GPQA Diamond leaderboard
Graduate-level questions in biology, physics and chemistry that experts answer well and search does not. Gemini 3.1 Pro Preview leads with 95.45%.
- Models
- 120
- Leader
- Gemini 3.1 Pro Preview
- 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 | Gemini 3.1 Pro Preview | 95.45% | $2 / $12 | — | $2 / $12 | |
| 2 | GPT-5.6 Sol | OpenAI | 95.20% | $4 / $20 | — | $4 / $20 |
| 3 | Grok 4.6 | xAI | 94.70% | $2 / $6 | — | $2 / $6 |
| 4 | Gemini 3.8 Flash | 94.44% | $1.5 / $7.5 | — | $0.82 / $4.13 | |
| 5 | Gemini 3.7 Flash | 93.94% | $1.5 / $7.5 | — | $0.75 / $3.75 | |
| 6 | Qwen3.8-Max | Alibaba | 93.69% | $2 / $6 | — | $2 / $6 |
| 7 | Gemini 3.6 Flash | 93.43% | $1.5 / $7.5 | — | $0.75 / $3.75 | |
| 8 | Claude Opus 5 | Anthropic | 93.43% | $5 / $25 | — | $5 / $25 |
| 9 | Claude Fable 5.1 | Anthropic | 93.43% | $10 / $50 | — | $10 / $50 |
| 10 | Claude Fable 5 | Anthropic | 93.18% | $10 / $50 | — | $10 / $50 |
| 11 | GPT-5.5 | OpenAI | 93.18% | $5 / $30 | — | $5 / $30 |
| 12 | Kimi K3 | Moonshot AI | 92.93% | $3 / $15 | — | $0.24 / $11 |
| 13 | Grok 4.5 | xAI | 92.93% | $2 / $6 | — | $2 / $6 |
| 14 | Gemini 3.5 Flash | 92.68% | $1.5 / $9 | — | $1.50 / $9 | |
| 15 | MiniMax-M3 | MiniMax | 92.68% | $0.6 / $2.4 | — | $0.30 / $1.20 |
| 16 | Claude Opus 4.8 | Anthropic | 92.42% | $5 / $25 | — | $5 / $25 |
| 18 | GPT-5.6 Luna | OpenAI | 91.67% | $0.2 / $1.2 | — | $0.20 / $1.20 |
| 19 | Gemini 3 Pro | 91.67% | $2 / $12 | — | — | |
| 20 | GPT-5.2 | OpenAI | 91.67% | $1.75 / $14 | — | $1.75 / $14 |
| 21 | GPT-5.4 | OpenAI | 91.67% | $2.5 / $15 | — | $2.50 / $15 |
| 22 | Grok 4.3 | xAI | 91.41% | $1.25 / $2.5 | — | $1.25 / $2.50 |
| 23 | Muse Spark 1.1 | Meta | 91.16% | $1.25 / $4.25 | — | $1.25 / $4.25 |
| 24 | GPT-5.6 Terra | OpenAI | 90.91% | $2 / $12 | — | $2 / $12 |
| 25 | Qwen3.7-Max-Preview | Alibaba | 90.15% | $2.5 / $7.5 | — | $1.48 / $4.42 |
| 26 | Claude Opus 4.7 | Anthropic | 90.15% | $5 / $25 | — | $5 / $25 |
| 27 | DeepSeek-V4-Flash | DeepSeek | 89.90% | $0.44 / $1.32 | — | $0.042 / $0.18 |
| 28 | Muse Spark | Meta | 89.65% | N/A | — | — |
| 29 | Claude Opus 4.6 | Anthropic | 89.65% | $5 / $25 | — | $5 / $25 |
| 30 | DeepSeek-V4-Pro | DeepSeek | 89.39% | $1.32 / $3.96 | — | $0.66 / $1.98 |
| 31 | Kimi K2.6 | Moonshot AI | 89.14% | $0.95 / $4 | — | $0.65 / $3.41 |
| 32 | Claude Sonnet 5 | Anthropic | 88.89% | $2 / $10 | — | $2 / $10 |
| 33 | Qwen3.8-27B | Alibaba | 88.89% | $0.5 / $3 | — | $0.20 / $2.50 |
| 34 | Grok 4.20 | xAI | 88.64% | $2 / $6 | — | $1.25 / $2.50 |
| 35 | Grok 4 | xAI | 88.13% | $3 / $15 | — | — |
| 36 | GLM-5.3 | Z.ai | 88.13% | $1.4 / $4.4 | — | $0.079 / $1.40 |
| 37 | Gemini 3 Flash | 87.88% | $0.5 / $3 | — | $0.50 / $3 | |
| 38 | Qwen 3.5 Plus | Alibaba | 87.37% | $0.4 / $2.4 | — | $0.30 / $1.80 |
| 39 | Qwen3.6-Plus | Alibaba | 87.37% | $0.5 / $3 | — | $0.33 / $1.95 |
| 40 | IInkling | Thinky | 87.12% | $1 / $4.05 | — | $1 / $4.05 |
| 41 | GPT-5.1 | OpenAI | 86.62% | $1.25 / $10 | — | $1.25 / $10 |
| 42 | MiniMax-M2.7 | MiniMax | 86.62% | $0.3 / $1.2 | — | $0.30 / $1.20 |
| 43 | GLM-5.3-Flash | Z.ai | 86.36% | $0.075 / $0.25 | — | $0.15 / $0.50 |
| 44 | Nemotron 3 Ultra | NVIDIA | 86.11% | N/A | — | $0.60 / $2.40 |
| 46 | GPT-5 | OpenAI | 85.61% | $1.25 / $10 | — | $1.25 / $10 |
| 47 | GLM-5.2 | Z.ai | 85.61% | $1.4 / $4.4 | — | $0.034 / $7 |
| 48 | Claude Sonnet 4.6 | Anthropic | 85.61% | $3 / $15 | — | $3 / $15 |
| 50 | LLing 3.0 Flash | inclusionAI | 84.85% | $0.075 / $0.22 | — | $0.021 / $0.063 |
| 52 | GLM-5.1 | Z.ai | 84.52% | $1 / $3.2 | — | $1.40 / $4.40 |
| 53 | Grok 4.1 Fast | xAI | 84.34% | $0.2 / $0.5 | — | — |
| 54 | o3 | OpenAI | 84.09% | $2 / $8 | — | $2 / $8 |
| 55 | Kimi K2.5 | Moonshot AI | 84.09% | $0.6 / $3 | — | $0.50 / $2.50 |
| 56 | Gemini 3.5 Flash-Lite | 83.84% | $0.3 / $2.5 | — | $0.30 / $2.50 | |
| 57 | IInkling-Small | Thinky | 83.59% | $0.3 / $1.2 | — | $0.45 / $1.20 |
| 58 | GLM-5 | Z.ai | 83.33% | $1 / $3.2 | — | $1 / $3.20 |
| 59 | GPT-5.4 mini | OpenAI | 83.08% | $0.75 / $4.5 | — | $0.75 / $4.50 |
| 60 | Qwen3.5-Flash | Alibaba | 82.83% | $0.1 / $0.4 | — | $0.065 / $0.26 |
| 61 | MiMo-V2.5-Pro | Xiaomi | 82.58% | $0.435 / $0.87 | — | $0.30 / $0.61 |
| 62 | MiniMax-M2.5 | MiniMax | 82.07% | $0.3 / $1.2 | — | $0.30 / $1.20 |
| 63 | Claude Sonnet 4.5 | Anthropic | 81.63% | $3 / $15 | — | $3 / $15 |
| 65 | MiMo-V2.5 | Xiaomi | 81.57% | $0.14 / $0.28 | — | $0.12 / $0.24 |
| 66 | Gemini 3.1 Flash-Lite Preview | 81.06% | $0.25 / $1.5 | — | $0.25 / $1.50 | |
| 67 | Gemini 2.5 Pro | 80.81% | $1.25 / $10 | — | $1.25 / $10 | |
| 68 | GPT-5 mini | OpenAI | 80.30% | $0.25 / $2 | — | $0.25 / $2 |
| 70 | GLM-4.7 | Z.ai | 80.05% | $0.6 / $2.2 | — | $0.54 / $1.98 |
| 71 | Claude Opus 4.5 | Anthropic | 79.55% | $5 / $25 | — | $5 / $25 |
| 74 | gpt-oss-120b | OpenAI | 78.54% | $0.15 / $0.6 | — | $0.15 / $0.60 |
| 75 | MiniMax-M2.1 Preview | MiniMax | 78.54% | $0.3 / $1.2 | — | $0.30 / $1.20 |
| 76 | Kimi K2 Thinking | Moonshot AI | 78.54% | $0.6 / $2.5 | — | $0.60 / $2.50 |
| 77 | Qwen3-Max-Preview | Alibaba | 77.78% | $1.2 / $6 | — | — |
| 78 | GPT-5.4 nano | OpenAI | 77.53% | $0.2 / $1.25 | — | $0.20 / $1.25 |
| 81 | DeepSeek-V3.2-Exp | DeepSeek | 76.26% | $0.56 / $1.68 | — | $0.28 / $0.42 |
| 82 | o3-mini | OpenAI | 75.50% | $1.1 / $4.4 | — | $1.10 / $4.40 |
| 85 | o4-mini | OpenAI | 74.50% | $1.1 / $4.4 | — | $1.10 / $4.40 |
| 86 | GLM-4.6 | Z.ai | 74.50% | $0.6 / $2.2 | — | $0.55 / $2.20 |
| 87 | Grok 3 Preview | xAI | 74.24% | $3 / $15 | — | — |
| 88 | o1 | OpenAI | 73.23% | $15 / $60 | — | $15 / $60 |
| 89 | Grok 3 Mini Reasoning | xAI | 72.98% | $0.3 / $0.5 | — | — |
| 90 | Claude Haiku 4.5 | Anthropic | 72.22% | $1 / $5 | — | $1 / $5 |
| 91 | GLM-4.5 | Z.ai | 72.22% | $0.6 / $2.2 | — | $0.60 / $2.20 |
| 92 | Claude Opus 4 | Anthropic | 71.72% | $15 / $75 | — | — |
| 93 | Kimi K2 Instruct | Moonshot AI | 71.46% | $1 / $3 | — | — |
| 95 | Qwen3-235B-A22B | Alibaba | 70.20% | $0.22 / $0.88 | — | $0.09 / $0.55 |
| 96 | Claude Opus 4.1 | Anthropic | 69.95% | $15 / $75 | — | $15 / $75 |
| 97 | Llama 4 Maverick | Fireworks AI | 69.44% | $0.22 / $0.88 | — | $0.19 / $0.65 |
| 98 | Claude Sonnet 4 | Anthropic | 69.44% | $3 / $15 | — | — |
| 99 | gpt-oss-20b | OpenAI | 68.94% | $0.07 / $0.3 | — | $0.018 / $0.09 |
| 101 | GPT-4.1 mini | OpenAI | 67.93% | $0.4 / $1.6 | — | $0.40 / $1.60 |
| 102 | Claude 3.7 Sonnet | Anthropic | 67.42% | $3 / $15 | — | — |
| 103 | GPT-4.1 | OpenAI | 65.40% | $2 / $8 | — | $2 / $8 |
| 104 | Gemini 2.0 Flash | 65.15% | $0.1 / $0.4 | — | — | |
| 105 | Grok 4.1 Fast Non-Reasoning | xAI | 65.15% | $0.2 / $0.5 | — | — |
| 106 | Gemini 2.5 Flash Preview | 64.14% | $0.1 / $0.4 | — | — | |
| 107 | GPT-5 nano | OpenAI | 63.38% | $0.05 / $0.4 | — | $0.05 / $0.40 |
| 109 | Magistral Medium | Mistral AI | 62.37% | $2 / $5 | — | — |
| 110 | Grok 4 Fast | xAI | 62.12% | $0.2 / $0.5 | — | — |
| 112 | Claude 3.5 Sonnet | Anthropic | 59.34% | $3 / $15 | — | — |
| 113 | MiMo-V2-Flash | Xiaomi | 59.34% | $0.1 / $0.3 | — | — |
| 114 | Gemini 1.5 Pro | 58.33% | $1.25 / $5 | — | — | |
| 116 | Gemini 2.5 Flash Preview 4/17 | 57.58% | $0.3 / $2.5 | — | — | |
| 117 | LLaguna XS.2 | Poolside | 55.05% | N/A | — | — |
| 118 | DeepSeek-V3 | DeepSeek | 54.55% | $0.9 / $0.9 | — | $0.29 / $1.14 |
| 120 | GPT-4.1 nano | OpenAI | 50.76% | $0.1 / $0.4 | — | $0.10 / $0.40 |
| 121 | Mistral Small | Mistral AI | 50.76% | $0.2 / $0.6 | — | — |
| 122 | Grok 2 | xAI | 50.76% | $2 / $10 | — | — |
| 123 | GPT-4o | OpenAI | 50.25% | $5 / $15 | — | $2.50 / $10 |
| 124 | Llama 3.3 Instruct Turbo | Meta | 50.00% | $0.88 / $0.88 | — | — |
| 125 | Command A | Cohere | 48.48% | $2.5 / $10 | — | $0.30 / $1.50 |
| 126 | Mistral Large | Mistral AI | 47.73% | $2 / $6 | — | $0.50 / $1.50 |
| 127 | Llama 3.3 Nemotron Super | Meta | 47.73% | N/A | — | — |
| 128 | Llama 4 Scout | Meta | 46.97% | $0.18 / $0.59 | — | $0.10 / $0.30 |
| 129 | Gemini 1.5 Flash | 45.96% | $0.075 / $0.3 | — | — | |
| 130 | Magistral Small 1.2 | Mistral AI | 44.19% | $0.075 / $0.3 | — | — |
| 131 | GPT-4o mini | OpenAI | 44.19% | $0.15 / $0.6 | — | $0.15 / $0.60 |
| 132 | Claude 3.5 Haiku | Anthropic | 37.88% | $0.8 / $4 | — | — |
| 133 | Jamba 1.6 Large | AI21 Labs | 36.11% | $2 / $8 | — | — |
| 134 | Mistral Medium 3.5 | Mistral AI | 34.85% | $1.5 / $7.5 | — | $1.50 / $7.50 |
| 135 | Jamba 1.6 Mini | AI21 Labs | 32.07% | $0.2 / $0.4 | — | — |
| 136 | Command R+ | Cohere | 31.06% | $2.5 / $10 | — | $0.15 / $0.60 |
| 137 | GPT-3.5 Turbo | OpenAI | 30.56% | $0.5 / $1.5 | — | $1 / $2 |
| 138 | LLaguna M.1 | Poolside | 27.02% | N/A | — | — |
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


