MMLU-Pro leaderboard
Harder, reasoning-focused multiple choice across 14 subjects, from law to engineering. Claude Fable 5.1 leads with 92.38%.
- Models
- 120
- Leader
- Claude Fable 5.1
- Source
- Vals AI
- As of
- Oct 24, 2026
Open weightsProprietaryBest for the price
Full leaderboard
| Rank | Model | Lab | Accuracy | Cost / test | Harness | Price in / out |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | Anthropic | 92.38% | $10 / $50 | — | $10 / $50 |
| 2 | Claude Opus 5 | Anthropic | 91.59% | $5 / $25 | — | $5 / $25 |
| 3 | Claude Fable 5 | Anthropic | 91.50% | $10 / $50 | — | $10 / $50 |
| 4 | Gemini 3.1 Pro Preview | 90.99% | $2 / $12 | — | $2 / $12 | |
| 5 | Gemini 3.8 Flash | 90.22% | $1.5 / $7.5 | — | $0.82 / $4.13 | |
| 6 | Gemini 3.7 Flash | 90.12% | $1.5 / $7.5 | — | $0.75 / $3.75 | |
| 7 | Gemini 3 Pro | 90.10% | $2 / $12 | — | — | |
| 8 | Claude Opus 4.7 | Anthropic | 89.87% | $5 / $25 | — | $5 / $25 |
| 9 | Claude Opus 4.8 | Anthropic | 89.58% | $5 / $25 | — | $5 / $25 |
| 10 | Gemini 3.5 Flash | 89.52% | $1.5 / $9 | — | $1.50 / $9 | |
| 11 | Grok 4.6 | xAI | 89.40% | $2 / $6 | — | $2 / $6 |
| 12 | Qwen3.7-Max-Preview | Alibaba | 89.31% | $2.5 / $7.5 | — | $1.48 / $4.42 |
| 13 | Gemini 3.6 Flash | 89.28% | $1.5 / $7.5 | — | $0.75 / $3.75 | |
| 14 | Grok 4.5 | xAI | 89.22% | $2 / $6 | — | $2 / $6 |
| 15 | Claude Opus 4.6 | Anthropic | 89.11% | $5 / $25 | — | $5 / $25 |
| 16 | GPT-5.6 Sol | OpenAI | 89.10% | $4 / $20 | — | $4 / $20 |
| 17 | Muse Spark 1.1 | Meta | 88.73% | $1.25 / $4.25 | — | $1.25 / $4.25 |
| 18 | Qwen3.8-Max | Alibaba | 88.60% | $2 / $6 | — | $2 / $6 |
| 19 | Gemini 3 Flash | 88.59% | $0.5 / $3 | — | $0.50 / $3 | |
| 20 | Muse Spark 1.2 | Meta | 88.28% | $1.25 / $4.25 | — | $1.25 / $4.25 |
| 21 | GPT-5.5 | OpenAI | 88.14% | $5 / $30 | — | $5 / $30 |
| 22 | Kimi K3 | Moonshot AI | 87.97% | $3 / $15 | — | $0.24 / $11 |
| 24 | Qwen3.6-Plus | Alibaba | 87.67% | $0.5 / $3 | — | $0.33 / $1.95 |
| 25 | Kimi K2.6 | Moonshot AI | 87.57% | $0.95 / $4 | — | $0.65 / $3.41 |
| 26 | Claude Sonnet 5 | Anthropic | 87.55% | $2 / $10 | — | $2 / $10 |
| 27 | GPT-5.4 | OpenAI | 87.48% | $2.5 / $15 | — | $2.50 / $15 |
| 28 | Claude Sonnet 4.5 | Anthropic | 87.36% | $3 / $15 | — | $3 / $15 |
| 29 | Claude Sonnet 4.6 | Anthropic | 87.34% | $3 / $15 | — | $3 / $15 |
| 30 | Muse Spark | Meta | 87.32% | N/A | — | — |
| 33 | Claude Opus 4.1 | Anthropic | 87.21% | $15 / $75 | — | $15 / $75 |
| 34 | Qwen 3.5 Plus | Alibaba | 87.18% | $0.4 / $2.4 | — | $0.30 / $1.80 |
| 35 | MiniMax-M2.1 Preview | MiniMax | 87.05% | $0.3 / $1.2 | — | $0.30 / $1.20 |
| 36 | DeepSeek-V4-Pro | DeepSeek | 86.97% | $1.32 / $3.96 | — | $0.66 / $1.98 |
| 37 | GLM-5.1 | Z.ai | 86.90% | $1 / $3.2 | — | $1.40 / $4.40 |
| 38 | GLM-5.3 | Z.ai | 86.77% | $1.4 / $4.4 | — | $0.079 / $1.40 |
| 39 | GLM-5.2 | Z.ai | 86.71% | $1.4 / $4.4 | — | $0.034 / $7 |
| 40 | GPT-5.6 Terra | OpenAI | 86.66% | $2 / $12 | — | $2 / $12 |
| 41 | GPT-5 | OpenAI | 86.54% | $1.25 / $10 | — | $1.25 / $10 |
| 42 | GPT-5.1 | OpenAI | 86.38% | $1.25 / $10 | — | $1.25 / $10 |
| 43 | IInkling | Thinky | 86.30% | $1 / $4.05 | — | $1 / $4.05 |
| 44 | Grok 4.20 | xAI | 86.25% | $2 / $6 | — | $1.25 / $2.50 |
| 45 | Gemini 3.1 Flash-Lite Preview | 86.24% | $0.25 / $1.5 | — | $0.25 / $1.50 | |
| 46 | GPT-5.2 | OpenAI | 86.23% | $1.75 / $14 | — | $1.75 / $14 |
| 47 | DeepSeek-V4-Flash | DeepSeek | 86.21% | $0.44 / $1.32 | — | $0.042 / $0.18 |
| 48 | Claude Opus 4 | Anthropic | 86.17% | $15 / $75 | — | — |
| 49 | GLM-5.3-Flash | Z.ai | 86.06% | $0.075 / $0.25 | — | $0.15 / $0.50 |
| 50 | GPT-5.6 Luna | OpenAI | 86.04% | $0.2 / $1.2 | — | $0.20 / $1.20 |
| 51 | GLM-5 | Z.ai | 86.03% | $1 / $3.2 | — | $1 / $3.20 |
| 52 | Kimi K2.5 | Moonshot AI | 85.91% | $0.6 / $3 | — | $0.50 / $2.50 |
| 53 | Grok 4.3 | xAI | 85.84% | $1.25 / $2.5 | — | $1.25 / $2.50 |
| 54 | Gemini 3.5 Flash-Lite | 85.84% | $0.3 / $2.5 | — | $0.30 / $2.50 | |
| 55 | Nemotron 3 Ultra | NVIDIA | 85.76% | N/A | — | $0.60 / $2.40 |
| 56 | o3 | OpenAI | 85.59% | $2 / $8 | — | $2 / $8 |
| 57 | Claude Opus 4.5 | Anthropic | 85.59% | $5 / $25 | — | $5 / $25 |
| 58 | IInkling-Small | Thinky | 85.57% | $0.3 / $1.2 | — | $0.45 / $1.20 |
| 59 | Grok 4 | xAI | 85.30% | $3 / $15 | — | — |
| 62 | MiMo-V2.5-Pro | Xiaomi | 84.59% | $0.435 / $0.87 | — | $0.30 / $0.61 |
| 63 | GPT-5.4 mini | OpenAI | 84.55% | $0.75 / $4.5 | — | $0.75 / $4.50 |
| 65 | Qwen3.8-27B | Alibaba | 84.34% | $0.5 / $3 | — | $0.20 / $2.50 |
| 66 | MiniMax-M3 | MiniMax | 84.22% | $0.6 / $2.4 | — | $0.30 / $1.20 |
| 67 | Grok 4.1 Fast | xAI | 84.18% | $0.2 / $0.5 | — | — |
| 68 | Qwen3.5-Flash | Alibaba | 84.06% | $0.1 / $0.4 | — | $0.065 / $0.26 |
| 69 | Gemini 2.5 Pro | 84.06% | $1.25 / $10 | — | $1.25 / $10 | |
| 73 | Qwen3-Max-Preview | Alibaba | 83.54% | $1.2 / $6 | — | — |
| 74 | o1 | OpenAI | 83.49% | $15 / $60 | — | $15 / $60 |
| 75 | DeepSeek-R1 | DeepSeek | 83.18% | $1.35 / $5.4 | — | $0.50 / $2.15 |
| 76 | DeepSeek-V3.2-Exp | DeepSeek | 83.06% | $0.56 / $1.68 | — | $0.28 / $0.42 |
| 77 | MiMo-V2.5 | Xiaomi | 82.93% | $0.14 / $0.28 | — | $0.12 / $0.24 |
| 78 | GLM-4.7 | Z.ai | 82.74% | $0.6 / $2.2 | — | $0.54 / $1.98 |
| 80 | GPT-5 mini | OpenAI | 82.23% | $0.25 / $2 | — | $0.25 / $2 |
| 81 | GLM-4.6 | Z.ai | 82.20% | $0.6 / $2.2 | — | $0.55 / $2.20 |
| 82 | LLing 3.0 Flash | inclusionAI | 82.01% | $0.075 / $0.22 | — | $0.021 / $0.063 |
| 84 | Qwen3-235B-A22B | Alibaba | 81.25% | $0.22 / $0.88 | — | $0.09 / $0.55 |
| 85 | GLM-4.5 | Z.ai | 81.22% | $0.6 / $2.2 | — | $0.60 / $2.20 |
| 86 | Kimi K2 Thinking | Moonshot AI | 81.07% | $0.6 / $2.5 | — | $0.60 / $2.50 |
| 87 | Claude 3.7 Sonnet | Anthropic | 80.66% | $3 / $15 | — | — |
| 88 | o4-mini | OpenAI | 80.56% | $1.1 / $4.4 | — | $1.10 / $4.40 |
| 89 | GPT-4.1 | OpenAI | 80.50% | $2 / $8 | — | $2 / $8 |
| 90 | MiniMax-M2.7 | MiniMax | 80.43% | $0.3 / $1.2 | — | $0.30 / $1.20 |
| 91 | MiniMax-M2.5 | MiniMax | 80.09% | $0.3 / $1.2 | — | $0.30 / $1.20 |
| 92 | Grok 3 Mini Reasoning | xAI | 80.01% | $0.3 / $0.5 | — | — |
| 93 | Grok 3 Preview | xAI | 79.95% | $3 / $15 | — | — |
| 97 | Claude Sonnet 4 | Anthropic | 79.43% | $3 / $15 | — | — |
| 98 | Llama 4 Maverick | Fireworks AI | 79.42% | $0.22 / $0.88 | — | $0.19 / $0.65 |
| 99 | Kimi K2 Instruct | Moonshot AI | 79.39% | $1 / $3 | — | — |
| 100 | gpt-oss-120b | OpenAI | 79.17% | $0.15 / $0.6 | — | $0.15 / $0.60 |
| 102 | Claude Haiku 4.5 | Anthropic | 78.72% | $1 / $5 | — | $1 / $5 |
| 103 | o3-mini | OpenAI | 78.69% | $1.1 / $4.4 | — | $1.10 / $4.40 |
| 104 | Gemini 2.5 Flash Preview | 78.64% | $0.1 / $0.4 | — | — | |
| 105 | Claude 3.5 Sonnet | Anthropic | 78.40% | $3 / $15 | — | — |
| 106 | Gemini 2.0 Flash | 77.38% | $0.1 / $0.4 | — | — | |
| 107 | GPT-4.1 mini | OpenAI | 77.22% | $0.4 / $1.6 | — | $0.40 / $1.60 |
| 108 | GPT-5.4 nano | OpenAI | 77.17% | $0.2 / $1.25 | — | $0.20 / $1.25 |
| 109 | GPT-5 nano | OpenAI | 76.07% | $0.05 / $0.4 | — | $0.05 / $0.40 |
| 110 | Grok 2 | xAI | 75.47% | $2 / $10 | — | — |
| 111 | Mistral Medium 3.5 | Mistral AI | 75.33% | $1.5 / $7.5 | — | $1.50 / $7.50 |
| 112 | Gemini 1.5 Pro | 75.29% | $1.25 / $5 | — | — | |
| 113 | Mistral Medium | Mistral AI | 75.29% | $0.4 / $2 | — | — |
| 114 | Grok 4.1 Fast Non-Reasoning | xAI | 75.21% | $0.2 / $0.5 | — | — |
| 116 | DeepSeek-V3 | DeepSeek | 73.82% | $0.9 / $0.9 | — | $0.29 / $1.14 |
| 117 | GPT-4o | OpenAI | 72.56% | $2.5 / $10 | — | $2.50 / $10 |
| 118 | gpt-oss-20b | OpenAI | 71.64% | $0.07 / $0.3 | — | $0.018 / $0.09 |
| 120 | Grok 4 Fast | xAI | 70.34% | $0.2 / $0.5 | — | — |
| 121 | Llama 3.3 Instruct Turbo | Meta | 69.86% | $0.88 / $0.88 | — | — |
| 122 | Mistral Large | Mistral AI | 69.71% | $2 / $6 | — | $0.50 / $1.50 |
| 123 | Llama 4 Scout | Meta | 69.63% | $0.18 / $0.59 | — | $0.10 / $0.30 |
| 124 | Llama 3.3 Nemotron Super | Meta | 69.58% | N/A | — | — |
| 125 | Command A | Cohere | 69.17% | $2.5 / $10 | — | $0.30 / $1.50 |
| 126 | LLaguna XS.2 | Poolside | 69.05% | N/A | — | — |
| 127 | LLaguna M.1 | Poolside | 68.84% | N/A | — | — |
| 128 | Magistral Medium | Mistral AI | 68.66% | $2 / $5 | — | — |
| 130 | Gemini 1.5 Flash | 65.61% | $0.075 / $0.3 | — | — | |
| 131 | Mistral Small | Mistral AI | 64.44% | $0.2 / $0.6 | — | — |
| 132 | Claude 3.5 Haiku | Anthropic | 64.12% | $0.8 / $4 | — | — |
| 133 | GPT-4.1 nano | OpenAI | 63.48% | $0.1 / $0.4 | — | $0.10 / $0.40 |
| 134 | GPT-4o mini | OpenAI | 62.73% | $0.15 / $0.6 | — | $0.15 / $0.60 |
| 135 | Magistral Small 1.2 | Mistral AI | 62.13% | $0.5 / $1.5 | — | — |
| 136 | Jamba 1.6 Large | AI21 Labs | 49.78% | $2 / $8 | — | — |
| 137 | Command R+ | Cohere | 44.00% | $2.5 / $10 | — | $0.15 / $0.60 |
| 138 | Jamba 1.6 Mini | AI21 Labs | 30.28% | $0.2 / $0.4 | — | — |
Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview


