Model rankings
A balanced intelligence index averages each model's per-category scores. Drill into a category for individual benchmarks, or sort by speed, price, and context. See what changed → How this is calculated → Embed this leaderboard →
Updated May 25, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error
Price vs. intelligence
Intelligence index vs. input price — up and to the left is better value.
Speed vs. intelligence
Intelligence index vs. output speed — up and to the right is fast and smart.
Intelligence over time
Every scored model by release date; the line traces the rising state of the art (intelligence index).
| # | Model | Index ↓ | Reason | Coding | Math | Agents | Multi | General | Long ctx | Context | Speed | In $/M |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Sonar Reasoning Pro | 95.7 | — | — | 95.7 | — | — | — | — | 128K | — | $2.00 |
| 2 | R1 1776 | 95.4 | — | — | 95.4 | — | — | — | — | — | — | $0.00 |
| 3 | Qwen3.7 Max | 92.3 | 92.3 | — | — | — | — | — | — | 1M | 203 | $2.50 |
| 4 | Gemini 3.5 Flash | 92.2 | 92.2 | — | — | — | — | — | — | 1M | 221 | $1.50 |
| 5 | GPT-5.3-Codex | 91.5 | 91.5 | — | — | — | — | — | — | 400K | 73 | $1.75 |
| 6 | Grok 4.20 0309 v2 | 91.1 | 91.1 | — | — | — | — | — | — | — | 105 | $2.00 |
| 7 | Claude Opus 4.7 | 90.9 | 94.2 | 87.6 | — | — | — | — | — | 1M | 49 | $5.00 |
| 8 | Gemini 3 Flash | 90.2 | 90.4 | 84.4 | 97 | — | — | 89 | — | 1M | 191 | $0.50 |
| 9 | Grok 4.3 | 90.1 | 90.1 | — | — | — | — | — | — | 1M | 88 | $1.25 |
| 10 | DeepSeek V3.2 Speciale | 89.9 | 87.1 | 89.6 | 96.7 | — | — | 86.3 | — | 164K | — | $0.29 |
| 11 | GPT-5.2-Codex | 89.9 | 89.9 | — | — | — | — | — | — | 400K | 106 | $1.75 |
| 12 | DeepSeek-V4-Flash | 89.4 | 89.4 | — | — | — | — | — | — | 1M | 109 | $0.10 |
| 13 | Grok-4 Heavy | 89.3 | 88.4 | 79.4 | 100 | — | — | — | — | — | — | — |
| 14 | Qwen3.5 397B A17B | 89.3 | 89.3 | — | — | — | — | — | — | 262K | 53 | $0.39 |
| 15 | GLM 4.7 | 89 | 85.9 | 89.4 | 95 | — | — | 85.6 | — | 203K | 98 | $0.40 |
| 16 | GPT-5.1 | 89 | 88.1 | 86.8 | 94 | — | — | 87 | — | 400K | 115 | $1.25 |
| 17 | Qwen3.6 Max | 88.8 | 88.8 | — | — | — | — | — | — | 262K | 36 | $1.04 |
| 18 | Grok 4.20 0309 | 88.5 | 88.5 | — | — | — | — | — | — | — | 97 | $2.00 |
| 19 | Muse Spark | 88.4 | 88.4 | — | — | — | — | — | — | — | — | $0.00 |
| 20 | GPT-5 Pro | 88.4 | 88.4 | — | — | — | — | — | — | 400K | — | $15.00 |
| 21 | GPT-5.1-Codex | 88.2 | 86 | 84.9 | 95.7 | — | — | 86 | — | 400K | 188 | $1.25 |
| 22 | Qwen3.6 Plus | 88.2 | 88.2 | — | — | — | — | — | — | 1M | 52 | $0.33 |
| 23 | DeepSeek-V4-Pro | 88.2 | 90.1 | 87.1 | — | — | — | 87.5 | — | 1M | 30 | $0.44 |
| 24 | MiMo-V2-Flash | 88 | 84.6 | 86.8 | 96.3 | — | — | 84.3 | — | 262K | 145 | $0.10 |
| 25 | Claude Opus 4.5 | 88 | 87 | 84 | 91.3 | — | — | 89.5 | — | 200K | 58 | $5.00 |
| 26 | Kimi K2.5 | 87.9 | 87.9 | — | — | — | — | — | — | 262K | 35 | $0.40 |
| 27 | GPT-5.4 mini | 87.5 | 87.5 | — | — | — | — | — | — | 400K | 162 | $0.75 |
| 28 | MiniMax M2.7 | 87.4 | 87.4 | — | — | — | — | — | — | 205K | 50 | $0.28 |
| 29 | GPT-5 Codex | 87.1 | 83.7 | 79.3 | 98.7 | — | — | 86.5 | — | 400K | 180 | $1.25 |
| 30 | DeepSeek-V3.2 | 87.1 | 84 | 86.2 | 92 | — | — | 86.2 | — | 131K | — | $0.25 |
| 31 | MiMo-V2-Pro | 87 | 87 | — | — | — | — | — | — | 1M | 60 | $1.00 |
| 32 | GLM 5.1 | 86.8 | 86.8 | — | — | — | — | — | — | 203K | 53 | $0.98 |
| 33 | Hy3 | 86.7 | 86.7 | — | — | — | — | — | — | 262K | 100 | $0.07 |
| 34 | MiMo-V2.5-Pro | 86.6 | 86.6 | — | — | — | — | — | — | 1M | 58 | $1.00 |
| 35 | GPT-5.2 | 86.2 | 72.7 | 84.7 | 100 | — | — | 87.4 | — | 400K | 73 | $1.75 |
| 36 | Grok-3 Mini | 85.9 | 84 | 80.4 | 93.3 | — | — | — | — | 128K | 100 | $0.30 |
| 37 | Qwen3.5-27B | 85.8 | 85.8 | — | — | — | — | — | — | 262K | 91 | $0.20 |
| 38 | Qwen3.5-122B-A10B | 85.7 | 85.7 | — | — | — | — | — | — | 262K | 129 | $0.26 |
| 39 | Gemma 4 31B | 85.7 | 85.7 | — | — | — | — | — | — | 262K | 36 | $0.12 |
| 40 | Ring-2.6-1T | 85.7 | 85.7 | — | — | — | — | — | — | 262K | 120 | $0.08 |
| 41 | Grok 4.1 Fast | 85.6 | 85.3 | 82.2 | 89.3 | — | — | 85.4 | — | — | — | $0.00 |
| 42 | Kimi K2 Thinking | 85.6 | 84.5 | 78.3 | 94.7 | — | — | 84.8 | — | 262K | 100 | $0.60 |
| 43 | MiMo-V2-Omni-0327 | 85.5 | 85.5 | — | — | — | — | — | — | — | 110 | $0.40 |
| 44 | KAT-Coder-Pro V2 | 85.5 | 85.5 | — | — | — | — | — | — | 256K | 108 | $0.30 |
| 45 | Nanbeige4.1-3B | 84.9 | 84.9 | — | — | — | — | — | — | — | — | $0.00 |
| 46 | MiMo-V2.5 | 84.9 | 84.9 | — | — | — | — | — | — | 1M | 92 | $0.40 |
| 47 | MiniMax M2.5 | 84.8 | 84.8 | — | — | — | — | — | — | 205K | 87 | $0.15 |
| 48 | GPT-5.1-Codex-Mini | 84.7 | 81.3 | 83.6 | 91.7 | — | — | 82 | — | 400K | 175 | $0.25 |
| 49 | GLM 5 Turbo | 84.7 | 84.7 | — | — | — | — | — | — | 203K | — | $1.20 |
| 50 | o3 Pro | 84.5 | 84.5 | — | — | — | — | — | — | 200K | 25 | $20.00 |
| 51 | Qwen3.5-35B-A3B | 84.5 | 84.5 | — | — | — | — | — | — | 262K | 121 | $0.14 |
| 52 | Qwen3 235B A22B 2507 | 84.2 | 79 | 78.8 | 94.7 | — | — | 84.3 | — | — | 59 | $0.40 |
| 53 | Qwen3.6 27B | 84.2 | 84.2 | — | — | — | — | — | — | 262K | 64 | $0.30 |
| 54 | Qwen3.6 35B A3B | 84.1 | 84.1 | — | — | — | — | — | — | 262K | 169 | $0.15 |
| 55 | MiniMax M2.1 | 83.6 | 83 | 81 | 82.7 | — | — | 87.5 | — | 205K | 92 | $0.29 |
| 56 | DeepSeek V3.1 Terminus | 83.5 | 79.2 | 79.8 | 89.7 | — | — | 85.1 | — | 164K | — | $0.27 |
| 57 | Gemini 3.1 Pro | 83.2 | 85.7 | 80.6 | — | — | — | — | — | 1M | 142 | $2.00 |
| 58 | Step 3.5 Flash | 83.1 | 83.1 | — | — | — | — | — | — | 262K | 194 | $0.09 |
| 59 | JT-35B-Flash | 82.9 | 82.9 | — | — | — | — | — | — | — | — | $0.00 |
| 60 | MiMo-V2-Omni | 82.8 | 82.8 | — | — | — | — | — | — | 262K | 108 | $0.40 |
| 61 | Gemini 3 Pro | 82.8 | 61.5 | 84 | 95.7 | — | — | 89.8 | — | 1M | 141 | $2.00 |
| 62 | Qwen3.5 Omni Plus | 82.6 | 82.6 | — | — | — | — | — | — | — | 54 | $0.40 |
| 63 | Step 3.5 Flash 2603 | 82.6 | 82.6 | — | — | — | — | — | — | — | 197 | $0.00 |
| 64 | Grok-3 | 82.6 | 84.6 | 79.4 | 91.2 | — | 78 | 80 | — | 128K | 100 | $3.00 |
| 65 | o1-pro | 82.5 | 79 | — | 86 | — | — | — | — | 200K | — | $150.00 |
| 66 | K-EXAONE | 82.3 | 78.3 | 76.8 | 90.3 | — | — | 83.8 | — | — | — | $0.00 |
| 67 | Kimi-k1.5 | 82.2 | — | — | 86.9 | — | 72.5 | 87.2 | — | — | — | — |
| 68 | Gemini 3.1 Flash Lite | 82.2 | 82.2 | — | — | — | — | — | — | 1M | 342 | $0.25 |
| 69 | Nova 2 Lite | 82.1 | 81.1 | 71.1 | 94.3 | — | — | 81.8 | — | 1M | 229 | $0.30 |
| 70 | GLM-5 | 81.9 | 86 | 77.8 | — | — | — | — | — | 203K | 67 | $0.60 |
| 71 | KAT-Coder-Pro V1 | 81.8 | 76.4 | 74.7 | 94.7 | — | — | 81.3 | — | — | 108 | $0.30 |
| 72 | ERNIE 5.0 Thinking | 81.7 | 77.7 | 81.2 | 85 | — | — | 83 | — | — | — | $0.00 |
| 73 | GPT-5.4 nano | 81.7 | 81.7 | — | — | — | — | — | — | 400K | 157 | $0.20 |
| 74 | INTELLECT-3 | 81 | 76.1 | 77.7 | 88 | — | — | 82.2 | — | 131K | — | $0.20 |
| 75 | Nova 2.0 Pro | 80.9 | 78.5 | 73 | 89 | — | — | 83 | — | — | 149 | $1.30 |
| 76 | Grok 3 mini Reasoning | 80.9 | 79.1 | 69.6 | 92 | — | — | 82.8 | — | — | 33 | $0.30 |
| 77 | GLM 5V Turbo | 80.9 | 80.9 | — | — | — | — | — | — | 203K | — | $1.20 |
| 78 | Qwen3.5-9B | 80.6 | 80.6 | — | — | — | — | — | — | 262K | 51 | $0.04 |
| 79 | GPT-5 | 80.5 | 87.3 | 82.5 | 78.4 | 66.2 | 81.3 | 87.1 | — | 400K | 100 | $1.25 |
| 80 | Claude Sonnet 4.5 | 80.4 | 83.4 | 66.2 | 87 | 78.1 | — | 87.5 | — | 1M | 42 | $3.00 |
| 81 | Apriel-v1.6-15B-Thinker | 80.3 | 73.3 | 80.7 | 88 | — | — | 79 | — | — | — | $0.00 |
| 82 | Qwen3-Next-80B-A3B | 80.3 | 75.9 | 78.4 | 84.3 | — | — | 82.4 | — | 262K | 147 | $0.50 |
| 83 | NVIDIA Nemotron 3 Nano 30B A3B | 80.1 | 75.7 | 74.1 | 91 | — | — | 79.4 | — | — | 148 | $0.10 |
| 84 | NVIDIA Nemotron 3 Super 120B A12B | 80 | 80 | — | — | — | — | — | — | — | 211 | $0.30 |
| 85 | EXAONE 4.0 32B | 79.8 | 73.9 | 74.7 | 88.9 | — | — | 81.8 | — | — | — | $0.00 |
| 86 | Qwen3-235B-A22B-Thinking-2507 | 79.6 | 81.1 | — | 92.3 | 60.9 | — | 84.3 | — | 256K | — | $0.30 |
| 87 | gpt-oss-120b | 79.6 | 80.9 | 75.1 | 93.4 | 67.8 | — | 80.8 | — | 131K | 500 | $0.04 |
| 88 | Qwen3 Max | 79.5 | 76.4 | 76.7 | 80.7 | — | — | 84.1 | — | 262K | 45 | $0.78 |
| 89 | Doubao Seed Code | 79.4 | 76.4 | 76.6 | 79.3 | — | — | 85.4 | — | — | — | $0.00 |
| 90 | EXAONE 4.5 33B | 79.4 | 79.4 | — | — | — | — | — | — | — | — | $0.00 |
| 91 | Llama Nemotron Super 49B v1.5 | 79.4 | 74.8 | 73.7 | 87.5 | — | — | 81.4 | — | — | 51 | $0.10 |
| 92 | Claude Opus 4.6 | 79.4 | 80.1 | 80.8 | — | — | 77.3 | — | — | 1M | 48 | $5.00 |
| 93 | Gemma 4 26B A4B | 79.2 | 79.2 | — | — | — | — | — | — | 262K | 66 | $0.06 |
| 94 | GPT-5 mini | 79.2 | 82.3 | 83.8 | 67 | — | — | 83.7 | — | 400K | 200 | $0.25 |
| 95 | Qwen2.5 VL 72B Instruct | 79.1 | — | — | — | — | 79.1 | — | — | 131K | — | $0.25 |
| 96 | Seed-OSS-36B-Instruct | 78.8 | 72.6 | 76.5 | 84.7 | — | — | 81.5 | — | — | 37 | $0.20 |
| 97 | Grok 4 Fast | 78.7 | 85.7 | 80 | 92.7 | 44.9 | — | 90 | — | 2M | 90 | $0.20 |
| 98 | Qwen3 VL 235B A22B | 78.4 | 77.2 | 64.6 | 88.3 | — | — | 83.6 | — | — | 34 | $0.80 |
| 99 | Qwen3 VL 32B | 78.4 | 73.3 | 73.8 | 84.7 | — | — | 81.8 | — | — | 93 | $0.70 |
| 100 | o4-mini | 78.4 | 81.4 | 70.3 | 95 | 57.5 | 82.9 | 83.2 | — | 200K | 115 | $1.10 |
| 101 | Gemini 2.5 Flash | 78.3 | 79.3 | 71.3 | 78.3 | — | — | 84.2 | — | — | — | $0.00 |
| 102 | Llama 3.1 Nemotron Ultra 253B v1 | 78.3 | 76 | 66.3 | 84.8 | — | — | 86 | — | — | 42 | $0.60 |
| 103 | Nova 2.0 Omni | 78.2 | 76 | 66 | 89.7 | — | — | 80.9 | — | — | — | $0.30 |
| 104 | Grok 4 | 78.2 | 51.7 | 79 | 95.4 | — | — | 86.6 | — | 256K | 100 | $3.00 |
| 105 | Magistral Medium 1.2 | 78.1 | 73.9 | 75 | 82 | — | — | 81.5 | — | — | 42 | $2.00 |
| 106 | Ring-1T | 77.9 | 77.4 | 64.3 | 89.3 | — | — | 80.6 | — | — | — | $0.00 |
| 107 | Nemotron Nano 9B V2 | 77.6 | 64 | 71.1 | 84.9 | — | — | 90.3 | — | 131K | — | $0.04 |
| 108 | Qwen3 Next 80B A3B Thinking | 77.5 | 77.2 | — | 87.8 | 61.7 | — | 83.1 | — | 262K | — | $0.10 |
| 109 | Apriel-v1.5-15B-Thinker | 77.2 | 71.3 | 72.8 | 87.5 | — | — | 77.3 | — | — | — | $0.00 |
| 110 | Sonar Reasoning | 77.2 | 62.3 | — | 92.1 | — | — | — | — | — | — | $0.00 |
| 111 | Qwen3.5 4B | 77.1 | 77.1 | — | — | — | — | — | — | — | 164 | $0.00 |
| 112 | Mercury 2 | 77 | 77 | — | — | — | — | — | — | 128K | 790 | $0.25 |
| 113 | Mistral Small 4 | 76.9 | 76.9 | — | — | — | — | — | — | 262K | 145 | $0.15 |
| 114 | Gemini 2.5 Pro Preview 06-05 | 76.6 | 86.4 | 72.8 | 88 | — | 82 | 54 | — | 1M | 85 | $1.25 |
| 115 | Claude Sonnet 4.6 | 76.3 | 72.9 | 79.6 | — | — | — | — | — | 1M | 75 | $3.00 |
| 116 | Qwen3 VL 30B A3B | 76.2 | 72 | 69.7 | 82.3 | — | — | 80.7 | — | — | 122 | $0.20 |
| 117 | Qwen3 Max Thinking | 76.1 | 86.1 | 53.5 | 82.3 | — | — | 82.4 | — | 262K | 45 | $0.78 |
| 118 | GPT-5.5 | 76.1 | 93.5 | 58.6 | — | — | — | — | — | 1.1M | 67 | $5.00 |
| 119 | MiniMax-M2 | 76 | 77.7 | 66.1 | 78.3 | — | — | 82 | — | 205K | 91 | $0.26 |
| 120 | Cogito v2.1 | 75.8 | 76.8 | 68.8 | 72.7 | — | — | 84.9 | — | — | 56 | $1.30 |
| 121 | Nemotron Cascade 2 30B A3B | 75.8 | 75.8 | — | — | — | — | — | — | — | — | $0.00 |
| 122 | Qwen3 | 75.8 | 65.8 | — | 81.5 | — | — | 80 | — | 128K | — | — |
| 123 | MiniMax M1 80k | 75.5 | 69.7 | 71.1 | 79.5 | — | — | 81.6 | — | — | — | $0.60 |
| 124 | Claude Opus 4.1 | 75.4 | 80.9 | 61.1 | 78 | 69.2 | — | 88 | — | 200K | 120 | $15.00 |
| 125 | Claude Haiku 4.5 | 75.3 | 73 | 53.8 | 96.3 | 73.4 | — | 80 | — | 200K | 100 | $1.00 |
| 126 | Trinity Large Thinking | 75.2 | 75.2 | — | — | — | — | — | — | 262K | 129 | $0.22 |
| 127 | Ling-2.6-1T | 75.2 | 75.2 | — | — | — | — | — | — | 262K | — | $0.08 |
| 128 | DeepSeek-R1 | 75 | 71.5 | 61.7 | 82.3 | — | — | 84.4 | — | 128K | 189 | $0.55 |
| 129 | DeepSeek VL2 | 74.9 | — | — | — | — | 74.9 | — | — | 129K | 22 | $9.50 |
| 130 | Qwen3 235B A22B | 74.9 | 68.2 | 68.3 | 86.7 | 70.8 | — | 80.3 | — | 131K | 68 | $0.46 |
| 131 | Kimi K2.6 | 74.9 | 91.1 | 58.6 | — | — | — | — | — | 262K | 57 | $0.73 |
| 132 | GPT-5.4 | 74.9 | 92 | 57.7 | — | — | — | — | — | 1.1M | 84 | $2.50 |
| 133 | Mistral Medium 3.5 | 74.8 | 74.8 | — | — | — | — | — | — | 262K | 140 | $1.50 |
| 134 | Qwen3 30B A3B 2507 | 74.7 | 70.7 | 70.7 | 76.9 | — | — | 80.5 | — | — | 151 | $0.30 |
| 135 | Claude 3.7 Sonnet | 74.7 | 84.8 | 50.9 | 79.1 | 69.8 | 75 | 88.5 | — | 200K | 101 | $3.00 |
| 136 | Ring-flash-2.0 | 74.6 | 72.5 | 62.8 | 83.7 | — | — | 79.3 | — | — | — | $0.10 |
| 137 | Claude Sonnet 4 | 74.5 | 75.4 | 57.9 | 84.8 | 70.3 | 74.4 | 84.2 | — | 1M | 101 | $3.00 |
| 138 | Mi:dm K 2.5 Pro | 74.4 | 72.2 | 65.6 | 78.7 | — | — | 81.3 | — | — | — | $0.00 |
| 139 | DeepSeek-Coder-V2 | 74.3 | — | — | 74.3 | — | — | — | — | — | — | $0.00 |
| 140 | Qwen3.5 Omni Flash | 74.2 | 74.2 | — | — | — | — | — | — | — | 235 | $0.10 |
| 141 | Magistral Small 1.2 | 73.9 | 66.3 | 72.3 | 80.3 | — | — | 76.8 | — | — | 106 | $0.50 |
| 142 | Sarvam 105B | 73.8 | 73.8 | — | — | — | — | — | — | — | 128 | $0.00 |
| 143 | Qwen3 32B | 73.8 | 66.8 | 65.7 | 83.5 | 70.3 | — | 82.8 | — | 131K | 328 | $0.08 |
| 144 | Qwen3 Coder Next | 73.7 | 73.7 | — | — | — | — | — | — | 262K | 92 | $0.11 |
| 145 | K2-V2 | 73.6 | 68.1 | 69.4 | 78.3 | — | — | 78.6 | — | — | — | $0.00 |
| 146 | Motif-2-12.7B-Reasoning | 73.6 | 69.5 | 65.1 | 80.3 | — | — | 79.6 | — | — | — | $0.00 |
| 147 | gpt-oss-20b | 73.6 | 71.5 | 77.7 | 89.3 | 54.8 | — | 74.8 | — | 131K | 1000 | $0.03 |
| 148 | Kimi K2 | 73.6 | 76.6 | 60.7 | 74.6 | — | — | 82.4 | — | 131K | 26 | $0.57 |
| 149 | Hermes 4 - Llama-3.1 405B | 73.5 | 72.7 | 68.6 | 69.7 | — | — | 82.9 | — | — | 34 | $1.00 |
| 150 | Qwen3 Omni 30B A3B | 73.4 | 72.6 | 67.9 | 74 | — | — | 79.2 | — | — | 102 | $0.30 |
| 151 | Ling-1T | 73.3 | 71.9 | 67.7 | 71.3 | — | — | 82.2 | — | — | — | $0.00 |
| 152 | Phi 4 Mini Reasoning | 73.3 | 52 | — | 94.6 | — | — | — | — | — | — | — |
| 153 | DeepSeek VL2 Small | 73.1 | — | — | — | — | 73.1 | — | — | — | — | — |
| 154 | Gemini 2.5 Flash | 73.1 | 82.8 | 62.1 | 86 | — | 79.7 | 55.1 | — | 1M | 85 | $0.30 |
| 155 | GLM-4.5 | 73 | 79.1 | 58.2 | 87.6 | 55.5 | — | 84.6 | — | 131K | 85 | $0.60 |
| 156 | Falcon-H1R-7B | 72.8 | 66.1 | 72.4 | 80 | — | — | 72.5 | — | — | — | $0.00 |
| 157 | Solar Pro 2 | 72.5 | 68.7 | 61.6 | 79 | — | — | 80.5 | — | — | — | $0.00 |
| 158 | Solar Pro 3 | 72.4 | 72.4 | — | — | — | — | — | — | 128K | — | $0.15 |
| 159 | GLM-4.6 | 72.4 | 81 | 59.3 | 93.9 | 45.1 | — | 82.9 | — | 203K | 85 | $0.43 |
| 160 | Gemini 2.5 Flash-Lite | 72.3 | 70.9 | 68.8 | 68.7 | — | — | 80.8 | — | — | — | $0.10 |
| 161 | Qwen3-235B-A22B-Instruct-2507 | 72.2 | 77.5 | 65.9 | 84.2 | 57.7 | — | 75.9 | — | 131K | 63 | $0.15 |
| 162 | DeepSeek V3.2 Exp | 72.2 | 79.9 | 63.5 | 86.4 | 40.1 | — | 91.1 | — | 164K | 100 | $0.27 |
| 163 | Qwen3 4B 2507 | 71.9 | 66.7 | 64.1 | 82.7 | — | — | 74.3 | — | — | — | $0.00 |
| 164 | Qwen3 30B A3B | 71.7 | 65.8 | 62.6 | 82.4 | 69.1 | — | 78.8 | — | 131K | 122 | $0.09 |
| 165 | Gemini 2.5 Pro | 71.6 | 44.5 | 73.3 | 92.2 | — | 79.6 | 68.4 | — | 1M | 85 | $1.25 |
| 166 | o3 | 71.6 | 47.1 | 77.1 | 73.3 | 64.9 | 82 | 85.3 | — | 200K | 50 | $2.00 |
| 167 | DeepSeek R1 Zero | 71.5 | 73.3 | 50 | 91.3 | — | — | — | — | — | — | — |
| 168 | K2 Think V2 | 71.3 | 71.3 | — | — | — | — | — | — | — | — | $0.00 |
| 169 | Hermes 4 - Llama-3.1 70B | 71.3 | 69.9 | 65.3 | 68.7 | — | — | 81.1 | — | — | 60 | $0.10 |
| 170 | Grok-1.5V | 71.3 | — | — | — | — | 71.3 | — | — | — | — | — |
| 171 | GPT-5 nano | 71.2 | 71.2 | 78.9 | 56.8 | — | — | 78 | — | 400K | 500 | $0.05 |
| 172 | Kimi K2 0905 | 71 | 75.8 | 61 | 64.7 | — | — | 82.5 | — | 262K | 16 | $0.60 |
| 173 | QvQ-72B-Preview | 70.9 | — | — | — | — | 70.9 | — | — | — | — | — |
| 174 | Ministral 8B Instruct | 70.9 | — | — | — | — | — | 70.9 | — | 128K | 0 | $0.10 |
| 175 | Qwen3 VL 235B A22B Instruct | 70.9 | 71.2 | 59.4 | 70.7 | — | — | 82.3 | — | 262K | 51 | $0.20 |
| 176 | Olmo 3.1 32B Think | 70.6 | 59.1 | 69.5 | 77.3 | — | — | 76.3 | — | — | — | $0.00 |
| 177 | o1-mini | 70.5 | 60 | 57.6 | 90 | — | — | 74.2 | — | 128K | 115 | $3.00 |
| 178 | Phi 4 Reasoning Plus | 70.4 | 68.9 | 53.1 | 79.7 | — | — | 80 | — | — | — | — |
| 179 | GLM 4.5 Air | 70.4 | 75 | 52.8 | 89.4 | 53.3 | — | 81.4 | — | 131K | 63 | $0.13 |
| 180 | Claude 3.5 Sonnet | 70.3 | 82.5 | 43.6 | 77.1 | 57.6 | 83.3 | 77.6 | — | 200K | 101 | $3.00 |
| 181 | DeepSeek R1 Distill Llama 70B | 70.1 | 65.2 | 57.5 | 78.3 | — | — | 79.5 | — | 128K | 37 | $0.10 |
| 182 | GLM 4.5V | 70.1 | 68.4 | 60.4 | 73 | — | — | 78.8 | — | 66K | 85 | $0.60 |
| 183 | Qwen2.5 VL 7B Instruct | 70 | — | — | — | — | 70 | — | — | — | — | — |
| 184 | GLM 4.6V | 69.6 | 71.9 | 41.1 | 85.3 | — | — | 79.9 | — | 131K | 44 | $0.30 |
| 185 | Olmo 3 32B Think | 69.5 | 61 | 67.2 | 73.7 | — | — | 75.9 | — | 66K | — | $0.15 |
| 186 | Gemini 3 Deep Think | 69.5 | 69.5 | — | — | — | — | — | — | 1M | — | $0.00 |
| 187 | NVIDIA Nemotron Nano 12B v2 VL | 69.4 | 57.2 | 69.4 | 75 | — | — | 75.9 | — | — | 244 | $0.20 |
| 188 | Claude Opus 4 | 69.4 | 44.1 | 58.4 | 86.9 | 70.5 | — | 87.3 | — | 200K | 120 | $15.00 |
| 189 | Qwen3 30B A3B 2507 Instruct | 69.3 | 65.9 | 51.5 | 81.9 | — | — | 77.7 | — | — | 122 | $0.20 |
| 190 | Gemini 2.0 Flash Thinking | 69.1 | 74.2 | 32.1 | 83.9 | — | 75.4 | 79.8 | — | — | — | $0.00 |
| 191 | Step3 VL 10B | 69 | 69 | — | — | — | — | — | — | — | — | $0.00 |
| 192 | Qwen3 Next 80B A3B Instruct | 68.9 | 72.9 | 68.7 | 69.5 | 51.9 | — | 81.3 | — | 262K | 161 | $0.09 |
| 193 | Granite 3.3 8B Instruct | 68.5 | 64.3 | — | 75.1 | — | — | 66.2 | — | — | — | — |
| 194 | DeepSeek R1 Distill Qwen 32B | 68.4 | 62.1 | 57.2 | 80.2 | — | — | 73.9 | — | 128K | 37 | $0.12 |
| 195 | NVIDIA Nemotron Nano 9B V2 | 68.3 | 57 | 72.4 | 69.7 | — | — | 74.2 | — | — | 129 | $0.00 |
| 196 | Llama 3.1 Nemotron Nano 8B V1 | 68.2 | 54.1 | — | 71.3 | — | — | 79.3 | — | — | — | — |
| 197 | ERNIE 4.5 300B A47B | 68.2 | 81.1 | 46.7 | 67.2 | — | — | 77.6 | — | 131K | 24 | $0.28 |
| 198 | QwQ-32B | 67.8 | 65.2 | 63.4 | 66.4 | 66.4 | — | 77.8 | — | — | 31 | $0.70 |
| 199 | MiniMax M1 40k | 67.6 | 68.2 | 65.7 | 55.5 | — | — | 80.8 | — | — | — | $0.00 |
| 200 | JT-MINI | 67.6 | 67.6 | — | — | — | — | — | — | — | — | $0.00 |
| 201 | Gemini 2.0 Pro | 67.4 | 62.2 | 34.7 | 92.3 | — | — | 80.5 | — | — | — | $0.00 |
| 202 | Qwen2-VL-72B-Instruct | 67.3 | — | — | — | — | 67.3 | — | — | — | — | — |
| 203 | Gemini 1.5 Pro | 67.3 | 74.4 | 31.6 | 87.6 | — | 67 | 75.8 | — | 2M | 85 | $1.25 |
| 204 | DeepSeek VL2 Tiny | 67.2 | — | — | — | — | 67.2 | — | — | — | — | — |
| 205 | Ling-flash-2.0 | 66.9 | 65.7 | 58.9 | 65.3 | — | — | 77.7 | — | — | 91 | $0.10 |
| 206 | Qwen3 14B | 66.8 | 60.4 | 52.3 | 77.1 | — | — | 77.4 | — | 132K | 62 | $0.10 |
| 207 | Qwen2.5 32B Instruct | 66.7 | 67 | 50.1 | 80.5 | — | — | 69 | — | — | — | $0.00 |
| 208 | Qwen3 Coder 480B A35B Instruct | 66.5 | 61.8 | 58.5 | 66.8 | — | — | 78.8 | — | — | 69 | $0.30 |
| 209 | Kimi K2 Instruct | 66.5 | 75.1 | 60.4 | 63.8 | 63.6 | — | 69.6 | — | 131K | 45 | $0.57 |
| 210 | Qwen3 VL 30B A3B Instruct | 66.5 | 69.5 | 47.6 | 72.3 | — | — | 76.4 | — | 262K | 123 | $0.13 |
| 211 | Qwen3 VL 32B Instruct | 66.5 | 67.1 | 51.4 | 68.3 | — | — | 79.1 | — | 262K | 76 | $0.10 |
| 212 | Phi 4 Reasoning | 66.4 | 65.8 | 53.8 | 69.1 | — | — | 77 | — | — | — | — |
| 213 | DeepSeek R1 0528 Qwen3 8B | 66.2 | 61.2 | 51.3 | 78.5 | — | — | 73.9 | — | — | — | $0.00 |
| 214 | Qwen2.5 14B Instruct | 66.1 | 61.9 | 72.8 | — | — | — | 63.7 | — | — | — | — |
| 215 | Pixtral-12B | 66.1 | — | — | — | — | 70.8 | 61.3 | — | 128K | 0 | $0.15 |
| 216 | Kimi K2-Instruct-0905 | 66 | 75.1 | 58 | 63.8 | 63.6 | — | 69.6 | — | — | — | — |
| 217 | Grok-2 mini | 65.9 | 51 | — | — | — | 74.8 | 72 | — | — | — | — |
| 218 | DeepSeek-V3 0324 | 65.9 | 68.4 | 49.2 | 64.8 | — | — | 81.2 | — | 164K | — | $0.28 |
| 219 | Solar Open 100B | 65.7 | 65.7 | — | — | — | — | — | — | — | — | $0.00 |
| 220 | DeepSeek R1 Distill Qwen 14B | 65.7 | 59.1 | 53.1 | 76.5 | — | — | 74 | — | — | — | $0.00 |
| 221 | Magistral Medium 1 | 65.5 | 67.9 | 52.7 | 66 | — | — | 75.3 | — | — | — | $0.00 |
| 222 | HyperCLOVA X SEED Think | 65.5 | 61.5 | 62.9 | 59 | — | — | 78.5 | — | — | — | $0.00 |
| 223 | o1 | 65.4 | 78 | 54.5 | 58.9 | 60.4 | 74.7 | 66 | — | 200K | 66 | $15.00 |
| 224 | Grok Code Fast 1 | 65.3 | 72.7 | 65.7 | 43.3 | — | — | 79.3 | — | — | — | $0.00 |
| 225 | Magistral Small 1 | 64.7 | 64.1 | 51.4 | 68.8 | — | — | 74.6 | — | — | — | $0.00 |
| 226 | Granite 3.3 8B Base | 64.6 | 52.6 | — | 75.1 | — | — | 66.2 | — | — | — | — |
| 227 | o3-mini | 64.1 | 77.2 | 62.5 | 65 | 45 | — | 70.6 | — | 200K | 115 | $1.10 |
| 228 | Llama-3.3 Nemotron Super 49B v1 | 63.9 | 66.7 | 28 | 77.5 | — | — | 83.4 | — | — | — | $0.00 |
| 229 | Llama 4 Maverick | 63.9 | 69.8 | 36.7 | 54.1 | — | 78.2 | 80.5 | — | 1M | 639 | $0.15 |
| 230 | GPT-4.1 | 63.8 | 66.3 | 51.2 | 53.7 | 58.7 | 73.5 | 79.6 | — | 1M | 100 | $2.00 |
| 231 | Qwen2.5 Max | 63.6 | 58.7 | 35.9 | 83.5 | — | — | 76.2 | — | — | 50 | $1.60 |
| 232 | LongCat Flash Lite | 63.6 | 63.6 | — | — | — | — | — | — | — | 110 | $0.00 |
| 233 | DeepSeek-V2.5 | 63.4 | 84.3 | 16.8 | 76.3 | — | — | 76.2 | — | 8K | 100 | $0.14 |
| 234 | Sarvam 30B | 63.3 | 63.3 | — | — | — | — | — | — | — | 214 | $0.00 |
| 235 | DeepSeek-R1-0528 | 63.3 | 81 | 48.8 | 89.2 | 8.9 | — | 88.7 | — | 131K | 45 | $0.55 |
| 236 | Magistral Medium | 62.9 | 70.8 | 48.7 | 69.3 | — | — | — | — | — | — | — |
| 237 | QwQ-32B-Preview | 62.6 | 65.2 | 50 | 70.3 | — | — | 64.8 | — | 33K | 99 | $0.15 |
| 238 | Olmo 3 7B Think | 62.4 | 51.6 | 61.7 | 70.7 | — | — | 65.5 | — | — | — | $0.00 |
| 239 | Grok-2 | 62.4 | 56 | 26.7 | 77.8 | — | 76.2 | 75.5 | — | 128K | 85 | $2.00 |
| 240 | Qwen2.5 VL 32B Instruct | 62.1 | 46 | — | — | — | 71.4 | 68.8 | — | — | — | — |
| 241 | Mistral Small 3 24B Instruct | 62.1 | 45.3 | — | — | — | — | 78.9 | — | 32K | 134 | $0.10 |
| 242 | Magistral Small 2506 | 62.1 | 68.2 | 51.3 | 66.8 | — | — | — | — | — | — | — |
| 243 | Gemini 1.5 Flash | 61.9 | 68.3 | 27.3 | 82.7 | — | 64.1 | 67.3 | — | 1M | 150 | $0.15 |
| 244 | Phi-3.5-vision-instruct | 61.7 | — | — | — | — | 61.7 | — | — | — | — | — |
| 245 | Nova Pro | 61.6 | 73.1 | 23.3 | 42.8 | 68.4 | 81.5 | 80.6 | — | 300K | 100 | $0.80 |
| 246 | MiniMax-M1 | 61.5 | — | — | — | — | — | — | 61.5 | 1M | — | $0.40 |
| 247 | Llama 3.1 405B Instruct | 60.9 | 67.8 | 30.5 | 36.7 | 88.5 | — | 80.9 | — | 128K | 100 | $0.89 |
| 248 | Gemini 2.0 Flash | 60.3 | 62.1 | 35.1 | 57.4 | — | 70.7 | 76.4 | — | 1M | 183 | $0.10 |
| 249 | Tri-21B-Think | 60.1 | 60.1 | — | — | — | — | — | — | — | — | $0.00 |
| 250 | Qwen2 72B Instruct | 59.9 | 62.4 | 42.6 | 70.1 | — | — | 64.4 | — | — | — | $0.00 |
| 251 | DeepSeek-V3.1 | 59.8 | 74.9 | 55.5 | 49.9 | 30 | — | 88.6 | — | 164K | — | $0.21 |
| 252 | GPT-4 Turbo | 59.8 | 67 | 29.1 | 73.7 | — | — | 69.4 | — | 128K | 100 | $10.00 |
| 253 | GPT-4.5 | 59.4 | 71.4 | 41.5 | 36.7 | 59.2 | 73.8 | 73.8 | — | 128K | 50 | $75.00 |
| 254 | Ling-2.6-flash | 59.3 | 59.3 | — | — | — | — | — | — | 262K | — | $0.01 |
| 255 | Qwen2.5 72B Instruct | 59.1 | 49 | 65.3 | 49.9 | — | — | 72.2 | — | 131K | 100 | $0.36 |
| 256 | Llama 4 Scout | 58.9 | 57.2 | 32.8 | 49.2 | — | 80.8 | 74.3 | — | 10M | 776 | $0.08 |
| 257 | Sonar Pro | 58.8 | 57.8 | 27.5 | 74.5 | — | — | 75.5 | — | 200K | — | $3.00 |
| 258 | Mistral Medium 3 | 58.6 | 57.8 | 40 | 60.5 | — | — | 76 | — | 131K | 32 | $0.40 |
| 259 | Claude 3 Opus | 58.5 | 73.4 | 27.9 | 64.1 | — | — | 68.5 | — | 200K | 120 | $15.00 |
| 260 | Gemma 3 27B | 58.4 | 65 | 29.7 | — | — | 83 | 56 | — | 131K | 33 | $0.08 |
| 261 | DeepSeek R1 Distill Qwen 7B | 58.3 | 49.1 | 37.6 | 88.1 | — | — | — | — | — | — | — |
| 262 | Mistral Large 3 | 58.3 | 68 | 46.5 | 38 | — | — | 80.7 | — | 262K | 54 | $0.50 |
| 263 | GPT-4 | 58.3 | 58.3 | — | — | — | — | — | — | 8K | 104 | $30.00 |
| 264 | GPT-4.1 Mini | 58.2 | 65 | 34.6 | 54.3 | 45.9 | 72.9 | 76.4 | — | 1M | 150 | $0.40 |
| 265 | GLM 4.7 Flash | 58.1 | 58.1 | — | — | — | — | — | — | 203K | 113 | $0.06 |
| 266 | DeepSeek-V3 | 58.1 | 75.4 | 52.2 | 51.8 | — | — | 62.3 | 48.7 | 131K | 100 | $0.23 |
| 267 | Qwen3 8B | 57.8 | 58.9 | 40.6 | 57.4 | — | — | 74.3 | — | 131K | 69 | $0.05 |
| 268 | Nova Lite | 57.7 | 68.2 | 16.7 | 41.8 | 66.6 | 78.5 | 74.4 | — | 300K | 100 | $0.06 |
| 269 | Gemma 4 E4B | 57.6 | 57.6 | — | — | — | — | — | — | — | — | $0.00 |
| 270 | Llama 3.1 Tulu3 405B | 57.5 | 51.6 | 29.1 | 77.8 | — | — | 71.6 | — | — | — | $0.00 |
| 271 | Qwen3 Omni 30B A3B Instruct | 57.3 | 62 | 42.2 | 52.3 | — | — | 72.5 | — | — | 103 | $0.30 |
| 272 | o1-preview | 57.3 | 73.3 | 41.3 | 67.2 | — | — | 47.3 | — | 128K | 66 | $15.00 |
| 273 | Mistral Saba | 57.1 | 42.4 | — | 67.7 | — | — | 61.1 | — | — | — | $0.00 |
| 274 | Gemini 2.5 Flash Lite | 57 | 64.6 | 30.7 | 73.4 | — | 72.9 | 43.3 | — | 1M | 6 | $0.10 |
| 275 | Gemma 3n E4B | 56.9 | 56.9 | — | — | — | — | — | — | — | — | — |
| 276 | Sonar | 56.8 | 47.1 | 29.5 | 81.7 | — | — | 68.9 | — | 127K | — | $1.00 |
| 277 | Qwen3 4B | 56.5 | 52.2 | 46.5 | 57.8 | — | — | 69.6 | — | — | 103 | $0.10 |
| 278 | Sarvam M | 56.4 | 41.6 | 29.5 | 84.7 | — | — | 69.6 | — | — | 136 | $0.00 |
| 279 | GPT-4o | 56.4 | 70.1 | 31.2 | 42.7 | 53 | 77.7 | 63.7 | — | 128K | 132 | $2.50 |
| 280 | Reka Flash 3 | 56.2 | 52.9 | 43.5 | 61.5 | — | — | 66.9 | — | 66K | 93 | $0.10 |
| 281 | Mistral Small 3.2 24B Instruct | 56.2 | 46.1 | — | — | — | 81 | 41.4 | — | — | — | — |
| 282 | Llama 3.1 70B Instruct | 56 | 60.7 | 23.2 | 34.5 | 84.8 | — | 77 | — | 131K | 1204 | $0.40 |
| 283 | Command A | 55.9 | 76.1 | 28.7 | 47.5 | — | — | 71.2 | — | 256K | 203 | $2.50 |
| 284 | Gemma 3 12B | 55.5 | 63.3 | 24.6 | — | — | 82.3 | 51.9 | — | 131K | 33 | $0.04 |
| 285 | Qwen3 Coder 30B A3B Instruct | 55.4 | 51.6 | 40.3 | 59.2 | — | — | 70.6 | — | 160K | 97 | $0.07 |
| 286 | Qwen3-Coder | 55.4 | — | 55.4 | — | — | — | — | — | 262K | — | — |
| 287 | Llama 3.1 Nemotron Nano 4B v1.1 | 54.5 | 40.8 | 49.3 | 72.4 | — | — | 55.6 | — | — | — | $0.00 |
| 288 | Claude 3.5 Haiku | 54.5 | 62.4 | 36 | 72.1 | 36.9 | — | 65 | — | 200K | 104 | $0.80 |
| 289 | Gemini 2.0 Flash Lite | 54.4 | 51.5 | 18.5 | 87.3 | — | 68 | 46.7 | — | 1M | 85 | $0.08 |
| 290 | Devstral 2 | 54.3 | 59.4 | 44.8 | 36.7 | — | — | 76.2 | — | 262K | 51 | $0.40 |
| 291 | Llama 3.2 90B Instruct | 54 | 46.7 | 21.4 | 62.9 | — | 71.8 | 67.1 | — | 128K | 100 | $0.35 |
| 292 | Ling-mini-2.0 | 53.9 | 56.2 | 42.9 | 49.3 | — | — | 67.1 | — | — | — | $0.00 |
| 293 | Olmo 3.1 32B Instruct | 53.9 | 53.9 | — | — | — | — | — | — | — | — | $0.00 |
| 294 | Grok | 53.8 | 47.1 | 24.1 | 73.7 | — | — | 70.3 | — | — | — | $0.00 |
| 295 | DeepSeek R1 Distill Llama 8B | 53.3 | 49 | 39.6 | 70.1 | — | — | 54.3 | — | — | — | $0.00 |
| 296 | Exaone 4.0 1.2B | 53.1 | 51.5 | 51.6 | 50.3 | — | — | 58.8 | — | — | — | $0.00 |
| 297 | Nova Premier | 53.1 | 56.9 | 31.7 | 50.6 | — | — | 73.3 | — | — | 40 | $2.50 |
| 298 | Pixtral Large | 53.1 | 50.5 | 26.1 | 36.9 | — | 81.7 | 70.1 | — | 131K | 0 | $2.00 |
| 299 | Reka Flash | 52.9 | — | — | 52.9 | — | — | — | — | — | 85 | $0.20 |
| 300 | Qwen3 4B 2507 Instruct | 52.2 | 51.7 | 37.7 | 52.3 | — | — | 67.2 | — | — | — | $0.00 |
| 301 | Qwen2.5-Omni-7B | 51.5 | 30.8 | 65.8 | — | — | 71.2 | 38.3 | — | — | — | — |
| 302 | Mistral Medium 3.1 | 51.5 | 58.8 | 40.6 | 38.3 | — | — | 68.3 | — | 131K | 47 | $0.40 |
| 303 | NVIDIA Nemotron 3 Nano 4B | 51.3 | 51.3 | — | — | — | — | — | — | — | — | $0.00 |
| 304 | Mistral Small 3.2 | 51 | 50.5 | 27.5 | 57.7 | — | — | 68.1 | — | — | 100 | $0.10 |
| 305 | Mistral Small 3.1 24B Base | 50.9 | 37.5 | — | — | — | 59.3 | 56 | — | 128K | 137 | $0.10 |
| 306 | Llama 3.3 70B Instruct | 50.6 | 50.5 | 28.8 | 42.5 | — | — | 80.5 | — | 131K | 2220 | $0.10 |
| 307 | Qwen2.5 Turbo | 50.3 | 41 | 16.3 | 80.5 | — | — | 63.3 | — | — | 67 | $0.10 |
| 308 | Grok-1.5 | 50.3 | 35.9 | — | — | — | 64 | 51 | — | — | — | — |
| 309 | Kimi K2 Base | 50.2 | 48.1 | — | — | — | — | 52.3 | — | — | — | — |
| 310 | Qwen2.5 Coder 32B Instruct | 50.1 | 41.7 | 31.4 | 76.7 | — | — | 50.4 | — | 128K | 110 | $0.66 |
| 311 | Phi-3.5-MoE-instruct | 49.8 | 58 | — | — | — | — | 41.6 | — | — | — | — |
| 312 | Qwen3 VL 8B | 49.7 | 57.9 | 35.3 | 30.7 | — | — | 74.9 | — | — | 120 | $0.20 |
| 313 | Gemma 3n E2B | 49.1 | 49.1 | — | — | — | — | — | — | — | — | — |
| 314 | GPT-4o-mini | 49.1 | 60 | 16 | 46.8 | — | 58.1 | 64.8 | — | 128K | 92 | $0.15 |
| 315 | Nova Micro | 49 | 66.3 | 14 | 38.2 | 56.2 | — | 70.2 | — | 128K | 100 | $0.03 |
| 316 | Gemini 1.5 Flash 8B | 48.4 | 38.4 | 21.7 | 68.9 | — | 54.2 | 58.7 | — | 1M | 150 | $0.07 |
| 317 | Granite 4.1 30B | 48.1 | 48.1 | — | — | — | — | — | — | — | — | $0.00 |
| 318 | Mistral Small 3.1 24B Instruct | 48 | 46 | — | — | — | 59.3 | 38.6 | — | — | — | — |
| 319 | IBM Granite 4.0 Tiny Preview | 48 | 51 | — | — | — | — | 44.9 | — | — | — | — |
| 320 | Ministral 3 14B | 47.9 | 57.2 | 35.1 | 30 | — | — | 69.3 | — | 262K | 67 | $0.20 |
| 321 | Mistral Large 2 | 47.9 | 48.6 | 29.3 | 43.8 | — | — | 69.7 | — | 128K | 42 | $2.00 |
| 322 | Devstral Medium | 47.8 | 49.2 | 33.7 | 37.7 | — | — | 70.8 | — | 131K | 72 | $0.40 |
| 323 | Phi 4 | 47.6 | 65.8 | 23.1 | 49.5 | — | — | 51.9 | — | 16K | 33 | $0.07 |
| 324 | Devstral Small 2 | 47.5 | 53.2 | 34.8 | 34.3 | — | — | 67.8 | — | — | 62 | $0.00 |
| 325 | LFM2-24B-A2B | 47.4 | 47.4 | — | — | — | — | — | — | 128K | 208 | $0.03 |
| 326 | Qwen3 1.7B | 46.9 | 35.6 | 30.8 | 64.1 | — | — | 57 | — | — | 138 | $0.10 |
| 327 | Nemotron 3 Nano Omni 30B A3B Reasoning | 46.9 | 46.9 | — | — | — | — | — | — | — | 301 | $0.10 |
| 328 | Qwen2.5 7B Instruct | 46.6 | 36.4 | 49.6 | — | — | — | 53.9 | — | 131K | 138 | $0.04 |
| 329 | Phi-4-multimodal-instruct | 46.2 | 31.5 | 13.1 | 69.3 | — | 68.8 | 48.5 | — | 128K | 25 | $0.05 |
| 330 | Phi-3.5-mini-instruct | 46 | 49.7 | — | — | — | — | 42.2 | — | 128K | 23 | $0.10 |
| 331 | Claude 3 Sonnet | 45.8 | 67.4 | 17.5 | 41.4 | — | — | 56.8 | — | 200K | 120 | $3.00 |
| 332 | Gemma 3 4B | 45.8 | 51.5 | 12.6 | — | — | 73.1 | 45.9 | — | 131K | 33 | $0.04 |
| 333 | Qwen3.5 2B | 45.6 | 45.6 | — | — | — | — | — | — | — | 328 | $0.00 |
| 334 | Devstral Small | 45.3 | 43.4 | 25.8 | 48.9 | — | — | 63.2 | — | — | 190 | $0.10 |
| 335 | Phi 4 Mini | 45.3 | 47.8 | — | — | — | — | 42.8 | — | — | — | — |
| 336 | Llama 3.1 8B Instruct | 45 | 45 | 11.6 | 28.1 | 76.1 | — | 64.4 | — | 131K | 2047 | $0.02 |
| 337 | Gemma 3 27B Instruct | 44.5 | 42.8 | 13.7 | 54.5 | — | — | 66.9 | — | — | — | $0.10 |
| 338 | Mistral Small 3 24B Base | 44.4 | 34.4 | — | — | — | — | 54.4 | — | — | — | — |
| 339 | Qwen3 VL 4B | 44.3 | 49.4 | 32 | 25.7 | — | — | 70 | — | — | — | $0.00 |
| 340 | DeepHermes 3 - Mistral 24B | 43.8 | 38.2 | 19.5 | 59.5 | — | — | 58 | — | — | — | $0.00 |
| 341 | Llama 3.1 Nemotron 70B Instruct | 43.7 | 46.5 | 16.9 | 42.2 | — | — | 69 | — | — | 292 | $1.20 |
| 342 | Mistral Small 3 | 43.6 | 46.2 | 25.2 | 37.9 | — | — | 65.2 | — | 33K | 136 | $0.05 |
| 343 | Kimi Linear 48B A3B Instruct | 43.5 | 41.2 | 37.8 | 36.3 | — | — | 58.5 | — | — | — | $0.00 |
| 344 | Gemma 4 E2B | 43.3 | 43.3 | — | — | — | — | — | — | — | — | $0.00 |
| 345 | Ministral 3 8B | 43.3 | 47.1 | 30.3 | 31.7 | — | — | 64.2 | — | 262K | 86 | $0.15 |
| 346 | Granite 4.1 8B | 43.3 | 43.3 | — | — | — | — | — | — | 131K | 133 | $0.05 |
| 347 | Qwen3 VL 8B Instruct | 43 | 42.7 | 33.2 | 27.3 | — | — | 68.6 | — | 256K | 145 | $0.08 |
| 348 | Jamba 1.5 Large | 42.8 | 36.9 | 14.3 | 60.6 | — | — | 59.5 | — | 256K | 100 | $2.00 |
| 349 | Jamba 1.6 Large | 42.6 | 38.7 | 17.2 | 58 | — | — | 56.5 | — | — | 52 | $2.00 |
| 350 | Hermes 3 - Llama-3.1 70B | 42.5 | 40.1 | 18.8 | 53.8 | — | — | 57.1 | — | — | 32 | $0.30 |
| 351 | Molmo2-8B | 42.5 | 42.5 | — | — | — | — | — | — | — | — | $0.00 |
| 352 | Mistral Small 3.1 | 42.4 | 45.4 | 21.2 | 37.2 | — | — | 65.9 | — | — | 134 | $0.10 |
| 353 | GPT-4.1 Nano | 42.1 | 50.3 | 16.2 | 46.1 | 18.3 | 55.8 | 65.8 | — | 1M | 200 | $0.10 |
| 354 | Qwen3 VL 4B Instruct | 41.6 | 37.1 | 29 | 37 | — | — | 63.4 | — | — | — | $0.00 |
| 355 | Llama 3 70B Instruct | 40.8 | 37.9 | 19.8 | 48.3 | — | — | 57.4 | — | 8K | 45 | $0.51 |
| 356 | Mistral Small | 40.3 | 38.1 | 14.1 | 56.3 | — | — | 52.9 | — | — | 134 | $0.20 |
| 357 | Gemma 3 12B Instruct | 40 | 34.9 | 13.7 | 51.8 | — | — | 59.5 | — | — | — | $0.10 |
| 358 | Olmo 3 7B Instruct | 40 | 40 | 26.6 | 41.3 | — | — | 52.2 | — | — | — | $0.10 |
| 359 | Qwen2.5-Coder 7B Instruct | 39.6 | 33.9 | 18.2 | 66 | — | — | 40.1 | — | — | — | $0.00 |
| 360 | Mistral Large | 39.3 | 35.1 | 17.8 | 52.7 | — | — | 51.5 | — | 128K | — | $2.00 |
| 361 | Mixtral 8x22B Instruct | 39.1 | 33.2 | 14.8 | 54.5 | — | — | 53.7 | — | 66K | — | $2.00 |
| 362 | Claude 3 Haiku | 38.9 | 61.8 | 15.4 | 39.4 | — | — | — | — | 200K | 104 | $0.25 |
| 363 | Qwen2 7B Instruct | 37.4 | 25.3 | 42.9 | — | — | — | 44.1 | — | — | — | — |
| 364 | Llama 3.2 11B Instruct | 36.7 | 32.8 | 11 | 26.7 | — | 66.4 | 46.4 | — | 128K | 168 | $0.05 |
| 365 | Jamba Large 1.7 | 36.5 | 39 | 18.1 | 31.2 | — | — | 57.7 | — | 256K | 48 | $2.00 |
| 366 | Granite 4.0 H Small | 35.7 | 41.6 | 25.1 | 13.7 | — | — | 62.4 | — | — | 524 | $0.10 |
| 367 | GPT-3.5 Turbo | 35.2 | 50.5 | — | 44.1 | — | 0 | 46.2 | — | 16K | 100 | $0.50 |
| 368 | Gemma 3n E4B Instruct | 34.7 | 29.6 | 14.6 | 45.7 | — | — | 48.8 | — | — | 56 | $0.00 |
| 369 | Claude 2.1 | 34.6 | 31.9 | 19.5 | 37.4 | — | — | 49.5 | — | — | — | $0.00 |
| 370 | Gemini 1.0 Pro | 34 | 27.9 | 11.6 | 40.3 | — | 47.3 | 43.1 | — | 33K | 120 | $0.50 |
| 371 | LFM2.5-1.2B-Thinking | 33.9 | 33.9 | — | — | — | — | — | — | — | — | $0.00 |
| 372 | Ministral 3 3B | 33.7 | 35.8 | 24.7 | 22 | — | — | 52.4 | — | 131K | 154 | $0.10 |
| 373 | Mistral Medium | 33.6 | 34.9 | 9.9 | 40.5 | — | — | 49.1 | — | — | 45 | $2.80 |
| 374 | Claude 2 | 33.4 | 34.4 | 17.1 | — | — | — | 48.6 | — | 100K | — | $0.00 |
| 375 | LFM 40B | 33.2 | 32.7 | 9.6 | 48 | — | — | 42.5 | — | — | — | $0.00 |
| 376 | Solar Mini | 33.1 | — | — | 33.1 | — | — | — | — | — | 63 | $0.20 |
| 377 | LFM2.5-1.2B-Instruct | 32.6 | 32.6 | — | — | — | — | — | — | — | — | $0.00 |
| 378 | DeepSeek R1 Distill Qwen 1.5B | 32.6 | 33.8 | 16.9 | 52.9 | — | — | 26.9 | — | — | — | $0.00 |
| 379 | Phi 4 Mini Instruct | 32.6 | 33.1 | 12.6 | 38.2 | — | — | 46.5 | — | 131K | — | $0.08 |
| 380 | Granite 3.3 8B | 32.5 | 33.8 | 12.7 | 36.6 | — | — | 46.8 | — | — | 376 | $0.00 |
| 381 | Llama 3 8B Instruct | 32.4 | 29.6 | 9.6 | 49.9 | — | — | 40.5 | — | 8K | 81 | $0.04 |
| 382 | Gemma 3 4B Instruct | 31.7 | 29.1 | 11.2 | 44.7 | — | — | 41.7 | — | — | — | $0.00 |
| 383 | Granite 4.1 3B | 31.4 | 31.4 | — | — | — | — | — | — | — | — | $0.00 |
| 384 | LFM2 8B A1B | 31.3 | 34.4 | 15.1 | 25.3 | — | — | 50.5 | — | — | — | $0.00 |
| 385 | Llama 3.2 3B Instruct | 30.8 | 32.8 | 8.3 | 26.1 | — | — | 56.1 | — | 131K | 172 | $0.05 |
| 386 | Jamba Reasoning 3B | 30.7 | 33.3 | 21 | 10.7 | — | — | 57.7 | — | — | — | $0.00 |
| 387 | Tiny Aya Global | 30.5 | 30.5 | — | — | — | — | — | — | — | 126 | $0.00 |
| 388 | MiniCPM-V 4.6 1.3B | 30.5 | 30.5 | — | — | — | — | — | — | — | — | $0.00 |
| 389 | Gemma 3n E4B Instructed LiteRT Preview | 30.3 | 45.8 | 13.2 | 11.6 | — | — | 50.6 | — | — | — | — |
| 390 | DeepSeek Coder V2 Lite Instruct | 30.2 | 31.9 | 15.8 | — | — | — | 42.9 | — | — | — | $0.00 |
| 391 | Gemini Diffusion | 30.2 | 40.4 | 26.9 | 23.3 | — | — | — | — | — | — | — |
| 392 | Jamba 1.5 Mini | 29.6 | 32.3 | 6.2 | 35.7 | — | — | 44.3 | — | 256K | 100 | $0.20 |
| 393 | Qwen3 0.6B | 29.3 | 23.9 | 12.1 | 46.5 | — | — | 34.7 | — | — | 225 | $0.10 |
| 394 | Qwen1.5 Chat 110B | 28.9 | 28.9 | — | — | — | — | — | — | — | — | $0.00 |
| 395 | Llama 2 Chat 13B | 28.9 | 32.1 | 9.8 | 32.9 | — | — | 40.6 | — | — | — | $0.00 |
| 396 | Llama 2 Chat 70B | 28.9 | 32.7 | 9.8 | 32.3 | — | — | 40.6 | — | — | — | $0.00 |
| 397 | LFM2.5-VL-1.6B | 28.9 | 28.9 | — | — | — | — | — | — | — | — | $0.00 |
| 398 | Command R+ | 28.9 | 32.3 | 12.2 | 27.9 | — | — | 43.2 | — | 128K | 100 | $0.15 |
| 399 | Claude Instant | 28.4 | 33 | 10.9 | 26.4 | — | — | 43.4 | — | — | — | $0.00 |
| 400 | DBRX Instruct | 27.5 | 33.1 | 9.3 | 27.9 | — | — | 39.7 | — | — | — | $0.00 |
| 401 | Phi-3 Mini Instruct 3.8B | 27.5 | 31.9 | 11.6 | 23 | — | — | 43.5 | — | — | — | $0.00 |
| 402 | Gemma 3n E2B Instruct | 27.5 | 22.9 | 9.5 | 39.7 | — | — | 37.8 | — | — | — | $0.00 |
| 403 | Apertus 70B Instruct | 27.2 | 27.2 | — | — | — | — | — | — | — | — | $0.80 |
| 404 | MiniCPM5-1B | 26.9 | 26.9 | — | — | — | — | — | — | — | — | $0.00 |
| 405 | Mixtral 8x7B Instruct | 26.1 | 29.2 | 6.6 | 29.9 | — | — | 38.7 | — | — | — | $0.50 |
| 406 | Apertus 8B Instruct | 25.6 | 25.6 | — | — | — | — | — | — | — | — | $0.10 |
| 407 | Granite 4.0 Micro | 25.6 | 33.6 | 18 | 6 | — | — | 44.7 | — | 131K | — | $0.02 |
| 408 | Gemma 3n E2B Instructed LiteRT (Preview) | 25.4 | 41 | 13.2 | 6.7 | — | — | 40.5 | — | — | — | — |
| 409 | Jamba 1.6 Mini | 24.9 | 30 | 7.1 | 25.7 | — | — | 36.7 | — | — | 183 | $0.20 |
| 410 | Gemma 3n E4B Instructed | 24.8 | 23.7 | 13.2 | 11.6 | — | — | 50.6 | — | 32K | 42 | $20.00 |
| 411 | OpenChat 3.5 | 24.1 | 23 | 11.5 | 30.7 | — | — | 31 | — | — | — | $0.00 |
| 412 | Qwen3.5 0.8B | 23.6 | 23.6 | — | — | — | — | — | — | — | 120 | $0.00 |
| 413 | OLMo 2 32B | 23.5 | 32.8 | 6.8 | 3.3 | — | — | 51.1 | — | — | — | $0.00 |
| 414 | DeepHermes 3 - Llama-3.1 8B | 23.5 | 27 | 8.5 | 21.8 | — | — | 36.5 | — | — | — | $0.00 |
| 415 | Jamba 1.7 Mini | 22.5 | 32.2 | 6.1 | 13.1 | — | — | 38.8 | — | — | — | $0.00 |
| 416 | Gemma 3n E2B Instructed | 21.3 | 24.8 | 13.2 | 6.7 | — | — | 40.5 | — | — | — | — |
| 417 | Gemma 3 1B | 21.2 | 29.2 | 1.9 | — | — | — | 32.4 | — | — | — | — |
| 418 | LFM2 2.6B | 19.2 | 30.6 | 8.1 | 8.3 | — | — | 29.8 | — | — | — | $0.00 |
| 419 | Granite 4.0 H 1B | 18 | 26.3 | 11.5 | 6.3 | — | — | 27.7 | — | — | — | $0.00 |
| 420 | Granite 4.0 1B | 17.9 | 28.1 | 4.7 | 6.3 | — | — | 32.5 | — | — | — | $0.00 |
| 421 | Molmo 7B-D | 16.3 | 24 | 3.9 | 0 | — | — | 37.1 | — | — | — | $0.00 |
| 422 | Gemma 3 1B Instruct | 16.2 | 23.7 | 1.7 | 25.9 | — | — | 13.5 | — | — | — | $0.00 |
| 423 | OLMo 2 7B | 15.5 | 28.8 | 4.1 | 0.7 | — | — | 28.2 | — | — | — | $0.00 |
| 424 | Mistral 7B Instruct | 14.7 | 17.7 | 4.6 | 12.1 | — | — | 24.5 | — | — | 90 | $0.20 |
| 425 | LFM2 1.2B | 13.5 | 22.8 | 2 | 3.3 | — | — | 25.7 | — | — | — | $0.00 |
| 426 | Llama 3.2 1B Instruct | 12.1 | 19.6 | 1.9 | 7 | — | — | 20 | — | 131K | 91 | $0.03 |
| 427 | Llama 2 Chat 7B | 11.3 | 22.7 | 0.2 | 5.9 | — | — | 16.4 | — | — | 113 | $0.10 |
| 428 | Granite 4.0 H 350M | 10.4 | 25.7 | 1.9 | 1.3 | — | — | 12.7 | — | — | — | $0.00 |
| 429 | Granite 4.0 350M | 10.2 | 26.1 | 2.4 | 0 | — | — | 12.4 | — | — | — | $0.00 |
| 430 | Gemma 3 270M | 7.6 | 22.4 | 0.3 | 2.3 | — | — | 5.5 | — | — | — | $0.00 |
430 models ranked. The intelligence index is a balanced mean of per-category scores; category columns average the benchmarks within each. Scores are curated approximations — see each model for sources. Click any column to sort.