Daily rank changes, score trends, and performance data for all coding AI models. Scores update hourly from live model data.
| # | Model | Provider | Score | 24h | 7d | State | 14d Trend |
|---|---|---|---|---|---|---|---|
| 1 | GPT-5.4 Pro | OpenAI | 90.9 | 0 | 0 | stable | |
| 2 | GPT-5.2 Pro | OpenAI | 89.9 | 0 | 0 | stable | |
| 3 | GPT-5 Pro | OpenAI | 89.9 | 0 | 0 | stable | |
| 4 | o3 Pro | OpenAI | 81.6 | 0 | 0 | stable | |
| 5 | Claude Opus 4.1 | Anthropic | 81.1 | 0 | 0 | stable | |
| 6 | o1-pro | OpenAI | 77.2 | 0 | 0 | stable | |
| 7 | Claude Opus 4 | Anthropic | 75.5 | 0 | 0 | stable | |
| 8 | o3 Deep Research | OpenAI | 74.0 | 0 | 0 | stable | |
| 9 | Claude Opus 4.6 | Anthropic | 70.5 | 0 | 0 | stable | |
| 10 | Claude Opus 4.5 | Anthropic | 70.0 | 0 | 0 | stable | |
| 11 | GPT-5.4 | OpenAI | 69.7 | 0 | 0 | stable | |
| 12 | Claude Sonnet 4.5 | Anthropic | 69.1 | 0 | 0 | stable | |
| 13 | Qwen3 VL 30B A3B Thinking | Alibaba | 68.6 | 0 | 0 | stable | |
| 14 | Qwen3 VL 235B A22B Thinking | Alibaba | 68.6 | 0 | 0 | stable | |
| 15 | GPT-5.2 | OpenAI | 68.4 | 0 | 0 | stable | |
| 16 | Gemini 3.1 Pro Preview Custom Tools | 68.2 | 0 | 0 | stable | ||
| 17 | Gemini 3.1 Pro Preview | 68.2 | 0 | 0 | stable | ||
| 18 | Gemini 3 Pro Preview | 68.2 | 0 | 0 | stable | ||
| 19 | Claude Sonnet 4.6 | Anthropic | 68.0 | 0 | 0 | stable | |
| 20 | GPT-5.1 | OpenAI | 67.4 | 0 | 0 | stable | |
| 21 | GPT-5.3-Codex | OpenAI | 66.8 | 0 | 0 | stable | |
| 22 | GPT-5.2-Codex | OpenAI | 66.8 | 0 | 0 | stable | |
| 23 | GPT-5 | OpenAI | 66.6 | 0 | 0 | stable | |
| 24 | Gemini 3 Flash Preview | 66.0 | 0 | 0 | stable | ||
| 25 | o4 Mini Deep Research | OpenAI | 66.0 | 0 | 0 | stable | |
| 26 | GPT-5.1-Codex-Max | OpenAI | 65.8 | 0 | 0 | stable | |
| 27 | Gemini 3.1 Flash Lite Preview | 65.6 | 0 | 0 | stable | ||
| 28 | Gemini 2.5 Pro | 65.5 | 0 | 0 | stable | ||
| 29 | Gemini 2.5 Flash Lite Preview 09-2025 | 65.3 | 0 | 0 | stable | ||
| 30 | o1 | OpenAI | 64.7 | 0 | 0 | stable | |
| 31 | GPT-5 Mini | OpenAI | 64.6 | 0 | 0 | stable | |
| 32 | Gemini 2.5 Pro Preview 05-06 | 64.4 | 0 | 0 | stable | ||
| 33 | GPT-5 Nano | OpenAI | 64.2 | 0 | 0 | stable | |
| 34 | Nemotron Nano 12B 2 VL (free) | NVIDIA | 64.1 | 0 | 0 | stable | |
| 35 | Grok 4.1 Fast | xAI | 64.0 | 0 | 0 | stable | |
| 36 | Grok 4 Fast | xAI | 64.0 | 0 | 0 | stable | |
| 37 | Gemini 2.5 Flash Lite | 64.0 | 0 | 0 | stable | ||
| 38 | Gemini 2.5 Flash | 63.6 | 0 | 0 | stable | ||
| 39 | Gemini 2.5 Pro Preview 06-05 | 63.5 | 0 | 0 | stable | ||
| 40 | Claude Haiku 4.5 | Anthropic | 63.3 | 0 | 0 | stable | |
| 41 | GPT-5.3 Chat | OpenAI | 62.2 | 0 | 0 | stable | |
| 42 | Qwen3.5 Plus 2026-02-15 | Alibaba | 62.2 | 0 | 0 | stable | |
| 43 | GPT-5.2 Chat | OpenAI | 62.2 | 0 | 0 | stable | |
| 44 | GPT-5.1-Codex | OpenAI | 62.2 | 0 | 0 | stable | |
| 45 | GPT-5 Codex | OpenAI | 62.2 | 0 | 0 | stable | |
| 46 | o3 | OpenAI | 62.1 | 0 | 0 | stable | |
| 47 | Qwen3.5-Flash | Alibaba | 61.9 | 0 | 0 | stable | |
| 48 | GPT-5.1 Chat | OpenAI | 61.2 | 0 | 0 | stable | |
| 49 | o4 Mini High | OpenAI | 61.2 | 0 | 0 | stable | |
| 50 | o4 Mini | OpenAI | 61.2 | 0 | 0 | stable | |
| 51 | Seed-2.0-Mini | ByteDance | 61.1 | 0 | 0 | stable | |
| 52 | Qwen3.5-122B-A10B | Alibaba | 61.0 | 0 | 0 | stable | |
| 53 | Qwen3.5 397B A17B | Alibaba | 61.0 | 0 | 0 | stable | |
| 54 | Claude Sonnet 4 | Anthropic | 61.0 | 0 | 0 | stable | |
| 55 | Qwen3.5-35B-A3B | Alibaba | 60.8 | 0 | 0 | stable | |
| 56 | Qwen3.5-27B | Alibaba | 60.8 | 0 | 0 | stable | |
| 57 | Sonar Pro Search | Perplexity | 60.7 | 0 | 0 | stable | |
| 58 | Nova 2 Lite | Amazon | 60.6 | 0 | 0 | stable | |
| 59 | Seed 1.6 | ByteDance | 60.4 | 0 | 0 | stable | |
| 60 | Seed 1.6 Flash | ByteDance | 60.0 | 0 | 0 | stable | |
| 61 | GPT-5.1-Codex-Mini | OpenAI | 60.0 | 0 | 0 | stable | |
| 62 | GPT-4.1 | OpenAI | 59.4 | 0 | 0 | stable | |
| 63 | Kimi K2.5 | Moonshot AI | 59.3 | 0 | 0 | stable | |
| 64 | Claude 3.7 Sonnet | Anthropic | 58.6 | 0 | 0 | stable | |
| 65 | Claude 3.7 Sonnet (thinking) | Anthropic | 58.6 | 0 | 0 | stable | |
| 66 | Step 3.5 Flash (free) | StepFun | 58.4 | 0 | 0 | stable | |
| 67 | Grok 4 | xAI | 58.4 | 0 | 0 | stable | |
| 68 | Qwen3 VL 8B Thinking | Alibaba | 57.9 | 0 | 0 | stable | |
| 69 | GPT-4.1 Mini | OpenAI | 57.8 | 0 | 0 | stable | |
| 70 | GPT-4.1 Nano | OpenAI | 57.5 | 0 | 0 | stable | |
| 71 | GPT-5 Chat | OpenAI | 56.8 | 0 | 0 | stable | |
| 72 | Qwen3 235B A22B Thinking 2507 | Alibaba | 56.7 | 0 | 0 | stable | |
| 73 | gpt-oss-120b (free) | OpenAI | 56.4 | 0 | 0 | stable | |
| 74 | gpt-oss-20b (free) | OpenAI | 56.4 | 0 | 0 | stable | |
| 75 | Grok Code Fast 1 | xAI | 55.8 | 0 | 0 | stable | |
| 76 | Nova Premier 1.0 | Amazon | 55.6 | 0 | 0 | stable | |
| 77 | Gemma 3 27B (free) | 55.6 | 0 | 0 | stable | ||
| 78 | Gemini 2.0 Flash Lite | 54.9 | 0 | 0 | stable | ||
| 79 | Qwen Plus 0728 (thinking) | Alibaba | 54.6 | 0 | 0 | stable | |
| 80 | Gemini 2.0 Flash | 54.4 | 0 | 0 | stable | ||
| 81 | MiniMax M2.5 | MiniMax | 54.3 | 0 | 0 | stable | |
| 82 | Trinity Large Preview (free) | arcee-ai | 54.3 | 0 | 0 | stable | |
| 83 | Trinity Mini (free) | arcee-ai | 54.3 | 0 | 0 | stable | |
| 84 | MiniMax M2 | MiniMax | 54.3 | 0 | 0 | stable | |
| 85 | Nemotron Nano 9B V2 (free) | NVIDIA | 54.2 | 0 | 0 | stable | |
| 86 | Qwen3 VL 32B Instruct | Alibaba | 54.1 | 0 | 0 | stable | |
| 87 | Qwen3 VL 8B Instruct | Alibaba | 54.1 | 0 | 0 | stable | |
| 88 | Qwen3 VL 30B A3B Instruct | Alibaba | 54.1 | 0 | 0 | stable | |
| 89 | Qwen3 Max Thinking | Alibaba | 54.0 | 0 | 0 | stable | |
| 90 | MiMo-V2-Flash | Xiaomi | 53.6 | 0 | 0 | stable | |
| 91 | Qwen3 Coder 480B A35B (free) | Alibaba | 53.6 | 0 | 0 | stable | |
| 92 | Trinity Mini | arcee-ai | 53.4 | 0 | 0 | stable | |
| 93 | Tongyi DeepResearch 30B A3B | Alibaba | 53.4 | 0 | 0 | stable | |
| 94 | GPT-4o Audio | OpenAI | 53.4 | 0 | 0 | stable | |
| 95 | DeepSeek V3.2 | DeepSeek | 53.2 | 0 | 0 | stable | |
| 96 | DeepSeek V3.2 Exp | DeepSeek | 53.2 | 0 | 0 | stable | |
| 97 | gpt-oss-safeguard-20b | OpenAI | 52.9 | 0 | 0 | stable | |
| 98 | Mistral Small 3.2 24B | Mistral AI | 52.9 | 0 | 0 | stable | |
| 99 | Mercury 2 | Inception | 52.8 | 0 | 0 | stable | |
| 100 | Qwen3 Coder Plus | Alibaba | 52.2 | 0 | 0 | stable | |
| 101 | Qwen3 Coder Flash | Alibaba | 51.6 | 0 | 0 | stable | |
| 102 | Llama 4 Maverick | Meta | 51.6 | 0 | 0 | stable | |
| 103 | Nemotron 3 Nano 30B A3B (free) | NVIDIA | 51.4 | 0 | 0 | stable | |
| 104 | Qwen3 Next 80B A3B Instruct (free) | Alibaba | 51.4 | 0 | 0 | stable | |
| 105 | Mistral Small 3.1 24B (free) | Mistral AI | 51.2 | 0 | 0 | stable | |
| 106 | Qwen Plus 0728 | Alibaba | 51.1 | 0 | 0 | stable | |
| 107 | Step 3.5 Flash | StepFun | 51.0 | 0 | 0 | stable | |
| 108 | Qwen3 Max | Alibaba | 51.0 | 0 | 0 | stable | |
| 109 | ERNIE 4.5 VL 28B A3B | Baidu | 50.9 | 0 | 0 | stable | |
| 110 | R1 0528 | DeepSeek | 50.8 | 0 | 0 | stable | |
| 111 | Gemma 3 4B (free) | 50.7 | 0 | 0 | stable | ||
| 112 | KAT-Coder-Pro V1 | Kuaishou | 50.6 | 0 | 0 | stable | |
| 113 | GPT Audio | OpenAI | 50.5 | 0 | 0 | stable | |
| 114 | DeepSeek V3.2 Speciale | DeepSeek | 50.5 | 0 | 0 | stable | |
| 115 | Nemotron Nano 12B 2 VL | NVIDIA | 50.3 | 0 | 0 | stable | |
| 116 | Llama 4 Scout | Meta | 50.3 | 0 | 0 | stable | |
| 117 | Claude 3.5 Sonnet | Anthropic | 50.3 | 0 | 0 | stable | |
| 118 | Qwen3 Coder Next | Alibaba | 50.2 | 0 | 0 | stable | |
| 119 | LongCat Flash Chat | Meituan | 50.0 | 0 | 0 | stable | |
| 120 | Qwen3 30B A3B Instruct 2507 | Alibaba | 50.0 | 0 | 0 | stable | |
| 121 | GPT-4o (2024-11-20) | OpenAI | 49.7 | 0 | 0 | stable | |
| 122 | Mistral Large 3 2512 | Mistral AI | 49.6 | 0 | 0 | stable | |
| 123 | Qwen3 4B (free) | Alibaba | 49.6 | 0 | 0 | stable | |
| 124 | Gemma 3 27B | 49.6 | 0 | 0 | stable | ||
| 125 | DeepSeek V3.1 | DeepSeek | 49.5 | 0 | 0 | stable | |
| 126 | Qwen3 VL 235B A22B Instruct | Alibaba | 49.4 | 0 | 0 | stable | |
| 127 | DeepSeek V3 0324 | DeepSeek | 49.4 | 0 | 0 | stable | |
| 128 | MiniMax M1 | MiniMax | 49.3 | 0 | 0 | stable | |
| 129 | Ministral 3 14B 2512 | Mistral AI | 49.2 | 0 | 0 | stable | |
| 130 | Ministral 3 8B 2512 | Mistral AI | 49.2 | 0 | 0 | stable | |
| 131 | Qwen3 Coder 480B A35B (exacto) | Alibaba | 49.2 | 0 | 0 | stable | |
| 132 | Jamba Large 1.7 | AI21 Labs | 49.1 | 0 | 0 | stable | |
| 133 | Qwen VL Max | Alibaba | 48.9 | 0 | 0 | stable | |
| 134 | Olmo 3.1 32B Think | Allen AI | 48.7 | 0 | 0 | stable | |
| 135 | Olmo 3 32B Think | Allen AI | 48.7 | 0 | 0 | stable | |
| 136 | GPT Audio Mini | OpenAI | 48.6 | 0 | 0 | stable | |
| 137 | Olmo 3 7B Think | Allen AI | 48.6 | 0 | 0 | stable | |
| 138 | Sonar Pro | Perplexity | 48.6 | 0 | 0 | stable | |
| 139 | Ministral 3 3B 2512 | Mistral AI | 48.5 | 0 | 0 | stable | |
| 140 | Mistral Medium 3.1 | Mistral AI | 48.3 | 0 | 0 | stable | |
| 141 | Hunyuan A13B Instruct | Tencent | 48.3 | 0 | 0 | stable | |
| 142 | ERNIE 4.5 VL 424B A47B | Baidu | 48.3 | 0 | 0 | stable | |
| 143 | Qwen3 235B A22B | Alibaba | 48.2 | 0 | 0 | stable | |
| 144 | Grok 3 Mini | xAI | 48.1 | 0 | 0 | stable | |
| 145 | Grok 3 | xAI | 48.1 | 0 | 0 | stable | |
| 146 | Qwen3 Coder 30B A3B Instruct | Alibaba | 48.0 | 0 | 0 | stable | |
| 147 | Qwen3 30B A3B | Alibaba | 47.8 | 0 | 0 | stable | |
| 148 | Qwen3 14B | Alibaba | 47.8 | 0 | 0 | stable | |
| 149 | Qwen3 32B | Alibaba | 47.8 | 0 | 0 | stable | |
| 150 | Nemotron 3 Nano 30B A3B | NVIDIA | 47.6 | 0 | 0 | stable | |
| 151 | MiniMax M2.1 | MiniMax | 47.5 | 0 | 0 | stable | |
| 152 | GPT-4o (extended) | OpenAI | 47.5 | 0 | 0 | stable | |
| 153 | Molmo2 8B | Allen AI | 47.3 | 0 | 0 | stable | |
| 154 | Kimi K2 Thinking | Moonshot AI | 47.3 | 0 | 0 | stable | |
| 155 | DeepSeek V3.1 Terminus (exacto) | DeepSeek | 47.2 | 0 | 0 | stable | |
| 156 | DeepSeek V3.1 Terminus | DeepSeek | 47.2 | 0 | 0 | stable | |
| 157 | Qwen3 Next 80B A3B Thinking | Alibaba | 47.1 | 0 | 0 | stable | |
| 158 | Gemma 3 12B (free) | 47.1 | 0 | 0 | stable | ||
| 159 | o3 Mini High | OpenAI | 47.1 | 0 | 0 | stable | |
| 160 | Solar Pro 3 | Upstage | 46.9 | 0 | 0 | stable | |
| 161 | Llama 3.3 Nemotron Super 49B V1.5 | NVIDIA | 46.9 | 0 | 0 | stable | |
| 162 | Mercury | Inception | 46.9 | 0 | 0 | stable | |
| 163 | Nemotron Nano 9B V2 | NVIDIA | 46.8 | 0 | 0 | stable | |
| 164 | o3 Mini | OpenAI | 46.8 | 0 | 0 | stable | |
| 165 | GPT-4o (2024-08-06) | OpenAI | 46.8 | 0 | 0 | stable | |
| 166 | Qwen3 8B | Alibaba | 46.6 | 0 | 0 | stable | |
| 167 | Grok 3 Beta | xAI | 46.5 | 0 | 0 | stable | |
| 168 | Grok 3 Mini Beta | xAI | 46.4 | 0 | 0 | stable | |
| 169 | Qwen3 235B A22B Instruct 2507 | Alibaba | 46.2 | 0 | 0 | stable | |
| 170 | Gemma 3n 2B (free) | 46.2 | 0 | 0 | stable | ||
| 171 | Llama 3.3 70B Instruct (free) | Meta | 46.2 | 0 | 0 | stable | |
| 172 | Claude 3.5 Haiku | Anthropic | 46.1 | 0 | 0 | stable | |
| 173 | gpt-oss-120b | OpenAI | 46.0 | 0 | 0 | stable | |
| 174 | gpt-oss-120b (exacto) | OpenAI | 46.0 | 0 | 0 | stable | |
| 175 | gpt-oss-20b | OpenAI | 46.0 | 0 | 0 | stable | |
| 176 | GPT-4o Search Preview | OpenAI | 45.9 | 0 | 0 | stable | |
| 177 | QwQ 32B | Alibaba | 45.9 | 0 | 0 | stable | |
| 178 | GPT-4 Turbo | OpenAI | 45.9 | 0 | 0 | stable | |
| 179 | ERNIE 4.5 21B A3B Thinking | Baidu | 45.8 | 0 | 0 | stable | |
| 180 | LFM2.5-1.2B-Thinking (free) | Liquid AI | 45.7 | 0 | 0 | stable | |
| 181 | Aion-2.0 | aion-labs | 45.6 | 0 | 0 | stable | |
| 182 | Mistral Medium 3 | Mistral AI | 45.6 | 0 | 0 | stable | |
| 183 | Mercury Coder | Inception | 45.4 | 0 | 0 | stable | |
| 184 | Sonar Reasoning Pro | Perplexity | 45.4 | 0 | 0 | stable | |
| 185 | MiniMax-01 | MiniMax | 45.3 | 0 | 0 | stable | |
| 186 | Qwen3 30B A3B Thinking 2507 | Alibaba | 45.2 | 0 | 0 | stable | |
| 187 | Qwen-Plus | Alibaba | 45.2 | 0 | 0 | stable | |
| 188 | Olmo 3 7B Instruct | Allen AI | 45.0 | 0 | 0 | stable | |
| 189 | Gemma 3n 4B (free) | 44.8 | 0 | 0 | stable | ||
| 190 | GPT-4o (2024-05-13) | OpenAI | 44.7 | 0 | 0 | stable | |
| 191 | Kimi K2 0905 (exacto) | Moonshot AI | 44.5 | 0 | 0 | stable | |
| 192 | GPT-4o | OpenAI | 44.5 | 0 | 0 | stable | |
| 193 | Devstral 2 2512 | Mistral AI | 44.4 | 0 | 0 | stable | |
| 194 | GPT-4 (older v0314) | OpenAI | 44.4 | 0 | 0 | stable | |
| 195 | GPT-4 | OpenAI | 44.4 | 0 | 0 | stable | |
| 196 | Palmyra X5 | Writer | 44.3 | 0 | 0 | stable | |
| 197 | Qwen3 Next 80B A3B Instruct | Alibaba | 44.2 | 0 | 0 | stable | |
| 198 | Spotlight | arcee-ai | 44.0 | 0 | 0 | stable | |
| 199 | GPT-4o-mini (2024-07-18) | OpenAI | 43.9 | 0 | 0 | stable | |
| 200 | GPT-4o-mini | OpenAI | 43.9 | 0 | 0 | stable | |
| 201 | Kimi K2 0905 | Moonshot AI | 43.7 | 0 | 0 | stable | |
| 202 | Qwen VL Plus | Alibaba | 43.7 | 0 | 0 | stable | |
| 203 | UI-TARS 7B | ByteDance | 43.6 | 0 | 0 | stable | |
| 204 | Cogito v2.1 671B | deepcogito | 43.5 | 0 | 0 | stable | |
| 205 | Voxtral Small 24B 2507 | Mistral AI | 43.5 | 0 | 0 | stable | |
| 206 | ERNIE 4.5 21B A3B | Baidu | 43.5 | 0 | 0 | stable | |
| 207 | GPT-4o-mini Search Preview | OpenAI | 43.5 | 0 | 0 | stable | |
| 208 | DeepSeek V3 | DeepSeek | 43.4 | 0 | 0 | stable | |
| 209 | Qwen2.5 VL 72B Instruct | Alibaba | 43.3 | 0 | 0 | stable | |
| 210 | Codestral 2508 | Mistral AI | 43.2 | 0 | 0 | stable | |
| 211 | Nova Pro 1.0 | Amazon | 43.2 | 0 | 0 | stable | |
| 212 | Qwen3 Coder 480B A35B | Alibaba | 42.9 | 0 | 0 | stable | |
| 213 | ERNIE 4.5 300B A47B | Baidu | 42.8 | 0 | 0 | stable | |
| 214 | Olmo 3.1 32B Instruct | Allen AI | 42.7 | 0 | 0 | stable | |
| 215 | Virtuoso Large | arcee-ai | 42.6 | 0 | 0 | stable | |
| 216 | Command A | Cohere | 42.5 | 0 | 0 | stable | |
| 217 | Nova Lite 1.0 | Amazon | 42.5 | 0 | 0 | stable | |
| 218 | R1 Distill Llama 70B | DeepSeek | 42.3 | 0 | 0 | stable | |
| 219 | LFM2.5-1.2B-Instruct (free) | Liquid AI | 42.2 | 0 | 0 | stable | |
| 220 | Kimi K2 0711 | Moonshot AI | 42.2 | 0 | 0 | stable | |
| 221 | Devstral Medium | Mistral AI | 42.1 | 0 | 0 | stable | |
| 222 | Pixtral Large 2411 | Mistral AI | 42.0 | 0 | 0 | stable | |
| 223 | R1 | DeepSeek | 41.9 | 0 | 0 | stable | |
| 224 | Rnj 1 Instruct | essentialai | 41.8 | 0 | 0 | stable | |
| 225 | Qwen-Turbo | Alibaba | 41.8 | 0 | 0 | stable | |
| 226 | Devstral Small 1.1 | Mistral AI | 41.7 | 0 | 0 | stable | |
| 227 | Llama Guard 4 12B | Meta | 41.6 | 0 | 0 | stable | |
| 228 | Qwen-Max | Alibaba | 41.4 | 0 | 0 | stable | |
| 229 | R1 Distill Qwen 32B | DeepSeek | 41.4 | 0 | 0 | stable | |
| 230 | Aion-1.0 | aion-labs | 41.3 | 0 | 0 | stable | |
| 231 | Mistral Small 3 | Mistral AI | 40.9 | 0 | 0 | stable | |
| 232 | Llama 3.3 70B Instruct | Meta | 40.8 | 0 | 0 | stable | |
| 233 | Qwen2.5 VL 32B Instruct | Alibaba | 40.5 | 0 | 0 | stable | |
| 234 | Llama 3.2 11B Vision Instruct | Meta | 40.5 | 0 | 0 | stable | |
| 235 | Sonar Deep Research | Perplexity | 40.2 | 0 | 0 | stable | |
| 236 | Gemma 3 4B | 40.1 | 0 | 0 | stable | ||
| 237 | Gemma 3 12B | 40.1 | 0 | 0 | stable | ||
| 238 | Aion-1.0-Mini | aion-labs | 39.7 | 0 | 0 | stable | |
| 239 | GPT-4 Turbo Preview | OpenAI | 39.7 | 0 | 0 | stable | |
| 240 | GPT-4 Turbo (older v1106) | OpenAI | 39.7 | 0 | 0 | stable | |
| 241 | Llama 3.1 Nemotron 70B Instruct | NVIDIA | 39.6 | 0 | 0 | stable | |
| 242 | Command R+ (08-2024) | Cohere | 39.5 | 0 | 0 | stable | |
| 243 | MiniMax M2-her | MiniMax | 39.2 | 0 | 0 | stable | |
| 244 | Sonar | Perplexity | 39.1 | 0 | 0 | stable | |
| 245 | Maestro Reasoning | arcee-ai | 39.0 | 0 | 0 | stable | |
| 246 | Mistral Small Creative | Mistral AI | 38.3 | 0 | 0 | stable | |
| 247 | Qwen2.5 72B Instruct | Alibaba | 37.3 | 0 | 0 | stable | |
| 248 | Command R (08-2024) | Cohere | 37.2 | 0 | 0 | stable | |
| 249 | Mistral Nemo | Mistral AI | 36.9 | 0 | 0 | stable | |
| 250 | Mistral Large 2411 | Mistral AI | 36.8 | 0 | 0 | stable | |
| 251 | Mistral Large 2407 | Mistral AI | 36.8 | 0 | 0 | stable | |
| 252 | Mistral Small 3.1 24B | Mistral AI | 36.7 | 0 | 0 | stable | |
| 253 | Saba | Mistral AI | 36.5 | 0 | 0 | stable | |
| 254 | Command R7B (12-2024) | Cohere | 36.4 | 0 | 0 | stable | |
| 255 | Nova Micro 1.0 | Amazon | 36.3 | 0 | 0 | stable | |
| 256 | Granite 4.0 Micro | IBM | 36.1 | 0 | 0 | stable | |
| 257 | Phi 4 | Microsoft | 36.0 | 0 | 0 | stable | |
| 258 | Llama 3.1 8B Instruct | Meta | 34.9 | 0 | 0 | stable | |
| 259 | Claude 3 Haiku | Anthropic | 34.9 | 0 | 0 | stable | |
| 260 | LFM2-24B-A2B | Liquid AI | 34.7 | 0 | 0 | stable | |
| 261 | LFM2-8B-A1B | Liquid AI | 34.7 | 0 | 0 | stable | |
| 262 | LFM2-2.6B | Liquid AI | 34.7 | 0 | 0 | stable | |
| 263 | Qwen2.5 Coder 7B Instruct | Alibaba | 34.3 | 0 | 0 | stable | |
| 264 | Llama 3.2 3B Instruct (free) | Meta | 34.1 | 0 | 0 | stable | |
| 265 | Llama 3.1 405B Instruct | Meta | 33.0 | 0 | 0 | stable | |
| 266 | Llemma 7b | eleutherai | 32.9 | 0 | 0 | stable | |
| 267 | Qwen2.5 7B Instruct | Alibaba | 32.9 | 0 | 0 | stable | |
| 268 | Llama 3.1 70B Instruct | Meta | 32.1 | 0 | 0 | stable | |
| 269 | Mixtral 8x7B Instruct | Mistral AI | 32.0 | 0 | 0 | stable | |
| 270 | Gemma 3n 4B | 31.7 | 0 | 0 | stable | ||
| 271 | Llama 3 8B Instruct | Meta | 31.6 | 0 | 0 | stable | |
| 272 | Coder Large | arcee-ai | 31.5 | 0 | 0 | stable | |
| 273 | Olmo 2 32B Instruct | Allen AI | 31.3 | 0 | 0 | stable | |
| 274 | Qwen2.5 Coder 32B Instruct | Alibaba | 31.1 | 0 | 0 | stable | |
| 275 | GPT-3.5 Turbo 16k | OpenAI | 31.1 | 0 | 0 | stable | |
| 276 | Llama Guard 3 8B | Meta | 30.5 | 0 | 0 | stable | |
| 277 | GPT-3.5 Turbo | OpenAI | 30.5 | 0 | 0 | stable | |
| 278 | Llama 3.1 405B (base) | Meta | 30.2 | 0 | 0 | stable | |
| 279 | Mixtral 8x22B Instruct | Mistral AI | 30.2 | 0 | 0 | stable | |
| 280 | Inflection 3 Pi | Inflection | 29.7 | 0 | 0 | stable | |
| 281 | Inflection 3 Productivity | Inflection | 29.7 | 0 | 0 | stable | |
| 282 | Qwen2.5-VL 7B Instruct | Alibaba | 29.7 | 0 | 0 | stable | |
| 283 | Mistral Large | Mistral AI | 29.7 | 0 | 0 | stable | |
| 284 | GPT-3.5 Turbo (older v0613) | OpenAI | 29.2 | 0 | 0 | stable | |
| 285 | Gemma 2 27B | 29.0 | 0 | 0 | stable | ||
| 286 | Llama 3 70B Instruct | Meta | 27.7 | 0 | 0 | stable | |
| 287 | Llama 3.2 3B Instruct | Meta | 26.2 | 0 | 0 | stable | |
| 288 | WizardLM-2 8x22B | Microsoft | 26.1 | 0 | 0 | stable | |
| 289 | Llama 3.2 1B Instruct | Meta | 25.9 | 0 | 0 | stable | |
| 290 | GPT-3.5 Turbo Instruct | OpenAI | 25.6 | 0 | 0 | stable | |
| 291 | Gemma 2 9B | 21.3 | 0 | 0 | stable | ||
| 292 | LlamaGuard 2 8B | Meta | 20.1 | 0 | 0 | stable | |
| 293 | Mistral 7B Instruct v0.1 | Mistral AI | 17.2 | 0 | 0 | stable |