Coding AI Performance Tracker
Daily rank changes, score trends, and performance data for all coding AI models. Scores update hourly from live model data.
Total Models
300
Gainers (24h)
10
Losers (24h)
165
Unchanged
125
Avg Score by Provider (Top 12)
LMMarketCap.com
Score Distribution
LMMarketCap.com
Top Movers (24h)
Top Gainers
Claude Opus 5.5Anthropic · #5
+428GPT-6 Luna ProOpenAI · #235
+198GPT-6 Luna Pro (batch)OpenAI · #236
+197GPT-6 LunaOpenAI · #237
+196GPT-6 Luna (batch)OpenAI · #238
+195 Top Losers
Ling 3.0 Flash Sante (free)inclusionai · #263
-13Muse Spark 1.3 Contributormeta · #264
-13Hy4 previewTencent · #265
-13Ling 3.0 Flash Fininclusionai · #266
-13Ling 3.0 Flash Fin (free)inclusionai · #267
-13Daily Performance
| # | Model | Provider | Score | 24h | 7d | State | 14d Trend |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | Anthropic | 95.9 | 0 | 0 | stable | |
| 2 | Claude Fable 5.1 (batch) | Anthropic | 95.9 | 0 | 0 | stable | |
| 3 | Claude Fable 5 | Anthropic | 95.9 | 0 | 0 | stable | |
| 4 | Claude Fable 5 (batch) | Anthropic | 95.9 | 0 | 0 | stable | |
| 5 | Claude Opus 5.5 | Anthropic | 95.1 | +428 | +428 | preliminary | |
| 6 | Claude Opus 5 | Anthropic | 95.1 | -1 | +272 | fragile | |
| 7 | Claude Opus 4.8 | Anthropic | 95.1 | -1 | 0 | stable | |
| 8 | Claude Opus 4.7 | Anthropic | 95.1 | -1 | -3 | stable | |
| 9 | Claude Opus 4.7 (batch) | Anthropic | 95.1 | -1 | -3 | stable | |
| 10 | Claude Opus 4.8 (batch) | Anthropic | 94.6 | -1 | -2 | stable | |
| 11 | GPT-5.5 Pro | OpenAI | 92.7 | -1 | +8 | fragile | |
| 12 | GPT-5.5 Pro (batch) | OpenAI | 92.7 | -1 | -3 | stable | |
| 13 | GPT-5.5 | OpenAI | 92.7 | -1 | -3 | stable | |
| 14 | GPT-5.5 (batch) | OpenAI | 92.7 | -1 | -3 | stable | |
| 15 | Gemini 3.1 Pro Preview Custom Tools | 92.2 | -1 | -3 | stable | ||
| 16 | Gemini 3.1 Pro Preview | 92.2 | -1 | -3 | stable | ||
| 17 | Gemini 3.1 Pro Preview (batch) | 92.2 | -1 | -3 | stable | ||
| 18 | GPT-5.4 Pro | OpenAI | 91.9 | -1 | -3 | stable | |
| 19 | GPT-5.4 Pro (batch) | OpenAI | 91.9 | -1 | -3 | stable | |
| 20 | GPT-5.4 | OpenAI | 91.9 | -1 | -3 | stable | |
| 21 | GPT-5.4 (batch) | OpenAI | 91.9 | -1 | -3 | stable | |
| 22 | GPT-5.3-Codex | OpenAI | 90.5 | -1 | +18 | fragile | |
| 23 | GPT-5.2-Codex | OpenAI | 90.5 | -1 | -3 | stable | |
| 24 | GPT-5.2 Chat | OpenAI | 90.5 | -1 | +80 | fragile | |
| 25 | GPT-5.2 Pro | OpenAI | 90.5 | -1 | -4 | stable | |
| 26 | GPT-5.2 Pro (batch) | OpenAI | 90.5 | -1 | -4 | stable | |
| 27 | GPT-5.2 | OpenAI | 90.5 | -1 | -4 | stable | |
| 28 | GPT-5.2 (batch) | OpenAI | 90.5 | -1 | -4 | stable | |
| 29 | Claude Opus 4.6 | Anthropic | 90.4 | -1 | -4 | stable | |
| 30 | Claude Opus 4.6 (batch) | Anthropic | 90.4 | -1 | -4 | stable | |
| 31 | GPT-5.6 Luna Pro | OpenAI | 89.0 | -1 | -4 | stable | |
| 32 | GPT-5.6 Luna Pro (batch) | OpenAI | 89.0 | -1 | -4 | stable | |
| 33 | GPT-5.6 Luna | OpenAI | 89.0 | -1 | -4 | stable | |
| 34 | GPT-5.6 Luna (batch) | OpenAI | 89.0 | -1 | -4 | stable | |
| 35 | GPT-5.6 Terra Pro | OpenAI | 89.0 | -1 | -4 | stable | |
| 36 | GPT-5.6 Terra Pro (batch) | OpenAI | 89.0 | -1 | -4 | stable | |
| 37 | GPT-5.6 Terra | OpenAI | 89.0 | -1 | -4 | stable | |
| 38 | GPT-5.6 Terra (batch) | OpenAI | 89.0 | -1 | -4 | stable | |
| 39 | GPT-5.6 Sol Pro | OpenAI | 89.0 | -1 | -4 | stable | |
| 40 | GPT-5.6 Sol Pro (batch) | OpenAI | 89.0 | -1 | -4 | stable | |
| 41 | GPT-5.6 Sol | OpenAI | 89.0 | -1 | -4 | stable | |
| 42 | GPT-5.6 Sol (batch) | OpenAI | 89.0 | -1 | -4 | stable | |
| 43 | Grok 4.7 | xAI | 88.8 | -1 | +390 | preliminary | |
| 44 | Grok 4.6 | xAI | 88.8 | -1 | +3 | stable | |
| 45 | Grok 4.5 | xAI | 88.8 | -1 | +56 | fragile | |
| 46 | Grok 4.3 | xAI | 88.8 | -1 | +30 | fragile | |
| 47 | Grok 4.20 | xAI | 88.8 | -1 | -8 | fragile | |
| 48 | GPT-5.1-Codex-Max | OpenAI | 88.7 | -1 | +1 | stable | |
| 49 | GPT-5.1 | OpenAI | 88.7 | -1 | +1 | stable | |
| 50 | GPT-5.1-Codex | OpenAI | 88.7 | -1 | +2 | stable | |
| 51 | GPT-5 Pro | OpenAI | 88.7 | -1 | -10 | fragile | |
| 52 | GPT-5 Pro (batch) | OpenAI | 88.7 | -1 | -10 | fragile | |
| 53 | GPT-5 | OpenAI | 88.7 | -1 | -10 | fragile | |
| 54 | GPT-5 (batch) | OpenAI | 88.7 | -1 | -10 | fragile | |
| 55 | Gemini 3 Flash Preview | 88.4 | -1 | -10 | fragile | ||
| 56 | Gemini 3 Flash Preview (batch) | 88.4 | -1 | -10 | fragile | ||
| 57 | Grok 4.20 Multi-Agent | xAI | 87.9 | -1 | -9 | fragile | |
| 58 | GPT-5.1 (batch) | OpenAI | 87.8 | -1 | -7 | fragile | |
| 59 | GPT-5.1-Codex-Mini | OpenAI | 87.8 | -1 | -6 | fragile | |
| 60 | o3 Pro | OpenAI | 86.7 | -1 | -6 | fragile | |
| 61 | o3 | OpenAI | 86.7 | -1 | -6 | fragile | |
| 62 | o3 (batch) | OpenAI | 86.7 | -1 | -6 | fragile | |
| 63 | Claude Sonnet 5 | Anthropic | 85.2 | -1 | +231 | fragile | |
| 64 | Claude Sonnet 4.6 | Anthropic | 85.2 | -1 | -7 | fragile | |
| 65 | Claude Sonnet 4.6 (batch) | Anthropic | 85.2 | -1 | -7 | fragile | |
| 66 | Claude Opus 4.5 | Anthropic | 85.1 | -1 | -7 | fragile | |
| 67 | Claude Opus 4.5 (batch) | Anthropic | 85.1 | -1 | -7 | fragile | |
| 68 | Gemini 2.5 Pro | 83.5 | -1 | -7 | fragile | ||
| 69 | Gemini 2.5 Pro (batch) | 83.5 | -1 | -7 | fragile | ||
| 70 | Gemini 2.5 Pro Preview 06-05 | 83.5 | -1 | -7 | fragile | ||
| 71 | DeepSeek V3.2 | DeepSeek | 83.4 | -1 | -7 | fragile | |
| 72 | Claude Sonnet 4.5 | Anthropic | 82.4 | -1 | -7 | fragile | |
| 73 | Claude Sonnet 4.5 (batch) | Anthropic | 82.4 | -1 | -7 | fragile | |
| 74 | GPT-6 Astra | OpenAI | 81.8 | -1 | -6 | fragile | |
| 75 | GPT-6 Astra (batch) | OpenAI | 81.8 | -1 | -6 | fragile | |
| 76 | GPT-6 Astra Pro | OpenAI | 81.8 | -1 | -6 | fragile | |
| 77 | GPT-6 Astra Pro (batch) | OpenAI | 81.8 | -1 | -6 | fragile | |
| 78 | o4 Mini | OpenAI | 81.4 | -1 | -6 | fragile | |
| 79 | o4 Mini (batch) | OpenAI | 81.4 | -1 | -6 | fragile | |
| 80 | Gemini 3.8 Flash | 81.0 | -1 | -6 | fragile | ||
| 81 | Gemini 3.8 Flash (batch) | 81.0 | -1 | -6 | fragile | ||
| 82 | Grok 4.3 (batch) | xAI | 81.0 | -1 | -5 | stable | |
| 83 | Muse Spark 1.3 | meta | 80.9 | -1 | +161 | fragile | |
| 84 | Muse Spark 1.2 | meta | 80.9 | -1 | +189 | fragile | |
| 85 | Muse Spark 1.1 | meta | 80.9 | -1 | -7 | fragile | |
| 86 | Gemma 4 31B | 80.5 | -1 | -7 | fragile | ||
| 87 | Gemma 4 31B (free) | 80.5 | -1 | -7 | fragile | ||
| 88 | Qwen3.5 397B A17B | Alibaba | 79.4 | -1 | -7 | fragile | |
| 89 | R1 0528 | DeepSeek | 79.4 | -1 | -7 | fragile | |
| 90 | GPT-5.4 Nano | OpenAI | 79.3 | -1 | -7 | fragile | |
| 91 | GPT-5.4 Nano (batch) | OpenAI | 79.3 | -1 | -7 | fragile | |
| 92 | GPT-5.4 Mini | OpenAI | 79.3 | -1 | -7 | fragile | |
| 93 | GPT-5.4 Mini (batch) | OpenAI | 79.3 | -1 | -7 | fragile | |
| 94 | Gemini 3.1 Flash Lite Preview | 79.3 | -1 | -7 | fragile | ||
| 95 | Gemini 2.5 Flash Lite | 79.1 | -1 | -7 | fragile | ||
| 96 | Gemini 2.5 Flash Lite (batch) | 79.1 | -1 | -7 | fragile | ||
| 97 | Gemini 2.5 Flash | 79.1 | -1 | -7 | fragile | ||
| 98 | Gemini 2.5 Flash (batch) | 79.1 | -1 | -7 | fragile | ||
| 99 | Gemini 3.5 Flash | 79.0 | -1 | -7 | fragile | ||
| 100 | Gemini 3.5 Flash (batch) | 79.0 | -1 | -7 | fragile | ||
| 101 | GLM 5.3 | Zhipu AI | 78.6 | -1 | +4 | stable | |
| 102 | GLM 5.3 (batch) | Zhipu AI | 78.6 | -1 | -8 | fragile | |
| 103 | GLM 5.2 | Zhipu AI | 78.6 | -1 | -8 | fragile | |
| 104 | GLM 5.3 Flash | Zhipu AI | 78.0 | 0 | -7 | fragile | |
| 105 | GLM 5.1 | Zhipu AI | 78.0 | 0 | +11 | fragile | |
| 106 | GLM 5 Turbo | Zhipu AI | 78.0 | 0 | +43 | fragile | |
| 107 | GLM 5 | Zhipu AI | 78.0 | 0 | -9 | fragile | |
| 108 | GLM 5.3 FlashX | Zhipu AI | 77.9 | 0 | -9 | fragile | |
| 109 | GLM 5.3 Flash (batch) | Zhipu AI | 77.9 | 0 | -9 | fragile | |
| 110 | Qwen3.5-122B-A10B | Alibaba | 77.7 | 0 | -8 | fragile | |
| 111 | Gemma 2 27B | 77.4 | 0 | -8 | fragile | ||
| 112 | Qwen3.5-27B | Alibaba | 77.0 | 0 | -6 | fragile | |
| 113 | GPT-5 Mini (batch) | OpenAI | 76.8 | 0 | -6 | fragile | |
| 114 | GPT-5 Nano (batch) | OpenAI | 76.8 | 0 | -6 | fragile | |
| 115 | Gemini 3.5 Flash Lite | 76.5 | 0 | -6 | fragile | ||
| 116 | Gemini 3.5 Flash Lite (batch) | 76.5 | 0 | -6 | fragile | ||
| 117 | MiMo-V2.6-Pro | Xiaomi | 76.2 | 0 | +316 | preliminary | |
| 118 | MiMo-V2.5-Pro | Xiaomi | 76.2 | 0 | -7 | fragile | |
| 119 | Qwen3.5-35B-A3B | Alibaba | 76.0 | 0 | -7 | fragile | |
| 120 | GLM 5.2 (free) | Zhipu AI | 75.7 | 0 | -7 | fragile | |
| 121 | Kimi K2.6 | Moonshot AI | 75.7 | 0 | -7 | fragile | |
| 122 | Qwen3.8 Max (0902) | Alibaba | 75.6 | 0 | +120 | fragile | |
| 123 | Qwen3.7 Plus | Alibaba | 75.6 | 0 | -8 | fragile | |
| 124 | o3 Mini | OpenAI | 75.3 | 0 | -7 | fragile | |
| 125 | Claude Opus 4.1 (batch) | Anthropic | 75.2 | 0 | -7 | fragile | |
| 126 | GLM 4.7 | Zhipu AI | 75.1 | 0 | +13 | fragile | |
| 127 | GLM 4.6 | Zhipu AI | 75.1 | 0 | +27 | fragile | |
| 128 | GLM 4.5 | Zhipu AI | 75.1 | 0 | -9 | fragile | |
| 129 | Qwen3.7 Max | Alibaba | 74.8 | 0 | +176 | fragile | |
| 130 | Qwen3.5 Plus 2026-04-20 | Alibaba | 74.8 | 0 | +187 | fragile | |
| 131 | Qwen3.6 Max Preview | Alibaba | 74.8 | 0 | -11 | fragile | |
| 132 | Hy3 | Tencent | 74.4 | 0 | -11 | fragile | |
| 133 | Claude Opus 4.1 | Anthropic | 74.4 | 0 | -11 | fragile | |
| 134 | o1 | OpenAI | 74.4 | 0 | -10 | fragile | |
| 135 | o3 Mini (batch) | OpenAI | 74.3 | 0 | -10 | fragile | |
| 136 | Qwen3.6 Plus | Alibaba | 74.1 | 0 | -10 | fragile | |
| 137 | MiniMax M3 | MiniMax | 73.9 | 0 | -10 | fragile | |
| 138 | Claude Sonnet 4 | Anthropic | 73.9 | 0 | -15 | fragile | |
| 139 | R1 | DeepSeek | 73.8 | 0 | -11 | fragile | |
| 140 | o1-pro | OpenAI | 73.6 | 0 | -10 | fragile | |
| 141 | Qwen3.8 27B | Alibaba | 73.4 | 0 | -10 | fragile | |
| 142 | MiMo-V2.5 | Xiaomi | 73.0 | 0 | -10 | fragile | |
| 143 | Gemma 4 26B A4B | 73.0 | 0 | -10 | fragile | ||
| 144 | Gemma 4 26B A4B (free) | 73.0 | 0 | -10 | fragile | ||
| 145 | Qwen3.8 27B (free) | Alibaba | 72.9 | 0 | -10 | fragile | |
| 146 | Inkling | thinkingmachines | 72.9 | 0 | -10 | fragile | |
| 147 | Inkling (free) | thinkingmachines | 72.9 | 0 | -10 | fragile | |
| 148 | GLM 5V Turbo | Zhipu AI | 72.3 | 0 | -8 | fragile | |
| 149 | o4 Mini High | OpenAI | 72.1 | 0 | -8 | fragile | |
| 150 | GPT-4o (batch) | OpenAI | 72.0 | 0 | -8 | fragile | |
| 151 | DeepSeek V3.2 Exp | DeepSeek | 71.8 | 0 | +4 | stable | |
| 152 | DeepSeek V3.1 | DeepSeek | 71.8 | 0 | +7 | fragile | |
| 153 | DeepSeek V3 0324 | DeepSeek | 71.8 | 0 | -10 | fragile | |
| 154 | Mistral Medium 3.5 | Mistral AI | 71.6 | 0 | -10 | fragile | |
| 155 | MiniMax M2.7 | MiniMax | 71.6 | 0 | +6 | fragile | |
| 156 | MiniMax M2.5 | MiniMax | 71.6 | 0 | -11 | fragile | |
| 157 | GPT-4o (2024-11-20) | OpenAI | 71.2 | 0 | +60 | fragile | |
| 158 | GPT-4o (2024-08-06) | OpenAI | 71.2 | 0 | -12 | fragile | |
| 159 | GPT-4o | OpenAI | 71.2 | 0 | -12 | fragile | |
| 160 | GPT-4o (2024-05-13) | OpenAI | 71.2 | 0 | -12 | fragile | |
| 161 | MiniMax M2.1 | MiniMax | 71.0 | 0 | -5 | stable | |
| 162 | MiniMax M2 | MiniMax | 71.0 | 0 | -12 | fragile | |
| 163 | MiniMax M1 | MiniMax | 70.8 | 0 | -12 | fragile | |
| 164 | GLM 4.5 Air | Zhipu AI | 70.7 | 0 | -12 | fragile | |
| 165 | Llama 4 Maverick | Meta | 70.7 | 0 | -12 | fragile | |
| 166 | Claude Haiku 4.5 | Anthropic | 69.9 | 0 | -9 | fragile | |
| 167 | Claude Haiku 4.5 (batch) | Anthropic | 69.9 | 0 | -9 | fragile | |
| 168 | DeepSeek V3 | DeepSeek | 69.5 | 0 | -8 | fragile | |
| 169 | Qwen3 VL 235B A22B Thinking | Alibaba | 69.3 | 0 | +4 | stable | |
| 170 | Qwen3 VL 235B A22B Instruct | Alibaba | 69.3 | 0 | -8 | fragile | |
| 171 | DeepSeek V3.1 Terminus | DeepSeek | 69.3 | 0 | -8 | fragile | |
| 172 | GPT-4o-mini | OpenAI | 69.3 | 0 | -8 | fragile | |
| 173 | Inkling Small | thinkingmachines | 68.7 | 0 | -8 | fragile | |
| 174 | Inkling Small (free) | thinkingmachines | 68.7 | 0 | -8 | fragile | |
| 175 | Qwen3.5-Flash | Alibaba | 68.6 | 0 | -8 | fragile | |
| 176 | Hy3 preview | Tencent | 68.4 | 0 | -8 | fragile | |
| 177 | Qwen3.5 Plus 2026-02-15 | Alibaba | 68.2 | 0 | +159 | fragile | |
| 178 | Qwen3 Max Thinking | Alibaba | 68.2 | 0 | -9 | fragile | |
| 179 | MiniMax M2-her | MiniMax | 68.1 | 0 | -9 | fragile | |
| 180 | GPT-4.1 | OpenAI | 67.7 | 0 | -9 | fragile | |
| 181 | GPT-4.1 (batch) | OpenAI | 67.7 | 0 | -9 | fragile | |
| 182 | Qwen3 Max | Alibaba | 67.4 | 0 | -8 | fragile | |
| 183 | Mistral Large 3 2512 (batch) | Mistral AI | 67.0 | 0 | -8 | fragile | |
| 184 | Llama 3.3 70B Instruct | Meta | 66.8 | 0 | -8 | fragile | |
| 185 | Qwen3 Next 80B A3B Thinking | Alibaba | 66.7 | 0 | +6 | fragile | |
| 186 | Qwen3 Next 80B A3B Instruct | Alibaba | 66.7 | 0 | -9 | fragile | |
| 187 | GPT-4 Turbo | OpenAI | 66.7 | 0 | -9 | fragile | |
| 188 | Qwen3.5-9B | Alibaba | 66.5 | 0 | -9 | fragile | |
| 189 | Step 3.5 Flash | StepFun | 66.1 | 0 | -9 | fragile | |
| 190 | Mistral Large 2407 | Mistral AI | 65.9 | 0 | +23 | fragile | |
| 191 | Mistral Large | Mistral AI | 65.9 | 0 | -10 | fragile | |
| 192 | Composer 2 | Cursor | 65.7 | 0 | -10 | fragile | |
| 193 | Composer 2 Fast | Cursor | 65.7 | 0 | -10 | fragile | |
| 194 | GLM 4.6V | Zhipu AI | 65.6 | 0 | -10 | fragile | |
| 195 | Qwen3 235B A22B Thinking 2507 | Alibaba | 65.3 | 0 | -10 | fragile | |
| 196 | Llama 3.1 70B Instruct | Meta | 65.3 | 0 | -10 | fragile | |
| 197 | GPT-4 | OpenAI | 64.9 | 0 | -10 | fragile | |
| 198 | Qwen3 235B A22B Instruct 2507 | Alibaba | 64.7 | 0 | -10 | fragile | |
| 199 | Qwen3 30B A3B Thinking 2507 | Alibaba | 64.1 | 0 | -9 | fragile | |
| 200 | Qwen3 30B A3B Instruct 2507 | Alibaba | 64.1 | 0 | +170 | fragile | |
| 201 | Qwen3 30B A3B | Alibaba | 64.1 | 0 | -12 | fragile | |
| 202 | o3 Mini High | OpenAI | 63.9 | 0 | -10 | fragile | |
| 203 | GLM 4.7 Flash | Zhipu AI | 63.5 | 0 | -10 | fragile | |
| 204 | Mixtral 8x22B Instruct | Mistral AI | 63.4 | 0 | -10 | fragile | |
| 205 | Trinity Large Thinking | arcee-ai | 63.1 | 0 | -10 | fragile | |
| 206 | GPT-4o-mini (batch) | OpenAI | 62.5 | 0 | -10 | fragile | |
| 207 | GLM 4.5V | Zhipu AI | 62.3 | 0 | -10 | fragile | |
| 208 | GPT-5 Nano | OpenAI | 61.9 | 0 | -10 | fragile | |
| 209 | gpt-oss-120b | OpenAI | 61.6 | 0 | -10 | fragile | |
| 210 | GPT-4 Turbo (batch) | OpenAI | 61.5 | 0 | -9 | fragile | |
| 211 | Mercury 2.5 | Inception | 61.2 | 0 | -9 | fragile | |
| 212 | Qwen3 8B | Alibaba | 61.0 | 0 | -9 | fragile | |
| 213 | Mercury 2 | Inception | 60.9 | 0 | -9 | fragile | |
| 214 | Nova 2 Lite | Amazon | 60.4 | 0 | -9 | fragile | |
| 215 | Llama 4 Scout | Meta | 60.2 | 0 | -9 | fragile | |
| 216 | Phi 4 | Microsoft | 60.2 | 0 | -9 | fragile | |
| 217 | GPT-4.1 Mini (batch) | OpenAI | 58.9 | 0 | -9 | fragile | |
| 218 | GPT-4.1 Nano (batch) | OpenAI | 58.9 | 0 | -9 | fragile | |
| 219 | gpt-oss-20b | OpenAI | 57.4 | 0 | -9 | fragile | |
| 220 | gpt-oss-20b (batch) | OpenAI | 57.4 | 0 | +213 | preliminary | |
| 221 | GPT-4o-mini (2024-07-18) | OpenAI | 56.5 | -1 | -10 | fragile | |
| 222 | GPT-4.1 Mini | OpenAI | 56.2 | -1 | -10 | fragile | |
| 223 | Qwen3 235B A22B | Alibaba | 54.0 | -1 | -9 | fragile | |
| 224 | Granite 4.2 8B | IBM | 53.8 | -1 | -9 | fragile | |
| 225 | GPT-5 Mini | OpenAI | 53.8 | -1 | -9 | fragile | |
| 226 | Command A+ | Cohere | 53.2 | 0 | -7 | fragile | |
| 227 | Claude 3 Haiku | Anthropic | 51.3 | -2 | -9 | fragile | |
| 228 | Command A | Cohere | 50.8 | -2 | -9 | fragile | |
| 229 | Command R (08-2024) | Cohere | 48.7 | -1 | -8 | fragile | |
| 230 | Command R+ (08-2024) | Cohere | 48.7 | -2 | -9 | fragile | |
| 231 | Kimi K2.5 | Moonshot AI | 47.5 | -2 | -9 | fragile | |
| 232 | Llama 3.1 8B Instruct | Meta | 44.5 | -2 | -9 | fragile | |
| 233 | GPT-4.1 Nano | OpenAI | 42.1 | -2 | -9 | fragile | |
| 234 | R1 Distill Llama 70B | DeepSeek | 40.7 | -2 | -9 | fragile | |
| 235 | GPT-6 Luna Pro | OpenAI | 40.0 | +198 | +198 | preliminary | |
| 236 | GPT-6 Luna Pro (batch) | OpenAI | 40.0 | +197 | +197 | preliminary | |
| 237 | GPT-6 Luna | OpenAI | 40.0 | +196 | +196 | preliminary | |
| 238 | GPT-6 Luna (batch) | OpenAI | 40.0 | +195 | +195 | preliminary | |
| 239 | GPT-6 Sol Pro | OpenAI | 40.0 | +194 | +194 | preliminary | |
| 240 | GPT-6 Sol Pro (batch) | OpenAI | 40.0 | +193 | +193 | preliminary | |
| 241 | GPT-6 Sol | OpenAI | 40.0 | +192 | +192 | preliminary | |
| 242 | GPT-6 Sol (batch) | OpenAI | 40.0 | +191 | +191 | preliminary | |
| 243 | Claude Opus 5.5 (batch) | Anthropic | 40.0 | +190 | +190 | preliminary | |
| 244 | MiMo-V2.6-Pro-UltraSpeed | Xiaomi | 40.0 | -11 | +189 | preliminary | |
| 245 | MiMo-V2.6-Flash | Xiaomi | 40.0 | -11 | +188 | preliminary | |
| 246 | Qwen3.8 Omni Flash | Alibaba | 40.0 | 0 | +187 | preliminary | |
| 247 | Ternary Bonsai 2 27B | prism-ml | 40.0 | -12 | -21 | fragile | |
| 248 | Pareto | unbiased | 40.0 | -12 | -21 | fragile | |
| 249 | DeepSeek Pro Latest | ~deepseek | 40.0 | -12 | -21 | fragile | |
| 250 | DeepSeek Flash Latest | ~deepseek | 40.0 | -12 | -21 | fragile | |
| 251 | Schematron V2 Turbo | inference-net | 40.0 | -12 | -21 | fragile | |
| 252 | Schematron V2 Small | inference-net | 40.0 | -12 | -21 | fragile | |
| 253 | GPT Astra Latest | ~openai | 40.0 | -12 | -21 | fragile | |
| 254 | GPT Sol Latest | ~openai | 40.0 | -12 | -21 | fragile | |
| 255 | GPT Terra Latest | ~openai | 40.0 | -12 | -21 | fragile | |
| 256 | GPT Luna Latest | ~openai | 40.0 | -12 | -21 | fragile | |
| 257 | Fugu Ultra v2 | sakana | 40.0 | -12 | -21 | fragile | |
| 258 | Fugu Max | sakana | 40.0 | -12 | -21 | fragile | |
| 259 | Ling 3.0 Flash VL | inclusionai | 40.0 | -12 | -21 | fragile | |
| 260 | Ling 3.0 Flash VL (free) | inclusionai | 40.0 | -12 | -21 | fragile | |
| 261 | DeepSeek V4.1 Flash | DeepSeek | 40.0 | -12 | -21 | fragile | |
| 262 | DeepSeek V4.1 Flash (batch) | DeepSeek | 40.0 | 0 | +171 | preliminary | |
| 263 | Ling 3.0 Flash Sante (free) | inclusionai | 40.0 | -13 | -22 | fragile | |
| 264 | Muse Spark 1.3 Contributor | meta | 40.0 | -13 | -21 | fragile | |
| 265 | Hy4 preview | Tencent | 40.0 | -13 | -20 | fragile | |
| 266 | Ling 3.0 Flash Fin | inclusionai | 40.0 | -13 | -20 | fragile | |
| 267 | Ling 3.0 Flash Fin (free) | inclusionai | 40.0 | -13 | -20 | fragile | |
| 268 | GLM Flash Latest | ~z-ai | 40.0 | -13 | -20 | fragile | |
| 269 | Qwen3.8 Flash | Alibaba | 40.0 | -13 | -20 | fragile | |
| 270 | Muse Spark 1.2 Contributor | meta | 40.0 | -13 | -20 | fragile | |
| 271 | DeepSeek V4 Flash Vision Exp | DeepSeek | 40.0 | -13 | -20 | fragile | |
| 272 | Hy-MT2-1.8B | Tencent | 40.0 | -12 | -19 | fragile | |
| 273 | Hy-MT2-30B-A3B | Tencent | 40.0 | -12 | -19 | fragile | |
| 274 | GLM Latest | ~z-ai | 40.0 | -12 | -19 | fragile | |
| 275 | Hy-MT2-7B | Tencent | 40.0 | -12 | -19 | fragile | |
| 276 | Dots3-Note Preview (free) | dots-studio | 40.0 | -12 | -19 | fragile | |
| 277 | Gemini 3.7 Flash | 40.0 | -12 | -19 | fragile | ||
| 278 | Gemini 3.7 Flash (batch) | 40.0 | -12 | -19 | fragile | ||
| 279 | Seed 2.1 Turbo | ByteDance | 40.0 | -12 | -19 | fragile | |
| 280 | Qwen3.8 2.4T A95B | Alibaba | 40.0 | -12 | -19 | fragile | |
| 281 | Seed-2.0-Code | ByteDance | 40.0 | -12 | -18 | fragile | |
| 282 | DeepSeek V4 Pro 0813 | DeepSeek | 40.0 | -12 | -18 | fragile | |
| 283 | LFM2.5-2.6B (free) | Liquid AI | 40.0 | -11 | -17 | fragile | |
| 284 | Nemotron 3.5 Lightning | NVIDIA | 40.0 | -11 | -17 | fragile | |
| 285 | Nemotron 3.5 Lightning (free) | NVIDIA | 40.0 | -11 | -17 | fragile | |
| 286 | Sakana Namazu | sakana | 40.0 | -11 | -17 | fragile | |
| 287 | Solar Pro 4 | Upstage | 40.0 | -11 | -17 | fragile | |
| 288 | Muse Glimmer 30B | meta | 40.0 | -11 | -17 | fragile | |
| 289 | DeepSeek V4 Flash Latest | ~deepseek | 40.0 | -10 | -15 | fragile | |
| 290 | DeepSeek V4 Flash 0731 | DeepSeek | 40.0 | -10 | -15 | fragile | |
| 291 | Qwen3.7 Flash | Alibaba | 40.0 | -9 | -14 | fragile | |
| 292 | Claude Opus 5 (batch) | Anthropic | 40.0 | -9 | -13 | fragile | |
| 293 | Ling 3.0 Flash | inclusionai | 40.0 | -9 | -13 | fragile | |
| 294 | Laguna S 2.1 | poolside | 40.0 | -9 | -13 | fragile | |
| 295 | Laguna S 2.1 (free) | poolside | 40.0 | -9 | -13 | fragile | |
| 296 | Gemini 3.6 Flash | 40.0 | -9 | -13 | fragile | ||
| 297 | Gemini 3.6 Flash (batch) | 40.0 | -9 | -13 | fragile | ||
| 298 | LongCat 2.0 | Meituan | 40.0 | -9 | -13 | fragile | |
| 299 | Kimi K3 | Moonshot AI | 40.0 | -9 | -13 | fragile | |
| 300 | Kimi K3 (batch) | Moonshot AI | 40.0 | 0 | -13 | fragile |
Provider Distribution
OpenAI
87 models
Alibaba
32 models
Google
28 models
Anthropic
27 models
Zhipu AI
18 models
DeepSeek
14 models
xAI
7 models
MiniMax
7 models
meta
6 models
Tencent
6 models
inclusionai
6 models
Xiaomi
5 models
Mistral AI
5 models
Meta
5 models
Moonshot AI
4 models
thinkingmachines
4 models
Cohere
4 models
~openai
4 models
~deepseek
3 models
sakana
3 models
Cursor
2 models
Inception
2 models
inference-net
2 models
~z-ai
2 models
ByteDance
2 models
NVIDIA
2 models
poolside
2 models
StepFun
1 model
arcee-ai
1 model
Amazon
1 model
Microsoft
1 model
IBM
1 model
prism-ml
1 model
unbiased
1 model
dots-studio
1 model
Liquid AI
1 model
Upstage
1 model
Meituan
1 model
Related
Frequently Asked Questions
Models are ranked using a benchmark-driven score from 0 to 100 where benchmark performance (90%) from LMArena, MMLU, GPQA, HumanEval, SWE-bench, and 15+ standardized evaluations is the primary signal. Capabilities and context window serve as tiebreakers (10%). Scores update hourly from live API data across 290+ coding models.
The 24h column shows how many positions a model moved up or down in the last 24 hours, while the 7d column shows the change over the past week. Green values with a + indicate rank improvements, red values indicate drops, and 0 means the rank was unchanged.
The state classification reflects a model's ranking consistency. "Stable" means the model has maintained its position reliably. "Held" indicates it is holding steady but with some variance. "Fragile" means the model's rank is fluctuating and may shift significantly. "Preliminary" is assigned to newly tracked models without enough history.