model leaderboards
Model capability leaderboards
Compare model rankings across multiple public benchmarks.
← Back to Proxy Detection · World Cup 2026 Prediction Arena →
Community model leaderboard
Relative rankings across four public leaderboards.
511 models
| Rank | Model name | Provider | Artificial Analysisi | LLM Statsi | BenchLMi | Arena.aii | Scorei |
|---|---|---|---|---|---|---|---|
| 🥇Gold medal1 | Claude 5.5 Opus | Anthropic | 1/261 | 1/377 | 2/514 | 1/409 | 574.30 |
| 🥈Silver medal2 | Claude 5.5 Sonnet | Anthropic | 3/261 | 3/377 | 4/514 | N/A | 470.19 |
| 🥉Bronze medal3 | Claude 5.1 Fable | Anthropic | 5/261 | 7/377 | 3/514 | 5/409 | 427.25 |
| 4 | Claude Fable 5 | Anthropic | N/A | 9/377 | 6/514 | 3/409 | 424.79 |
| 5 | Claude Opus 5 | Anthropic | N/A | 4/377 | 5/514 | 11/409 | 415.13 |
| 6 | GPT-6 Astra | OpenAI | 7/261 | 2/377 | 1/514 | 26/409 | 371.28 |
| 7 | GPT-5.6 Sol | OpenAI | N/A | 6/377 | 8/514 | 19/409 | 365.05 |
| 8 | GPT-6.1 Sol | OpenAI | 10/261 | 11/377 | 23/514 | N/A | 328.57 |
| 9 | Claude 4.8 Opus | Anthropic | N/A | 18/377 | 16/514 | 22/409 | 311.86 |
| 10 | Muse Spark 1.1 | Meta | N/A | 23/377 | 28/514 | 12/409 | 303.09 |
| 11 | Gemini 3.7 | N/A | 29/377 | 22/514 | 15/409 | 295.40 | |
| 12 | Kimi K3 | Moonshot AI | 32/261 | 10/377 | 13/514 | 16/409 | 293.02 |
| 13 | Claude 4.7 Opus | Anthropic | N/A | 43/377 | 20/514 | 4/409 | 291.42 |
| 14 | MiMo V2.6 Pro | Xiaomi | 25/261 | 20/377 | 9/514 | 23/409 | 288.88 |
| 15 | Qwen3.8 | Alibaba | 27/261 | 14/377 | 14/514 | 25/409 | 286.06 |
| 16 | Claude 4.6 Opus | Anthropic | N/A | 39/377 | 37/514 | 2/409 | 281.16 |
| 17 | Gemini 3.8 Flash | 38/261 | 21/377 | 10/514 | 10/409 | 279.20 | |
| 18 | GLM-5.3 | Zhipu AI | 29/261 | 12/377 | 30/514 | 24/409 | 273.34 |
| 19 | Hy4 preview | Tencent | N/A | 17/377 | 49/514 | N/A | 265.62 |
| 20 | GPT-6 Sol | OpenAI | 20/261 | 24/377 | 7/514 | 60/409 | 258.82 |
| 21 | Dots3 note | Dots Studio | N/A | N/A | 40/514 | N/A | 255.33 |
| 22 | Step 5 | StepFun | 31/261 | N/A | 19/514 | N/A | 255.27 |
| 23 | Qwen3.7 | Alibaba | N/A | 34/377 | 39/514 | 33/409 | 249.80 |
| 24 | GLM-5.2 | Z.ai | N/A | 35/377 | 41/514 | 31/409 | 249.13 |
| 25 | GPT-5.6 Terra | OpenAI | 36/261 | 19/377 | 11/514 | 50/409 | 248.90 |
| 26 | Ornith 1 5 397b | Ornith AI | N/A | N/A | 43/514 | N/A | 248.10 |
| 27 | Claude Sonnet 5 | Anthropic | N/A | 27/377 | 25/514 | 54/409 | 247.58 |
| 28 | GPT-5.2 | OpenAI | N/A | 50/377 | 24/514 | 30/409 | 247.43 |
| 29 | Gemini 3.6 | N/A | 52/377 | 34/514 | 20/409 | 247.31 | |
| 30 | GPT-5.4 | OpenAI | N/A | 57/377 | 15/514 | 32/409 | 245.10 |
| 31 | Muse Spark 1.2 | Meta | N/A | 73/377 | 32/514 | 7/409 | 239.69 |
| 32 | Muse Spark | Meta | N/A | 58/377 | 48/514 | 13/409 | 237.51 |
| 33 | GLM-5.3 Flash | Zhipu AI | 37/261 | 22/377 | 47/514 | 35/409 | 236.15 |
| 34 | Grok 4.5 | xAI | N/A | 41/377 | 31/514 | 47/409 | 235.75 |
| 35 | DeepSeek V4.1 Flash | DeepSeek | 44/261 | 15/377 | 58/514 | 29/409 | 232.25 |
| 36 | Grok 4.6 | xAI | N/A | 33/377 | 17/514 | 72/409 | 231.38 |
| 37 | Qwen3.8 Flash Next | Alibaba Cloud / Qwen Team | 41/261 | 25/377 | 46/514 | N/A | 226.05 |
| 38 | DeepSeek V4 | DeepSeek | 48/261 | 16/377 | 35/514 | 53/409 | 224.43 |
| 39 | Gemini 3 | N/A | 71/377 | 45/514 | 18/409 | 223.84 | |
| 40 | GPT-5.5 | OpenAI | 75/261 | 28/377 | 12/514 | 21/409 | 221.57 |
| 41 | ERNIE 5.1 | Baidu | N/A | N/A | N/A | 45/409 | 220.71 |
| 42 | GPT-5.6 Luna | OpenAI | N/A | 40/377 | 29/514 | 70/409 | 219.62 |
| 43 | Gemini 3.1 | 63/261 | 47/377 | 33/514 | 17/409 | 213.75 | |
| 44 | Kimi K2.6 | Moonshot AI | N/A | 46/377 | 51/514 | 55/409 | 213.22 |
| 45 | MiMo V2.6 Flash | Xiaomi | 46/261 | 32/377 | 36/514 | 71/409 | 207.00 |
| 46 | Muse Spark 1.3 | Meta | 18/261 | 8/377 | 214/514 | 9/409 | 202.39 |
| 47 | GLM-5.1 | Z.AI | N/A | 66/377 | 53/514 | 49/409 | 202.00 |
| 48 | Claude 4.5 Opus | Anthropic | N/A | 74/377 | 60/514 | 38/409 | 200.02 |
| 49 | Claude 4.6 Sonnet | Anthropic | N/A | 78/377 | 54/514 | 41/409 | 198.49 |
| 50 | GPT-6 Luna | OpenAI | 47/261 | 42/377 | 27/514 | 86/409 | 197.64 |
| 51 | Agents-A1 | InternScience | N/A | N/A | 72/514 | N/A | 196.56 |
| 52 | Ternary bonsai 2 27b | Prism ML | N/A | N/A | 77/514 | N/A | 189.84 |
| 53 | Gemini 3.5 | 88/261 | 55/377 | 38/514 | 27/409 | 185.95 | |
| 54 | GPT-5.1 | OpenAI | N/A | 82/377 | 52/514 | 67/409 | 182.74 |
| 55 | GLM-5 | Z.AI | N/A | 77/377 | 67/514 | 61/409 | 182.48 |
| 56 | Kimi K2.5 | Moonshot AI | N/A | 69/377 | 69/514 | 74/409 | 179.54 |
| 57 | MiMo V2.5 | Xiaomi | N/A | 88/377 | 79/514 | 46/409 | 179.26 |
| 58 | Qwen3.6 Plus | Alibaba | N/A | 64/377 | 66/514 | 84/409 | 178.47 |
| 59 | GPT-5.3 Codex | OpenAI | 58/261 | 84/377 | 42/514 | N/A | 173.96 |
| 60 | Qwen3.5 Plus | Alibaba | N/A | N/A | 91/514 | N/A | 173.14 |
| 61 | Qwen3.7-Plus | Alibaba | 80/261 | 54/377 | 55/514 | 66/409 | 171.74 |
| 62 | Hunyuan HY3 | Tencent | 79/261 | 51/377 | 80/514 | 62/409 | 168.04 |
| 63 | o3-pro | OpenAI | N/A | N/A | 96/514 | N/A | 167.79 |
| 64 | MiniMax M3 | MiniMax | 65/261 | 60/377 | 65/514 | 91/409 | 166.45 |
| 65 | MiMo V2 | Xiaomi | N/A | 91/377 | 78/514 | 79/409 | 163.26 |
| 66 | JT-4.1 Flash 236B A21B | China Mobile | 52/261 | N/A | N/A | N/A | 161.33 |
| 67 | Grok-4 | xAI | N/A | 61/377 | 70/514 | 125/409 | 160.34 |
| 68 | Inkling | Thinking Machines Lab | 77/261 | 72/377 | 57/514 | 87/409 | 159.75 |
| 69 | Grok 4.7 | xAI | 23/261 | 30/377 | 215/514 | 92/409 | 159.59 |
| 70 | Kimi K2.7 Code | Moonshot AI | 76/261 | 65/377 | 83/514 | N/A | 156.85 |
| 71 | Claude Mythos 5 | Anthropic | N/A | 5/377 | 211/514 | N/A | 155.17 |
| 72 | Qwen3.5 | Alibaba | 91/261 | 70/377 | 98/514 | 52/409 | 154.63 |
| 73 | Claude 4.5 Sonnet | Anthropic | N/A | 115/377 | 94/514 | 63/409 | 154.19 |
| 74 | Motif 3 | Motif Technologies | 56/261 | N/A | N/A | N/A | 153.92 |
| 75 | GPT-5.2 Codex | OpenAI | N/A | 100/377 | 87/514 | N/A | 152.67 |
| 76 | GLM-4.7 | Z.AI | N/A | 99/377 | 89/514 | 90/409 | 152.05 |
| 77 | Grok 4.20 | SpaceXAI | N/A | 180/377 | 50/514 | 34/409 | 151.74 |
| 78 | Qwen3.6 | Alibaba | 105/261 | 92/377 | 59/514 | 56/409 | 149.38 |
| 79 | Ling 3.0 | InclusionAI | 84/261 | 53/377 | 109/514 | N/A | 149.24 |
| 80 | K2 horizon 375b a23b | Institute of Foundation Models | 60/261 | N/A | N/A | N/A | 147.02 |
| 81 | Atria dawn | Shanghai AI Laboratory | N/A | 13/377 | 219/514 | N/A | 146.85 |
| 82 | Quasar 438b | Multiverse Computing | 72/261 | N/A | 101/514 | N/A | 144.32 |
| 83 | Gemini 2.5 | N/A | 130/377 | 84/514 | 82/409 | 144.29 | |
| 84 | Apodex 1 1 | Apodex | 73/261 | N/A | 102/514 | N/A | 143.10 |
| 85 | DeepSeek V3.2 | DeepSeek | N/A | 104/377 | 85/514 | 116/409 | 142.04 |
| 86 | GPT-5 | OpenAI | N/A | 102/377 | 108/514 | 102/409 | 141.32 |
| 87 | MiniMax M2.7 | MiniMax | N/A | 94/377 | 93/514 | 134/409 | 137.58 |
| 88 | Nex n2 pro | Nex AGI | 66/261 | N/A | N/A | N/A | 137.49 |
| 89 | GLM-5V Turbo | Z.AI | N/A | 127/377 | 92/514 | 104/409 | 135.98 |
| 90 | Claude 4.1 Opus | Anthropic | N/A | 131/377 | 132/514 | 76/409 | 133.42 |
| 91 | MiniMax M2.5 | MiniMax | N/A | 79/377 | 88/514 | 168/409 | 133.24 |
| 92 | K-EXAONE | LG AI Research | N/A | N/A | 136/514 | N/A | 132.96 |
| 93 | Nemotron 3 | NVIDIA | 85/261 | 87/377 | 114/514 | 115/409 | 132.86 |
| 94 | Seed 1.8 | ByteDance | N/A | 101/377 | N/A | N/A | 131.71 |
| 95 | Gemma 4 | 110/261 | 109/377 | 100/514 | 73/409 | 130.60 | |
| 96 | JT-4.1 | China Mobile | 71/261 | N/A | N/A | N/A | 130.18 |
| 97 | Grok 4.3 | xAI | N/A | 185/377 | 64/514 | 89/409 | 128.15 |
| 98 | MiMo-V2-Omni | Xiaomi | N/A | 150/377 | 90/514 | 107/409 | 127.94 |
| 99 | Step 3.5 | StepFun | N/A | 76/377 | 124/514 | 165/409 | 126.55 |
| 100 | o3 | OpenAI | 97/261 | 121/377 | 97/514 | 106/409 | 125.48 |
| 101 | Seed 2.0 | Bytedance | N/A | 63/377 | 275/514 | 64/409 | 125.11 |
| 102 | GPT-5.1 Codex | OpenAI | N/A | 136/377 | 110/514 | N/A | 124.70 |
| 103 | Grok-3 | xAI | N/A | 119/377 | 106/514 | 141/409 | 124.18 |
| 104 | Step 3.7 | StepFun | N/A | 129/377 | 123/514 | N/A | 123.53 |
| 105 | Grok 4.1 | SpaceXAI | N/A | 209/377 | 105/514 | 48/409 | 123.10 |
| 106 | Kimi K2 | Moonshot AI | N/A | 90/377 | 190/514 | 110/409 | 122.95 |
| 107 | Qwen3 | Alibaba | N/A | 143/377 | 130/514 | 101/409 | 122.74 |
| 108 | Ling 2.6 | InclusionAI | N/A | N/A | 151/514 | N/A | 122.49 |
| 109 | DeepSeek-V3.2 (Thinking) | DeepSeek | N/A | 112/377 | N/A | N/A | 121.37 |
| 110 | Muse Glimmer | Meta | 107/261 | 98/377 | 121/514 | 118/409 | 120.91 |
| 111 | K2 horizon mova 36b a4b | Institute of Foundation Models | 78/261 | N/A | N/A | N/A | 120.78 |
| 112 | Solar Pro 3 | Upstage | N/A | N/A | 156/514 | N/A | 119.24 |
| 113 | GLM-4.6 | Z.AI | N/A | 139/377 | 129/514 | 119/409 | 119.22 |
| 114 | ERNIE 5.0 | Baidu | 118/261 | 107/377 | N/A | 77/409 | 117.74 |
| 115 | Laguna S 2.1 | Poolside | N/A | 62/377 | 233/514 | N/A | 117.48 |
| 116 | Ornith 1 5 35b a3b | Ornith AI | N/A | N/A | 161/514 | N/A | 116.08 |
| 117 | Solar Pro 2 | Upstage | N/A | N/A | 162/514 | N/A | 115.46 |
| 118 | Seed 2.1 | ByteDance | N/A | 31/377 | 291/514 | N/A | 112.64 |
| 119 | ChatGPT-4o | OpenAI | N/A | 168/377 | N/A | 85/409 | 111.86 |
| 120 | ZAYA1 | Zyphra | N/A | N/A | 169/514 | N/A | 111.23 |
| 121 | DeepSeek R1 | DeepSeek | N/A | 175/377 | 116/514 | 124/409 | 110.56 |
| 122 | Claude 4 Opus | Anthropic | N/A | 147/377 | N/A | 114/409 | 109.56 |
| 123 | GLM-4.5 | Z.AI | N/A | 148/377 | 145/514 | 142/409 | 107.70 |
| 124 | G9v3 | AI9Stars | 89/261 | N/A | N/A | N/A | 107.59 |
| 125 | KAT-Coder-Pro V2 | KwaiKAT | 90/261 | N/A | N/A | N/A | 106.47 |
| 126 | GPT-5.3 | OpenAI | N/A | 133/377 | 260/514 | 75/409 | 105.75 |
| 127 | DeepSeek-V3.1 | DeepSeek | N/A | 186/377 | 122/514 | 129/409 | 105.35 |
| 128 | Mistral Medium 3.5 | Mistral | 119/261 | 153/377 | 141/514 | 113/409 | 104.10 |
| 129 | Claude 4.5 Haiku | Anthropic | 109/261 | 163/377 | 117/514 | 137/409 | 104.09 |
| 130 | Mistral Medium | Mistral | N/A | N/A | N/A | 147/409 | 102.33 |
| 131 | Mistral Medium 3 | Mistral | N/A | N/A | 185/514 | N/A | 102.19 |
| 132 | K2 horizon 7b | Institute of Foundation Models | 94/261 | N/A | N/A | N/A | 102.12 |
| 133 | Amazon Nova | Amazon | 121/261 | 124/377 | 199/514 | 111/409 | 101.40 |
| 134 | Claude 5.1 Mythos | Anthropic | N/A | 45/377 | 312/514 | N/A | 101.28 |
| 135 | Ornith 1 5 9b | Ornith AI | N/A | N/A | 187/514 | N/A | 101.11 |
| 136 | Qwen3.5 Omni Plus | Alibaba | 95/261 | N/A | N/A | N/A | 101.06 |
| 137 | Solar Pro 4 | Upstage | 67/261 | 96/377 | 264/514 | 177/409 | 100.94 |
| 138 | MAI Code 1 | Microsoft | N/A | 138/377 | N/A | N/A | 100.50 |
| 139 | Claude 4 Sonnet | Anthropic | N/A | 173/377 | 142/514 | 153/409 | 99.49 |
| 140 | GPT-4.5 | OpenAI | N/A | 204/377 | N/A | 83/409 | 98.88 |
| 141 | MiniMax M2.1 | MiniMax | N/A | 117/377 | N/A | 178/409 | 98.68 |
| 142 | MAI-Thinking-1 | Microsoft | N/A | 110/377 | 234/514 | N/A | 98.48 |
| 143 | Qwen3 VL | Alibaba | N/A | 156/377 | N/A | 138/409 | 97.92 |
| 144 | o1 | OpenAI | N/A | 199/377 | 135/514 | 152/409 | 94.84 |
| 145 | Qwen2.5 | Alibaba | N/A | N/A | 164/514 | 188/409 | 94.32 |
| 146 | GPT-4.1 | OpenAI | N/A | 224/377 | 128/514 | 133/409 | 94.30 |
| 147 | JT-35B | China Mobile | 102/261 | N/A | N/A | N/A | 93.95 |
| 148 | Hunyuan | Tencent | N/A | N/A | N/A | 162/409 | 92.61 |
| 149 | A.X-K2 | SK Telecom | 86/261 | N/A | 241/514 | N/A | 91.83 |
| 150 | LongCat Flash | Meituan | 145/261 | 93/377 | 289/514 | 98/409 | 91.37 |
| 151 | EXAONE | LG AI Research | 127/261 | 160/377 | 166/514 | N/A | 88.84 |
| 152 | Sakana Fugu | Sakana AI | N/A | N/A | 212/514 | N/A | 88.56 |
| 153 | o1-pro | OpenAI | N/A | 207/377 | 143/514 | N/A | 88.28 |
| 154 | Doubao Seed Code | ByteDance Seed | 108/261 | N/A | N/A | N/A | 88.24 |
| 155 | Holo3 | H Company | N/A | N/A | 213/514 | N/A | 88.09 |
| 156 | o3-mini | OpenAI | N/A | 195/377 | 125/514 | 198/409 | 87.98 |
| 157 | GPT-5 Codex | OpenAI | N/A | 157/377 | N/A | N/A | 87.60 |
| 158 | Grok Code Fast 1 | xAI | N/A | 200/377 | 159/514 | N/A | 86.77 |
| 159 | Holo3.1 | H Company | N/A | N/A | 216/514 | N/A | 86.69 |
| 160 | GPT-OSS | OpenAI | 143/261 | 140/377 | 134/514 | 208/409 | 86.25 |
| 161 | o4-mini | OpenAI | N/A | 151/377 | 238/514 | 167/409 | 85.81 |
| 162 | Qwen3.8 Omni Flash | Alibaba | N/A | N/A | 218/514 | N/A | 85.77 |
| 163 | Ring 2.6 | InclusionAI | 111/261 | N/A | N/A | N/A | 85.50 |
| 164 | Sakana Namazu | Sakana AI | N/A | 56/377 | 363/514 | N/A | 85.01 |
| 165 | K2 horizon 3 7b | Institute of Foundation Models | 112/261 | N/A | N/A | N/A | 84.60 |
| 166 | BTL-4 | Bad Theory Labs | N/A | N/A | 221/514 | N/A | 84.41 |
| 167 | Composer 2.5 | Cursor | N/A | N/A | 222/514 | N/A | 83.95 |
| 168 | Command A | Cohere | 128/261 | 176/377 | 140/514 | 205/409 | 83.77 |
| 169 | Composer 2 | Cursor | N/A | N/A | 223/514 | N/A | 83.51 |
| 170 | Swe 1 7 | Cognition | N/A | N/A | 224/514 | N/A | 83.06 |
| 171 | Step 3 VL | StepFun | N/A | 165/377 | N/A | N/A | 82.63 |
| 172 | Ornith 1.0 | DeepReinforce AI | N/A | N/A | 225/514 | N/A | 82.61 |
| 173 | DeepSeek V3 | DeepSeek | N/A | 236/377 | 160/514 | 160/409 | 81.46 |
| 174 | Solar Open 2 | Upstage | 82/261 | N/A | 294/514 | N/A | 81.40 |
| 175 | Trinity Large | Arcee AI | 155/261 | N/A | 149/514 | 183/409 | 81.25 |
| 176 | Claude 3.7 Sonnet | Anthropic | N/A | 177/377 | N/A | 172/409 | 80.96 |
| 177 | Interfaze beta | Interfaze | N/A | N/A | 230/514 | N/A | 80.41 |
| 178 | GLM-4.6V | Z.ai | N/A | N/A | N/A | 184/409 | 79.88 |
| 179 | Mellum2 | JetBrains | N/A | N/A | 232/514 | N/A | 79.55 |
| 180 | Granite 4.2 | IBM | 116/261 | 179/377 | 177/514 | 227/409 | 78.82 |
| 181 | K-EXAONE 2.0 | LG AI Research | 100/261 | 159/377 | 290/514 | N/A | 78.45 |
| 182 | Claude 3.5 Sonnet | Anthropic | N/A | 215/377 | 178/514 | 187/409 | 78.10 |
| 183 | Mercury 2 | Inception | 137/261 | 181/377 | 146/514 | 223/409 | 77.96 |
| 184 | MiniMax M1 | MiniMax | N/A | 196/377 | 194/514 | 196/409 | 77.90 |
| 185 | Soofi s 30b a3b | Soofi Project | N/A | N/A | 239/514 | N/A | 76.58 |
| 186 | Pokee isaac 28b | Pokee AI | N/A | N/A | 242/514 | N/A | 75.33 |
| 187 | Laguna XS.2 | Poolside | N/A | 171/377 | 254/514 | N/A | 74.68 |
| 188 | Sarvam | Sarvam | 181/261 | 162/377 | 154/514 | N/A | 74.60 |
| 189 | Qwen3 Next | Alibaba | 148/261 | 178/377 | N/A | 157/409 | 74.58 |
| 190 | MiniMax M2 | MiniMax | N/A | 154/377 | N/A | 221/409 | 74.57 |
| 191 | Mistral Small 4 | Mistral | 147/261 | 217/377 | 147/514 | N/A | 74.46 |
| 192 | Apriel v1 6 15b thinker | ServiceNow | 124/261 | N/A | N/A | N/A | 74.42 |
| 193 | Nemotron 3.5 Lightning | NVIDIA | 131/261 | 187/377 | 202/514 | 217/409 | 73.32 |
| 194 | U2 | Unisound | N/A | 184/377 | N/A | N/A | 71.73 |
| 195 | MAI Code 1.1 | Microsoft | N/A | 146/377 | 304/514 | N/A | 71.47 |
| 196 | Laguna M.1 | Poolside | N/A | N/A | 252/514 | N/A | 71.28 |
| 197 | Mistral Small | Mistral | N/A | N/A | N/A | 203/409 | 70.05 |
| 198 | Nemotron 4 | NVIDIA | N/A | N/A | 208/514 | 241/409 | 69.93 |
| 199 | MiniCPM5 2b | OpenBMB | 136/261 | N/A | 245/514 | N/A | 69.54 |
| 200 | Mistral Large 3 | Mistral | 169/261 | 271/377 | 150/514 | 139/409 | 69.41 |
| 201 | GPT-4o | OpenAI | N/A | 246/377 | 170/514 | 218/409 | 68.24 |
| 202 | GLM-4.5V | Z.ai | N/A | N/A | N/A | 207/409 | 68.10 |
| 203 | DeepSeek R1 Distill Qwen | DeepSeek | N/A | 256/377 | 174/514 | N/A | 67.57 |
| 204 | Qwen3.5 Omni Flash | Alibaba | 135/261 | N/A | N/A | N/A | 65.92 |
| 205 | DeepSeek LLM V2 | DeepSeek | N/A | N/A | 266/514 | N/A | 65.87 |
| 206 | Gemini 1.5 | N/A | 263/377 | 186/514 | 209/409 | 64.72 | |
| 207 | Seed 1.6 | ByteDance | N/A | N/A | 271/514 | N/A | 64.01 |
| 208 | JT-MINI | China Mobile | 138/261 | N/A | N/A | N/A | 63.73 |
| 209 | LFM2.5 | LiquidAI | 186/261 | 216/377 | 155/514 | N/A | 63.67 |
| 210 | Qwen3 Omni | Alibaba | 193/261 | N/A | 167/514 | N/A | 63.08 |
| 211 | DeepSeekMath V2 | DeepSeek | N/A | N/A | 274/514 | N/A | 62.91 |
| 212 | Qwen3 Coder | Alibaba | 170/261 | 197/377 | N/A | 174/409 | 62.90 |
| 213 | Qwen Plus | Alibaba | N/A | N/A | N/A | 219/409 | 62.46 |
| 214 | Ling 2.0 | Ant Group | N/A | N/A | N/A | 220/409 | 62.01 |
| 215 | Aion 2 0 | Aion Labs | N/A | N/A | 277/514 | N/A | 61.82 |
| 216 | HyperNova 60B 2605 | Multiverse Computing | 141/261 | N/A | N/A | N/A | 61.58 |
| 217 | Z-1 | Z | N/A | N/A | 278/514 | N/A | 61.46 |
| 218 | Gemini 2.0 | N/A | 227/377 | N/A | 200/409 | 60.59 | |
| 219 | Nemotron | Nvidia | 142/261 | 214/377 | 283/514 | 214/409 | 60.44 |
| 220 | Moonshot v1 | Moonshot AI | N/A | N/A | 281/514 | N/A | 60.39 |
| 221 | MiniCPM5 | OpenBMB | 180/261 | N/A | 210/514 | N/A | 59.95 |
| 222 | GLM-4 Plus | Z.ai | N/A | N/A | N/A | 225/409 | 59.76 |
| 223 | INTELLECT-3 | N/A | 157/261 | N/A | N/A | 204/409 | 59.76 |
| 224 | K2-V2 (high) | Institute of Foundation Models | 144/261 | N/A | N/A | N/A | 59.47 |
| 225 | Llama 3 | Meta | N/A | N/A | 195/514 | 298/409 | 59.06 |
| 226 | Qwen2.5 Coder | Alibaba | N/A | N/A | 188/514 | 304/409 | 58.97 |
| 227 | Llama 4 Behemoth | Meta | N/A | N/A | 286/514 | N/A | 58.62 |
| 228 | Llama 4 Maverick | Meta | 161/261 | 242/377 | 196/514 | 242/409 | 58.35 |
| 229 | LongCat 2.0 | LongCat | 101/261 | N/A | 377/514 | N/A | 57.94 |
| 230 | Gemini Advanced | N/A | N/A | N/A | 231/409 | 57.13 | |
| 231 | Claude 3 Opus | Anthropic | N/A | 275/377 | 183/514 | 251/409 | 56.85 |
| 232 | Mistral Large 2 | Mistral | N/A | 296/377 | 181/514 | N/A | 56.45 |
| 233 | Lfm2 5 vl 3b | LiquidAI | N/A | N/A | 293/514 | N/A | 56.21 |
| 234 | GPT-4 | OpenAI | N/A | 278/377 | 197/514 | 246/409 | 55.50 |
| 235 | Llada2 2 flash | InclusionAI | N/A | N/A | 296/514 | N/A | 55.19 |
| 236 | Llada2 2 mini | InclusionAI | N/A | N/A | 297/514 | N/A | 54.85 |
| 237 | Step 2 | StepFun | N/A | N/A | N/A | 237/409 | 54.57 |
| 238 | Ember 1 | Fireworks | N/A | N/A | 298/514 | N/A | 54.51 |
| 239 | Swe 2 | Cognition | N/A | N/A | 299/514 | N/A | 54.18 |
| 240 | Celeris-1 | Celeris | 220/261 | N/A | 165/514 | N/A | 54.14 |
| 241 | Llama 3.1 | Meta | 206/261 | 241/377 | 168/514 | 235/409 | 54.04 |
| 242 | ZAYA1 vl 8b | Zyphra | N/A | N/A | 301/514 | N/A | 53.51 |
| 243 | Mi:dm K 2.5 Pro | Korea Telecom | 153/261 | N/A | N/A | N/A | 53.41 |
| 244 | Yi | N/A | N/A | N/A | N/A | 240/409 | 53.31 |
| 245 | Pareto 26 9 | Unbiased | N/A | N/A | 302/514 | N/A | 53.18 |
| 246 | Qwen3 14b | Alibaba Cloud / Qwen Team | N/A | 222/377 | N/A | N/A | 52.96 |
| 247 | Mixtral 8x22B | Mistral | N/A | N/A | 198/514 | 325/409 | 52.78 |
| 248 | Kanana 2 3b instruct | Kakao | N/A | N/A | 305/514 | N/A | 52.19 |
| 249 | Ministral 3 | Mistral | 228/261 | 201/377 | 192/514 | N/A | 52.19 |
| 250 | Kanana 2 1 3b instruct | Kakao | N/A | N/A | 306/514 | N/A | 51.86 |
| 251 | Kimi K1.5 | Moonshot AI | N/A | 226/377 | N/A | N/A | 51.17 |
| 252 | North Small Translate | Cohere | N/A | N/A | 309/514 | N/A | 50.89 |
| 253 | QwQ | Alibaba | N/A | 240/377 | N/A | 232/409 | 50.76 |
| 254 | DiffusionGemma | 167/261 | 213/377 | N/A | N/A | 50.68 | |
| 255 | Apodex 1 1 mini | Apodex | N/A | N/A | 310/514 | N/A | 50.57 |
| 256 | Btl 3 | Bad Theory Labs | N/A | N/A | 311/514 | N/A | 50.24 |
| 257 | Solar Open | Upstage | 158/261 | N/A | N/A | N/A | 50.19 |
| 258 | UI-Mate 27b | Tencent | N/A | N/A | 313/514 | N/A | 49.60 |
| 259 | UI-Mate 9b | Tencent | N/A | N/A | 314/514 | N/A | 49.28 |
| 260 | Llama 4 Scout | Meta | 189/261 | 291/377 | 179/514 | 253/409 | 48.50 |
| 261 | Fara1.5-27B | Microsoft | N/A | N/A | 318/514 | N/A | 48.02 |
| 262 | Qwen2.5 VL | Alibaba | N/A | 258/377 | 285/514 | N/A | 47.90 |
| 263 | Fara1.5-4B | Microsoft | N/A | N/A | 319/514 | N/A | 47.70 |
| 264 | DeepSeek R1 Zero | DeepSeek | N/A | 234/377 | N/A | N/A | 47.69 |
| 265 | Step-1o | StepFun | N/A | N/A | N/A | 254/409 | 47.64 |
| 266 | Qwen | Alibaba | N/A | N/A | N/A | 256/409 | 46.85 |
| 267 | NORTH Mini | Cohere | 164/261 | 189/377 | 385/514 | N/A | 46.80 |
| 268 | Magistral Medium | Mistral | 139/261 | 255/377 | N/A | 275/409 | 46.66 |
| 269 | Step 3 | StepFun | 194/261 | N/A | N/A | 210/409 | 46.46 |
| 270 | Phi 4 Reasoning | Microsoft | N/A | 239/377 | N/A | N/A | 45.58 |
| 271 | LFM2 | LiquidAI | 230/261 | N/A | 200/514 | N/A | 45.39 |
| 272 | Holo2 | H Company | N/A | N/A | 327/514 | N/A | 45.23 |
| 273 | Gemma 3 | 250/261 | 288/377 | 182/514 | 193/409 | 45.11 | |
| 274 | Grok-2 | SpaceXAI | N/A | 266/377 | N/A | 233/409 | 45.00 |
| 275 | DeepSeek Coder V2 | DeepSeek | N/A | N/A | 270/514 | 307/409 | 44.95 |
| 276 | Qwen2.5 Plus | Alibaba | N/A | N/A | N/A | 261/409 | 44.92 |
| 277 | Mistral Large | Mistral | N/A | N/A | N/A | 262/409 | 44.54 |
| 278 | Athene | N/A | N/A | N/A | N/A | 263/409 | 44.16 |
| 279 | DeepSeek R1 Distill Llama | DeepSeek | N/A | 243/377 | N/A | N/A | 43.92 |
| 280 | o1-mini | OpenAI | N/A | 274/377 | N/A | 230/409 | 43.92 |
| 281 | Elevenlabs eleven v4 | ElevenLabs | N/A | N/A | 332/514 | N/A | 43.71 |
| 282 | MiniCPM-SALA | OpenBMB | N/A | 244/377 | N/A | N/A | 43.51 |
| 283 | Elevenlabs eleven v4 turbo | ElevenLabs | N/A | N/A | 333/514 | N/A | 43.41 |
| 284 | Qwen2 VL | Alibaba Cloud / Qwen Team | N/A | 245/377 | N/A | N/A | 43.10 |
| 285 | Gemini 3.8 TTS | N/A | N/A | 335/514 | N/A | 42.81 | |
| 286 | Motif 2 | Motif Technologies | 171/261 | N/A | N/A | N/A | 42.29 |
| 287 | Grok Voice Transcribe 2.0 | xAI | N/A | N/A | 337/514 | N/A | 42.21 |
| 288 | Mistral 7B | Mistral | N/A | N/A | 209/514 | 371/409 | 42.03 |
| 289 | Mercury | Inception | N/A | N/A | 331/514 | 274/409 | 42.02 |
| 290 | Wispr canto | Wispr | N/A | N/A | 338/514 | N/A | 41.92 |
| 291 | Gemini 3.8 Live | N/A | N/A | 339/514 | N/A | 41.62 | |
| 292 | GPT live 1 | OpenAI | N/A | N/A | 341/514 | N/A | 41.03 |
| 293 | Br voice reasoner | Bairong Xdynamics | N/A | N/A | 342/514 | N/A | 40.74 |
| 294 | Devstral | Mistral AI | N/A | 251/377 | N/A | N/A | 40.68 |
| 295 | MAI transcribe 2 | Microsoft | N/A | N/A | 343/514 | N/A | 40.45 |
| 296 | Vibevoice asr streaming 7b | Microsoft | N/A | N/A | 345/514 | N/A | 39.87 |
| 297 | Vibevoice asr streaming 1 5b | Microsoft | N/A | N/A | 346/514 | N/A | 39.58 |
| 298 | Tri-21B-Think | Trillion Labs | 176/261 | N/A | N/A | N/A | 39.40 |
| 299 | Granite 4.1 | IBM | N/A | N/A | N/A | 276/409 | 39.33 |
| 300 | Muse voice transcribe | Meta | N/A | N/A | 347/514 | N/A | 39.29 |
| 301 | Llama 3.3 | Meta | 195/261 | 249/377 | N/A | 257/409 | 38.76 |
| 302 | Inworld Realtime TTS-2 | Inworld | N/A | N/A | 349/514 | N/A | 38.72 |
| 303 | Inworld Realtime TTS-2 Flash | Inworld | N/A | N/A | 350/514 | N/A | 38.43 |
| 304 | Cartesia Sonic 3 | Cartesia | N/A | N/A | 351/514 | N/A | 38.14 |
| 305 | Gemini 3 5 transcribe | N/A | N/A | 352/514 | N/A | 37.86 | |
| 306 | Gemini 1.0 | N/A | 365/377 | 207/514 | N/A | 37.77 | |
| 307 | DeepSeek-V2.5 | DeepSeek | N/A | 289/377 | N/A | 248/409 | 37.62 |
| 308 | Granite speech 5 0 470m turboctc | IBM | N/A | N/A | 353/514 | N/A | 37.58 |
| 309 | AuK | Tencent | N/A | N/A | 354/514 | N/A | 37.29 |
| 310 | Claude 3 Haiku | Anthropic | N/A | 343/377 | 206/514 | 310/409 | 37.18 |
| 311 | Mixtral 8x7B | Mistral | N/A | N/A | 280/514 | 342/409 | 37.04 |
| 312 | Toast 1 | Mixedbread | N/A | N/A | 355/514 | N/A | 37.01 |
| 313 | Qwen 2.5 | Alibaba Cloud / Qwen Team | N/A | 261/377 | N/A | N/A | 36.77 |
| 314 | OLMo 3.1 | Ai2 | 209/261 | N/A | N/A | 239/409 | 36.74 |
| 315 | GPT-5.6 Cyber | OpenAI | N/A | N/A | 356/514 | N/A | 36.73 |
| 316 | LFG-3 | glenn2 | N/A | N/A | 357/514 | N/A | 36.45 |
| 317 | Hark handoff | Hark | N/A | N/A | 358/514 | N/A | 36.17 |
| 318 | Macaw | Bad Theory Labs | N/A | N/A | 359/514 | N/A | 35.89 |
| 319 | Pixtral Large | Mistral AI | N/A | 264/377 | N/A | N/A | 35.63 |
| 320 | Seedrealtime | ByteDance | N/A | N/A | 361/514 | N/A | 35.33 |
| 321 | Ring 2.0 | Ant Group | 208/261 | N/A | N/A | 249/409 | 35.26 |
| 322 | Reka Core | N/A | N/A | N/A | N/A | 288/409 | 35.08 |
| 323 | Hy asr 3 0 | Tencent | N/A | N/A | 362/514 | N/A | 35.06 |
| 324 | Claude 3.5 Haiku | Anthropic | N/A | 306/377 | N/A | 245/409 | 34.91 |
| 325 | Phi 4 | Microsoft | 231/261 | 304/377 | 191/514 | 313/409 | 34.66 |
| 326 | GPT transcribe | OpenAI | N/A | N/A | 364/514 | N/A | 34.51 |
| 327 | Nanbeige4 1 3b | Nanbeige | 185/261 | N/A | N/A | N/A | 34.42 |
| 328 | Magistral Small | Mistral | 184/261 | 269/377 | N/A | N/A | 34.35 |
| 329 | GPT live transcribe | OpenAI | N/A | N/A | 365/514 | N/A | 34.23 |
| 330 | MAI cyber 1 flash | Microsoft | N/A | N/A | 366/514 | N/A | 33.96 |
| 331 | MAI-Voice-2 | Microsoft | N/A | N/A | 368/514 | N/A | 33.41 |
| 332 | Cosmos3-Edge | NVIDIA | N/A | N/A | 370/514 | N/A | 32.87 |
| 333 | HyperCLOVA X | Naver | 146/261 | N/A | 453/514 | N/A | 32.80 |
| 334 | Granite 4.0 | IBM | 227/261 | 366/377 | 173/514 | 290/409 | 32.64 |
| 335 | 1-bit Bonsai 27B | Prism ML | N/A | N/A | 371/514 | N/A | 32.60 |
| 336 | Ternary bonsai 27b | Prism ML | N/A | N/A | 372/514 | N/A | 32.33 |
| 337 | GPT Realtime | OpenAI | N/A | N/A | 373/514 | N/A | 32.06 |
| 338 | Hermes 4 | Nous Research | 190/261 | N/A | N/A | N/A | 31.75 |
| 339 | Leanstral | Mistral | N/A | N/A | 375/514 | N/A | 31.53 |
| 340 | Cohere transcribe arabic 07 | Cohere | N/A | N/A | 376/514 | N/A | 31.26 |
| 341 | Falcon h1r 7b | TII UAE | 191/261 | N/A | N/A | N/A | 31.22 |
| 342 | LFG-2 | glenn2 | N/A | N/A | 378/514 | N/A | 30.73 |
| 343 | Qwen3 asr 1 7b | Alibaba | N/A | N/A | 379/514 | N/A | 30.47 |
| 344 | GLM-4 | Z.ai | N/A | N/A | N/A | 302/409 | 30.33 |
| 345 | Qwen3 asr 0 6b | Alibaba | N/A | N/A | 380/514 | N/A | 30.21 |
| 346 | Reka Flash | N/A | N/A | N/A | N/A | 303/409 | 30.00 |
| 347 | Qwen agentworld 35b a3b | Alibaba | N/A | N/A | 381/514 | N/A | 29.94 |
| 348 | C4AI Aya Expanse | Cohere | N/A | N/A | N/A | 305/409 | 29.34 |
| 349 | Zonos 2 | Zyphra | N/A | N/A | 384/514 | N/A | 29.16 |
| 350 | Mistral Small 3.1 | Mistral | N/A | 311/377 | N/A | 278/409 | 28.46 |
| 351 | MAI transcribe 1 5 | Microsoft | N/A | N/A | 387/514 | N/A | 28.38 |
| 352 | Mistral Small 3.2 | Mistral AI | N/A | 286/377 | N/A | N/A | 27.63 |
| 353 | Hy-MT2 30b a3b | Tencent | N/A | N/A | 393/514 | N/A | 26.84 |
| 354 | Hy-MT2 1 8b | Tencent | N/A | N/A | 394/514 | N/A | 26.59 |
| 355 | OLMo 2 | Ai2 | N/A | N/A | N/A | 314/409 | 26.43 |
| 356 | Grok Build | xAI | N/A | N/A | 395/514 | N/A | 26.33 |
| 357 | QvQ | Alibaba Cloud / Qwen Team | N/A | 290/377 | N/A | N/A | 26.24 |
| 358 | Hy-MT1 5 1 8b 1 25bit | Tencent Hunyuan | N/A | N/A | 397/514 | N/A | 25.83 |
| 359 | Deepgram flux multilingual | Deepgram | N/A | N/A | 398/514 | N/A | 25.58 |
| 360 | GPT audio 1 5 | OpenAI | N/A | N/A | 399/514 | N/A | 25.33 |
| 361 | Qwen2 | Alibaba | N/A | 302/377 | N/A | 308/409 | 25.22 |
| 362 | LFG-1 | glenn2 | N/A | N/A | 400/514 | N/A | 25.08 |
| 363 | Mistral Small 3 | Mistral | N/A | 310/377 | N/A | 301/409 | 24.96 |
| 364 | Grok TTS | xAI | N/A | N/A | 401/514 | N/A | 24.83 |
| 365 | Bonsai | Prism ML | N/A | N/A | 402/514 | N/A | 24.58 |
| 366 | Gemini Pro | N/A | N/A | N/A | 320/409 | 24.54 | |
| 367 | Qwen1.5 | Alibaba | N/A | N/A | N/A | 321/409 | 24.23 |
| 368 | Kimi Linear | Kimi | 205/261 | N/A | N/A | N/A | 24.15 |
| 369 | Jamba 1.5 | N/A | N/A | 330/377 | N/A | 286/409 | 23.91 |
| 370 | NORTH Micro | Cohere | N/A | 363/377 | 315/514 | N/A | 23.84 |
| 371 | OLMo 3 | Ai2 | 238/261 | N/A | N/A | 272/409 | 23.77 |
| 372 | Gemma 3n | N/A | 358/377 | N/A | 260/409 | 23.24 | |
| 373 | Claude 3 Sonnet | Anthropic | N/A | 327/377 | N/A | 295/409 | 23.03 |
| 374 | Molmo 2 | Ai2 | 254/261 | N/A | N/A | 252/409 | 22.98 |
| 375 | Gemma 2 | N/A | 338/377 | N/A | 285/409 | 22.73 | |
| 376 | Murf falcon 2 | Murf AI | N/A | N/A | 413/514 | N/A | 21.88 |
| 377 | ElevenLabs Eleven v3 | ElevenLabs | N/A | N/A | 415/514 | N/A | 21.39 |
| 378 | Command R | Cohere | N/A | 336/377 | N/A | 299/409 | 20.93 |
| 379 | MiniMax speech 2 8 hd | MiniMax | N/A | N/A | 418/514 | N/A | 20.67 |
| 380 | Inworld tts 1 5 | Inworld | N/A | N/A | 419/514 | N/A | 20.44 |
| 381 | Zephyr | N/A | N/A | N/A | N/A | 334/409 | 20.26 |
| 382 | Kyutai pocket tts | Kyutai | N/A | N/A | 420/514 | N/A | 20.20 |
| 383 | Phi-4 Mini | Microsoft | 221/261 | 297/377 | N/A | N/A | 20.18 |
| 384 | Hermes 3 405b | Nous Research | N/A | 309/377 | N/A | N/A | 19.89 |
| 385 | Granite 3.1 | IBM | N/A | N/A | N/A | 337/409 | 19.36 |
| 386 | Deepgram flux | Deepgram | N/A | N/A | 424/514 | N/A | 19.25 |
| 387 | Qwen2.5 Omni | Alibaba Cloud / Qwen Team | N/A | 307/377 | 430/514 | N/A | 19.18 |
| 388 | Hermes 3 | Nous Research | N/A | 312/377 | N/A | N/A | 18.92 |
| 389 | Audio Flamingo | NVIDIA | N/A | N/A | 426/514 | N/A | 18.78 |
| 390 | Phi 3 | Microsoft | N/A | N/A | N/A | 341/409 | 18.18 |
| 391 | Kimi Audio | Moonshot AI | N/A | N/A | 429/514 | N/A | 18.08 |
| 392 | R1 1776 | Perplexity | 218/261 | N/A | N/A | N/A | 18.00 |
| 393 | Baichuan-Audio | Baichuan | N/A | N/A | 433/514 | N/A | 17.15 |
| 394 | InternLM2 5 20b chat | N/A | N/A | N/A | N/A | 345/409 | 17.02 |
| 395 | Step-Audio | StepFun | N/A | N/A | 434/514 | N/A | 16.92 |
| 396 | Llama 3.2 | Meta | 219/261 | 305/377 | N/A | 362/409 | 16.91 |
| 397 | DeepSeek LLM | DeepSeek | N/A | N/A | N/A | 346/409 | 16.73 |
| 398 | DeepSeek VL2 | DeepSeek | N/A | 319/377 | N/A | N/A | 16.71 |
| 399 | Ola | Ola-Omni | N/A | N/A | 435/514 | N/A | 16.69 |
| 400 | Baichuan Omni | Baichuan | N/A | N/A | 436/514 | N/A | 16.46 |
| 401 | WizardLM | Microsoft | N/A | N/A | N/A | 347/409 | 16.44 |
| 402 | MiniCPM O | OpenBMB | N/A | N/A | 437/514 | N/A | 16.23 |
| 403 | VITA | VITA-MLLM | N/A | N/A | 438/514 | N/A | 16.00 |
| 404 | Granite 3.0 | IBM | N/A | N/A | N/A | 349/409 | 15.86 |
| 405 | Slam omni | X-LANCE | N/A | N/A | 439/514 | N/A | 15.77 |
| 406 | OpenChat 3.5 | N/A | N/A | N/A | N/A | 350/409 | 15.58 |
| 407 | MERaLiON audiollm | AI Singapore | N/A | N/A | 440/514 | N/A | 15.54 |
| 408 | Granite 3.3 | IBM | N/A | 323/377 | N/A | N/A | 15.46 |
| 409 | Lyra Base | DVL Lab | N/A | N/A | 441/514 | N/A | 15.32 |
| 410 | DBRX | N/A | N/A | N/A | 452/514 | 343/409 | 15.20 |
| 411 | Lyra Mini | DVL Lab | N/A | N/A | 442/514 | N/A | 15.09 |
| 412 | Gemma 1.1 | N/A | N/A | N/A | 352/409 | 15.01 | |
| 413 | GLM-4-Voice | Zhipu AI | N/A | N/A | 443/514 | N/A | 14.87 |
| 414 | Phi-4 Multimodal | Microsoft | 234/261 | 320/377 | 432/514 | N/A | 14.86 |
| 415 | DeepHermes 3 | Nous Research | 225/261 | N/A | N/A | N/A | 14.84 |
| 416 | Snowflake arctic instruct | N/A | N/A | N/A | N/A | 353/409 | 14.72 |
| 417 | Ichigo | Jan | N/A | N/A | 444/514 | N/A | 14.64 |
| 418 | Phi 3.5 MoE | Microsoft | N/A | 326/377 | N/A | N/A | 14.53 |
| 419 | Mini-Omni2 | gpt-omni | N/A | N/A | 445/514 | N/A | 14.41 |
| 420 | Jamba 1.7 | AI21 Labs | 226/261 | N/A | N/A | N/A | 14.40 |
| 421 | Ministral | Mistral | N/A | 360/377 | N/A | 319/409 | 14.22 |
| 422 | DiVA Llama 3 8B | DiVA authors | N/A | N/A | 446/514 | N/A | 14.19 |
| 423 | Tulu 2 | N/A | N/A | N/A | N/A | 355/409 | 14.16 |
| 424 | Moshi 7b | Kyutai | N/A | N/A | 447/514 | N/A | 13.97 |
| 425 | Openhermes 2.5 mistral 7b | N/A | N/A | N/A | N/A | 356/409 | 13.88 |
| 426 | Llama omni | ICTNLP | N/A | N/A | 448/514 | N/A | 13.74 |
| 427 | Vicuna | N/A | N/A | N/A | N/A | 357/409 | 13.60 |
| 428 | Mini-Omni 0.5B | gpt-omni | N/A | N/A | 449/514 | N/A | 13.52 |
| 429 | ERNIE 4.5 | Baidu | 197/261 | 377/377 | N/A | N/A | 13.08 |
| 430 | Qwen2 Audio | Alibaba | N/A | N/A | 451/514 | N/A | 13.08 |
| 431 | Starling | N/A | N/A | N/A | N/A | 359/409 | 13.04 |
| 432 | Gemini Diffusion | N/A | 331/377 | N/A | N/A | 13.01 | |
| 433 | Llama 2 | Meta | N/A | N/A | N/A | 360/409 | 12.76 |
| 434 | Starling lm 7b alpha | N/A | N/A | N/A | N/A | 361/409 | 12.48 |
| 435 | Kanana | Kakao | N/A | N/A | 455/514 | N/A | 12.19 |
| 436 | Codestral | Mistral AI | N/A | 334/377 | N/A | N/A | 12.11 |
| 437 | Nous Hermes 2 | N/A | N/A | N/A | N/A | 363/409 | 11.93 |
| 438 | A.X series | SK Telecom | N/A | N/A | 458/514 | N/A | 11.54 |
| 439 | Varco | NC AI | N/A | N/A | 459/514 | N/A | 11.32 |
| 440 | GPT-3.5 | OpenAI | N/A | 372/377 | N/A | 328/409 | 11.17 |
| 441 | Thunder-LLM 8B | Academic | N/A | N/A | 460/514 | N/A | 11.10 |
| 442 | DNA 1.0 8B | Community | N/A | N/A | 461/514 | N/A | 10.88 |
| 443 | Solar 1 | N/A | N/A | N/A | N/A | 367/409 | 10.84 |
| 444 | Pharia 1 | Aleph Alpha | N/A | N/A | 462/514 | N/A | 10.67 |
| 445 | Dolphin 2.2.1 mistral 7b | N/A | N/A | N/A | N/A | 368/409 | 10.56 |
| 446 | MiniCPM V4.6 | OpenBMB | 235/261 | N/A | N/A | N/A | 10.49 |
| 447 | Grok-1.5V | xAI | N/A | 340/377 | N/A | N/A | 10.33 |
| 448 | MPT | N/A | N/A | N/A | N/A | 369/409 | 10.29 |
| 449 | Orion | LightOn | N/A | N/A | 464/514 | N/A | 10.23 |
| 450 | Jamba Reasoning | AI21 Labs | 236/261 | N/A | N/A | N/A | 10.07 |
| 451 | Holotron | H Company | N/A | N/A | 466/514 | N/A | 9.80 |
| 452 | Reka Flash 3 | Reka AI | 237/261 | N/A | N/A | N/A | 9.65 |
| 453 | Bland speech v3 | Bland AI | N/A | N/A | 467/514 | N/A | 9.59 |
| 454 | Falcon 180b chat | N/A | N/A | N/A | N/A | 372/409 | 9.48 |
| 455 | MiniMax Speech 02 | MiniMax | N/A | N/A | 468/514 | N/A | 9.38 |
| 456 | Lightning v3 1 pro | Smallest AI | N/A | N/A | 469/514 | N/A | 9.16 |
| 457 | Pixtral | Mistral AI | N/A | 344/377 | N/A | N/A | 9.16 |
| 458 | Ultravox | Fixie AI | N/A | N/A | 470/514 | N/A | 8.95 |
| 459 | Molmo 1 | Allen Institute for AI | 239/261 | N/A | N/A | N/A | 8.81 |
| 460 | ShieldStral | Mistral AI | N/A | 346/377 | N/A | N/A | 8.58 |
| 461 | Grok-1.5 | xAI | N/A | 348/377 | N/A | N/A | 8.00 |
| 462 | PaLM 2 | N/A | N/A | N/A | 378/409 | 7.88 | |
| 463 | Gemma 1 | N/A | N/A | N/A | 379/409 | 7.62 | |
| 464 | CodeLlama | Meta | N/A | N/A | N/A | 380/409 | 7.35 |
| 465 | Megrez 3b omni | Infinigence AI | N/A | N/A | 478/514 | N/A | 7.26 |
| 466 | MAIr hub 0 5b omni | Mair Hub | N/A | N/A | 479/514 | N/A | 7.05 |
| 467 | Phi 3.5 Vision | Microsoft | N/A | 352/377 | N/A | N/A | 6.86 |
| 468 | Grok Voice 2.0 | xAI | N/A | N/A | 480/514 | N/A | 6.84 |
| 469 | Grok Realtime | xAI | N/A | N/A | 482/514 | N/A | 6.43 |
| 470 | Guanaco 33b | N/A | N/A | N/A | N/A | 384/409 | 6.31 |
| 471 | Phi 3.5 Mini | Microsoft | N/A | 354/377 | N/A | N/A | 6.29 |
| 472 | Grok Voice 1.0 | xAI | N/A | N/A | 483/514 | N/A | 6.22 |
| 473 | Stripedhyena nous 7b | N/A | N/A | N/A | N/A | 386/409 | 5.79 |
| 474 | MedGemma | N/A | 357/377 | N/A | N/A | 5.45 | |
| 475 | GLM Realtime | Zhipu AI | N/A | N/A | 488/514 | N/A | 5.19 |
| 476 | SmolLM2 | N/A | N/A | N/A | N/A | 390/409 | 4.76 |
| 477 | Pandagpt 7b | PandaGPT authors | N/A | N/A | 491/514 | N/A | 4.58 |
| 478 | Next gpt 7b | NExT-GPT authors | N/A | N/A | 492/514 | N/A | 4.37 |
| 479 | Mistral Nemo | Mistral AI | N/A | 361/377 | N/A | N/A | 4.34 |
| 480 | Qwen Audio | Alibaba | N/A | N/A | 493/514 | N/A | 4.17 |
| 481 | SALMONN | SALMONN authors | N/A | N/A | 494/514 | N/A | 3.97 |
| 482 | Apertus | Swiss AI Initiative | 251/261 | N/A | N/A | N/A | 3.91 |
| 483 | Speechgpt 7b | OpenMOSS | N/A | N/A | 496/514 | N/A | 3.56 |
| 484 | OLMo 1 | Ai2 | N/A | N/A | N/A | 396/409 | 3.23 |
| 485 | Blsp 7b | BLSP authors | N/A | N/A | 498/514 | N/A | 3.16 |
| 486 | Koala 13b | N/A | N/A | N/A | N/A | 397/409 | 2.98 |
| 487 | Cohere Transcribe | Cohere | N/A | N/A | 500/514 | N/A | 2.76 |
| 488 | Alpaca 13b | N/A | N/A | N/A | N/A | 398/409 | 2.73 |
| 489 | Scribe v2.2 | ElevenLabs | N/A | N/A | 501/514 | N/A | 2.56 |
| 490 | GPT4all 13b snoozy | N/A | N/A | N/A | N/A | 399/409 | 2.48 |
| 491 | Cartesia Ink-Whisper | Cartesia | N/A | N/A | 502/514 | N/A | 2.36 |
| 492 | ChatGLM | N/A | N/A | N/A | N/A | 401/409 | 1.98 |
| 493 | Deepgram Nova | Deepgram | N/A | N/A | 504/514 | N/A | 1.96 |
| 494 | Kokoro 82m | hexgrad | N/A | N/A | 505/514 | N/A | 1.77 |
| 495 | RWKV 4 Raven 14B | N/A | N/A | N/A | N/A | 402/409 | 1.73 |
| 496 | Voxtral | Mistral AI | N/A | N/A | 506/514 | N/A | 1.57 |
| 497 | Deepgram Aura | Deepgram | N/A | N/A | 507/514 | N/A | 1.37 |
| 498 | Oasst pythia 12b | N/A | N/A | N/A | N/A | 404/409 | 1.23 |
| 499 | Parakeet | NVIDIA | N/A | N/A | 508/514 | N/A | 1.17 |
| 500 | Aya | Cohere | 258/261 | N/A | N/A | N/A | 1.16 |
| 501 | Kalpa tts beta v0 1 | Kalpa Labs | N/A | N/A | 509/514 | N/A | 0.98 |
| 502 | Freya tts adam v1 | Freya | N/A | N/A | 510/514 | N/A | 0.78 |
| 503 | FastChat | N/A | N/A | N/A | N/A | 406/409 | 0.74 |
| 504 | Fish audio s2 1 pro | Fish Audio | N/A | N/A | 511/514 | N/A | 0.59 |
| 505 | Dolly V2 | N/A | N/A | N/A | N/A | 407/409 | 0.49 |
| 506 | Qwen4 Max | Alibaba | N/A | N/A | 512/514 | N/A | 0.39 |
| 507 | Llama 1 | Meta | N/A | N/A | N/A | 408/409 | 0.24 |
| 508 | Qwen4 Flash & Plus | Alibaba | N/A | N/A | 513/514 | N/A | 0.19 |
| 509 | K2 horizon 0 9b | Institute of Foundation Models | 261/261 | N/A | N/A | N/A | 0.00 |
| 510 | Qwen4 | Alibaba | N/A | N/A | 514/514 | N/A | 0.00 |
| 511 | Stablelm tuned alpha 7b | N/A | N/A | N/A | N/A | 409/409 | 0.00 |