Rankings based on user votes and Elo ratings
# | Model(18/18) | Elo | Win % | Votes | Record |
|---|---|---|---|---|---|
| 1 | GLM 5 | 1259 | 44.7% | 188 | 84W-76L-28T |
| 2 | Claude Sonnet 4.5 | 1259 | 43.3% | 157 | 68W-62L-27T |
| 3 | GPT-5.2 | 1256 | 51.8% | 166 | 86W-53L-27T |
| 4 | MiniMax M3 | 1236 | 50.0% | 42 | 21W-18L-3T |
| 5 | GLM 5.2 | 1231 | 56.4% | 39 | 22W-15L-2T |
| 6 | Functionary Swahili Large | 1224 | 47.1% | 153 | 72W-57L-24T |
| 7 | Claude Sonnet 4.6 | 1199 | 41.8% | 170 | 71W-79L-20T |
| 8 | GPT-oss-120B | 1198 | 42.4% | 151 | 64W-64L-23T |
| 9 | Functionary Swahili Mini | 1186 | 49.3% | 73 | 36W-31L-6T |
| 10 | Claude Haiku 4.5 | 1182 | 38.3% | 180 | 69W-83L-28T |
| 11 | DeepSeek V4 Flash | 1169 | 37.1% | 35 | 13W-22L |
| 12 | GPT-5.6 Luna | 1146 | 32.3% | 31 | 10W-21L |
| 13 | GPT-5 Nano | 1127 | 32.5% | 160 | 52W-87L-21T |
| 14 | Kimi K2.6 | 1254 | 58.3% | 24 | 14W-9L-1T |
| 15 | Mistral Medium 3.5 | 1251 | 45.5% | 22 | 10W-9L-3T |
| 16 | Step 3.7 Flash | 1214 | 50.0% | 14 | 7W-6L-1T |
| 17 | DeepSeek V4 Pro | 1188 | 40.0% | 20 | 8W-11L-1T |
| 18 | Qwen3.7 Max | 1164 | 46.4% | 28 | 13W-15L |
Click column headers to sort by category
Model(18/18) | Overall | Long Prompt | Hard Prompt | Math | Instruction-Following | Coding |
|---|---|---|---|---|---|---|
| GLM 5 | 1 | — | 1 | 2 | 2 | 4 |
| Claude Sonnet 4.5 | 2 | — | 8 | 3 | 5 | 5 |
| GPT-5.2 | 3 | — | 4 | 6 | 1 | 9 |
| MiniMax M3 | 4 | — | 9 | — | — | — |
| GLM 5.2 | 5 | — | — | — | — | — |
| Functionary Swahili Large | 6 | — | 6 | — | 10 | 2 |
| Claude Sonnet 4.6 | 7 | — | 7 | 4 | 9 | 7 |
| GPT-oss-120B | 8 | 1 | 14 | 1 | 8 | 6 |
| Functionary Swahili Mini | 9 | — | 5 | — | 7 | 3 |
| Claude Haiku 4.5 | 10 | — | 2 | 5 | 4 | 1 |
| DeepSeek V4 Flash | 11 | — | 11 | — | — | — |
| GPT-5.6 Luna | 12 | — | 13 | — | — | — |
| GPT-5 Nano | 13 | 2 | 3 | 7 | 11 | 8 |
| Kimi K2.6 | 14 | — | 10 | — | — | — |
| Mistral Medium 3.5 | 15 | — | — | — | — | — |
| Step 3.7 Flash | 16 | — | 12 | — | — | — |
| DeepSeek V4 Pro | 17 | — | 15 | — | 3 | — |
| Qwen3.7 Max | 18 | — | 16 | — | 6 | — |