1M | 64.9 |
| 36 | [Gemini 3.1 Pro](/models/gemini-3-1-pro) | Google | Proprietary | 1M | 64.7 |
| 37 | [MiMo-V2.6-Flash](/models/mimo-v2-6-flash) | Xiaomi | Open Weight | 1M | 64.5 |
| 38 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | OpenAI | Proprietary | 1.05M | 64.4 |
| 39 | [dots3-note Preview](/models/dots3-note-preview) | Dots Studio | Open Weight | 512K | 63.8 |
| 40 | [MiniMax M3.1 Flash](/models/minimax-m3-1-flash) | MiniMax | Proprietary | 1M | 63.4 |
| 41 | [Grok 4.5](/models/grok-4-5) | xAI | Proprietary | 500K | 63.3 |
| 42 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | DeepSeek | Open Weight | 1M | 63.2 |
| 43 | [Qwen3.8-Flash-Next](/models/qwen3-8-flash-next) | Alibaba | Open Weight | 262K | 62.8 |
| 44 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | Google | Proprietary | 1M | 62.8 |
| 45 | [Muse Spark Open](/models/muse-spark-open) | Meta | Open Weight | 1M | 62.8 |
| 46 | [Qwen3.7 Max](/models/qwen3-7-max) | Alibaba | Proprietary | 1M | 62.6 |
| 47 | [Ornith-1.5-397B](/models/ornith-1-5-397b) | Ornith AI | Open Weight | 262K | 62.2 |
| 48 | [Gemini 3.5 Flash](/models/gemini-3-5-flash) | Google | Proprietary | 1M | 61.9 |
| 49 | [Hy4 preview](/models/hy4-preview) | Tencent | Open Weight | 1M | 61.2 |
| 50 | [GLM-5.2](/models/glm-5-2) | Z.AI | Open Weight | 1M | 60.5 |
| 51 | [GPT-5.3 Codex](/models/gpt-5-3-codex) | OpenAI | Proprietary | 400K | 60.5 |
| 52 | [Muse Spark](/models/muse-spark) | Meta | Proprietary | 262K | 60.5 |
| 53 | [GPT-5.2](/models/gpt-5-2) | OpenAI | Proprietary | 400K | 59.9 |
| 54 | [Qwen3.8-27B](/models/qwen3-8-27b) | Alibaba | Open Weight | 262K | 59.6 |
| 55 | [GLM-5.3-Flash](/models/glm-5-3-flash) | Z.AI | Open Weight | 1M | 58.5 |
| 56 | [Kimi K2.6](/models/kimi-2-6) | Moonshot AI | Open Weight | 256K | 58.4 |
| 57 | [Grok 4.20](/models/grok-4-20-beta) | xAI | Proprietary | 2M | 57.4 |
| 58 | [GPT-5.1](/models/gpt-5-1) | OpenAI | Proprietary | 200K | 57.2 |
| 59 | [GLM-5.1](/models/glm-5-1) | Z.AI | Open Weight | 203K | 56.3 |
| 60 | [Kimi K2.5 (Reasoning)](/models/kimi-k2-5-reasoning) | Moonshot AI | Proprietary | 128K | 56.1 |
| 61 | [GPT-5.2-Codex](/models/gpt-5-2-codex) | OpenAI | Proprietary | 400K | 55.3 |
| 62 | [Qwen 3.6 Max (preview)](/models/qwen3-6-max-preview) | Alibaba | Proprietary | 256K | 55.1 |
| 63 | [Agents-A1](/models/agents-a1) | InternScience | Open Weight | 262K | 54.2 |
| 64 | [Agents-A1-F16-GGUF](/models/agents-a1-f16-gguf) | InternScience | Open Weight | 262K | 54.2 |
| 65 | [Agents-A1-FP8](/models/agents-a1-fp8) | InternScience | Open Weight | 262K | 54.2 |
| 66 | [Agents-A1-Q4_K_M-GGUF](/models/agents-a1-q4-k-m-gguf) | InternScience | Open Weight | 262K | 54.2 |
| 67 | [Agents-A1-Q8_0-GGUF](/models/agents-a1-q8-0-gguf) | InternScience | Open Weight | 262K | 54.2 |
| 68 | [Claude Opus 4.5 Thinking](/models/claude-opus-4-5-thinking) | Anthropic | Proprietary | 200K | 54.1 |
| 69 | [Ternary Bonsai 2 27B](/models/ternary-bonsai-2-27b) | Prism ML | Open Weight | 262K | 54 |
| 70 | [Qwen3.6 Plus](/models/qwen3-6-plus) | Alibaba | Proprietary | 1M | 53.8 |
| 71 | [Qwen3.7 Plus](/models/qwen3-7-plus) | Alibaba | Proprietary | 1M | 53.8 |
| 72 | [GPT-5.4 mini](/models/gpt-5-4-mini) | OpenAI | Proprietary | 400K | 53.4 |
| 73 | [MAI-Thinking-1](/models/mai-thinking-1) | Microsoft | Proprietary | 256K | 53.3 |
| 74 | [GLM-5-Turbo](/models/glm-5-turbo) | Z.AI | Proprietary | 200K | 53.2 |
| 75 | [Grok 4.3](/models/grok-4-3) | xAI | Proprietary | 1M | 53.1 |
| 76 | [MiMo-V2-Pro](/models/mimo-v2-pro) | Xiaomi | Proprietary | 1M | 53 |
| 77 | [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) | Xiaomi | Proprietary | 1M | 53 |
| 78 | [Hy3](/models/hy3) | Tencent | Open Weight | 256K | 52.5 |
| 79 | [Hy3 Preview](/models/hy3-preview) | Tencent | Open Weight | 256K | 52.2 |
| 80 | [Beam 1.0 501B-A23B](/models/reflection-beam) | Reflection AI | Open Weight | 1M | 51.6 |
| 81 | [GPT-5.1-Codex](/models/gpt-5-1-codex) | OpenAI | Proprietary | 400K | 50.4 |
| 82 | [Apodex 1.1](/models/apodex-1-1) | Apodex | Proprietary | N/A | 50.3 |
| 83 | [MiMo-V2-Omni](/models/mimo-v2-omni) | Xiaomi | Proprietary | 262K | 50 |
| 84 | [Gemini 3.5 Flash-Lite](/models/gemini-3-5-flash-lite) | Google | Proprietary | 1M | 49.6 |
| 85 | [Kimi K2.7 Code](/models/kimi-k2-7-code) | Moonshot AI | Open Weight | 256K | 49.5 |
| 86 | [Nemotron 3.5 Super VL 120B A12B](/models/nemotron-3-5-super-vl-120b-a12b) | NVIDIA | Open Weight | 1M | 49.4 |
| 87 | [Qwen3.5 Plus](/models/qwen3-5-plus) | Alibaba | Proprietary | 1M | 48.9 |
| 88 | [GLM-4.7](/models/glm-4-7) | Z.AI | Open Weight | 200K | 48.9 |
| 89 | [Qwen3.6-27B](/models/qwen3-6-27b) | Alibaba | Open Weight | 262K | 48.6 |
| 90 | [Quasar 438B](/models/quasar-438b) | Multiverse Computing | Proprietary | 1M | 48.6 |
| 91 | [Qwen3.5-27B](/models/qwen3-5-27b) | Alibaba | Open Weight | 262K | 48.5 |
| 92 | [GPT-5 mini](/models/gpt-5-mini) | OpenAI | Proprietary | 128K | 48.4 |
| 93 | [Qwen3.7 Flash](/models/qwen3-7-flash) | Alibaba | Proprietary | 1M | 47 |
| 94 | [GPT-5.4 nano](/models/gpt-5-4-nano) | OpenAI | Proprietary | 400K | 46.9 |
| 95 | [Ling 3.0 Flash VL](/models/ling-3-0-flash-vl) | InclusionAI | Open Weight | 262K | 46.8 |
| 96 | [Nemotron 3 Ultra](/models/nemotron-3-ultra) | NVIDIA | Open Weight | 1M | 46.7 |
| 97 | [GPT-5 (medium)](/models/gpt-5-medium) | OpenAI | Proprietary | 128K | 46 |
| 98 | [Grok 4.1 Fast (Reasoning)](/models/grok-4-1-fast-reasoning) | xAI | Proprietary | 2M | 45.9 |
| 99 | [Qwen3.5-35B-A3B](/models/qwen3-5-35b-a3b) | Alibaba | Open Weight | 262K | 45.8 |
| 100 | [Gemma 4 26B A4B](/models/gemma-4-26b-a4b) | Google | Open Weight | 256K | 45.7 |
| 101 | [o3](/models/o3) | OpenAI | Proprietary | 200K | 45.5 |
| 102 | [o3-pro](/models/o3-pro) | OpenAI | Proprietary | 200K | 45.4 |
| 103 | [Nemotron 3.5 Bolt 74B-A9B](/models/nemotron-3-5-bolt-74b-a9b) | NVIDIA | Open Weight | 256K | 45.3 |
| 104 | [Ling 3.0 Flash](/models/ling-3-0-flash) | InclusionAI | Open Weight | 262K | 45.1 |
| 105 | [Grok 3 Mini](/models/grok-3-mini) | xAI | Proprietary | 128K | 44.2 |
| 106 | [Step 3.7 Flash](/models/step-3-7-flash) | StepFun | Open Weight | 256K | 43.7 |
| 107 | [Qwen3.6-35B-A3B](/models/qwen3-6-35b-a3b) | Alibaba | Open Weight | 262K | 43.6 |
| 108 | [Grok 4 Fast (Reasoning)](/models/grok-4-fast-reasoning) | xAI | Proprietary | 2M | 43.5 |
| 109 | [Qwen3.5 Flash](/models/qwen3-5-flash) | Alibaba | Proprietary | 1M | 42.8 |
| 110 | [Qwen3.5-122B-A10B](/models/qwen3-5-122b-a10b) | Alibaba | Open Weight | 262K | 41.8 |
| 111 | [Muse Glimmer 30B](/models/muse-glimmer-30b) | Meta | Open Weight | 131K | 41.2 |
| 112 | [DeepSeek-R1](/models/deepseek-r1) | DeepSeek | Open Weight | 128K | 41.1 |
| 113 | [MiMo-V2-Flash](/models/mimo-v2-flash) | Xiaomi | Open Weight | 256K | 41 |
| 114 | [GLM-4.6](/models/glm-4-6) | Z.AI | Open Weight | 200K | 40 |
| 115 | [Gemma 4 31B](/models/gemma-4-31b) | Google | Open Weight | 256K | 39.9 |
| 116 | [Qwen3 Max](/models/qwen3-max) | Alibaba | Proprietary | 1M | 39.6 |
| 117 | [o3-mini](/models/o3-mini) | OpenAI | Proprietary | 200K | 39.6 |
| 118 | [Claude 4.1 Opus Thinking](/models/claude-4-1-opus-thinking) | Anthropic | Proprietary | 200K | 39.4 |
| 119 | [DeepSeek V3.1 (Reasoning)](/models/deepseek-v3-1-reasoning) | DeepSeek | Open Weight | 128K | 39.2 |
| 120 | [GLM-4.7-Flash](/models/glm-4-7-flash) | Z.AI | Open Weight | 200K | 39.2 |
| 121 | [o1](/models/o1) | OpenAI | Proprietary | 200K | 38.4 |
| 122 | [LFM2.5-24B-A2B](/models/lfm2-5-24b-a2b) | LiquidAI | Open Weight | 131K | 37.9 |
| 123 | [K-Exaone](/models/k-exaone) | LG AI Research | Proprietary | 256K | 37.6 |
| 124 | [GPT-5 nano](/models/gpt-5-nano) | OpenAI | Proprietary | 400K | 37.4 |
| 125 | [Gemma 4 12B](/models/gemma-4-12b) | Google | Open Weight | 256K | 36.3 |
| 126 | [Command A+](/models/command-a-plus) | Cohere | Open Weight | 128K | 36.2 |
| 127 | [o1-preview](/models/o1-preview) | OpenAI | Proprietary | 200K | 36 |
| 128 | [o1-pro](/models/o1-pro) | OpenAI | Proprietary | 200K | 35.8 |
| 129 | [Trinity-Large-Thinking](/models/trinity-large-thinking) | Arcee AI | Open Weight | 512K | 34.5 |
| 130 | [ZAYA1-8B](/models/zaya1-8b) | Zyphra | Open Weight | 131K | 34.4 |
| 131 | [Mercury 2.5](/models/mercury-2-5) | Inception | Proprietary | 260K | 33.9 |
| 132 | [Ornith-1.5-35B-A3B](/models/ornith-1-5-35b-a3b) | Ornith AI | Open Weight | 262K | 33.9 |
| 133 | [Mistral Medium 3.5 128B](/models/mistral-medium-3-5-128b) | Mistral | Open Weight | 256K | 33.7 |
| 134 | [Mercury 2](/models/mercury-2) | Inception | Proprietary | 128K | 33.6 |
| 135 | [Granite 4.2 8B](/models/granite-4-2-8b) | IBM | Open Weight | 128K | 33.2 |
| 136 | [Nemotron 3 Nano Omni 30B A3B](/models/nemotron-3-nano-omni-30b-a3b) | NVIDIA | Open Weight | 256K | 32.2 |
| 137 | [Sarvam 105B](/models/sarvam-105b) | Sarvam | Open Weight | 128K | 31.7 |
| 138 | [Ornith-1.5-9B](/models/ornith-1-5-9b) | Ornith AI | Open Weight | 262K | 31.4 |
| 139 | [LFM2.5-2.6B](/models/lfm2-5-2-6b) | LiquidAI | Open Weight | 128K | 31.3 |
| 140 | [Gemma 4 E4B](/models/gemma-4-e4b) | Google | Open Weight | 128K | 31.1 |
| 141 | [DeepSeek R1 Distill Qwen 32B](/models/deepseek-r1-distill-qwen-32b) | DeepSeek | Open Weight | 128K | 30.8 |
| 142 | [LFM2.5-8B-A1B](/models/lfm2-5-8b-a1b) | LiquidAI | Open Weight | 128K | 30.2 |
| 143 | [Solar Pro 3](/models/solar-pro-3) | Upstage | Proprietary | 128K | 30.1 |
| 144 | [Gemma 4 E2B](/models/gemma-4-e2b) | Google | Open Weight | 128K | 30 |
| 145 | [Solar Pro 2](/models/solar-pro-2) | Upstage | Proprietary | 128K | 29.1 |
| 146 | [Sarvam 30B](/models/sarvam-30b) | Sarvam | Open Weight | 64K | 28.7 |
| 147 | [Exaone 4.0 32B](/models/exaone-4-0-32b) | LG AI Research | Open Weight | 128K | 28.5 |
| 148 | [Nemotron 3.5 Lightning 30B A3B NVFP4](/models/nemotron-3-5-lightning-30b-a3b-nvfp4) | NVIDIA | Open Weight | 1M | 25.6 |
| 149 | [LFM2.5-1.2B-Thinking](/models/lfm2-5-1-2b-thinking) | LiquidAI | Proprietary | 32K | 19.4 |
| 150 | [MiniCPM5-1B](/models/minicpm5-1b) | OpenBMB | Open Weight | 131K | 6.3 |

## Key Takeaways

- Top model: [Claude Opus 5.5](/models/claude-opus-5-5) with a score of 86.6
- Best open-weight option: [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) at #12
- Models included: 150

## Compare the Leaders

- [Claude Opus 5.5 vs GPT-6.1 Sol](/compare/claude-opus-5-5-vs-gpt-6-1-sol)