Metrics
| Country ↑↓ | Provider ↑↓ | Model ↑↓ | Elo ↑↓ | Seconds ↑↓ | Avg Strlen ↑↓ | Avg Lines ↑↓ | Input $ ↑↓ | Output $ ↑↓ | Release ↑↓ | Cutoff ↑↓ | Voter | Votes ↑↓ | Votings ↑↓ | Answers ↑↓ | Bar Chart |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CN | Alibaba | Qwen-Plus | 504 | 2.2 | 945 | 12 | 0.40 | 8.00 | 0 | 176 | 46 | ||||
| FR | Mistral | mistral-large | 768 | 6.6 | 1,186 | 16 | 2.00 | 6.00 | 2024-07-24 | 2023-08-01 | 0 | 309 | 46 | ||
| FR | Mistral | codestral | 771 | 2.5 | 1,915 | 25 | 0.30 | 0.90 | 2024-05-29 | 2023-08-01 | 0 | 185 | 46 | ||
| US | xAI | Grok-2 | 876 | 3.9 | 1,043 | 13 | 2.00 | 10.00 | 2024-11-04 | 2023-10-01 | 0 | 437 | 46 | ||
| US | OpenAI | GPT-4o | 899 | 8.3 | 1,753 | 17 | 2.50 | 10.00 | 2024-05-13 | 2023-10-01 | 0 | 417 | 46 | ||
| US | OpenAI | o3-mini | 915 | 7.5 | 1,486 | 14 | 1.10 | 4.40 | 2025-01-31 | 2023-10-01 | 216 | 387 | 46 | ||
| US | Gemini-2.5-flash | 972 | 12.1 | 1,681 | 19 | 0.15 | 3.50 | 2025-04-17 | 2024-06-30 | 0 | 201 | 46 | |||
| US | Gemini-2.5-pro | 1,014 | 37.1 | 1,499 | 18 | 1.25 | 10.00 | 2025-03-25 | 2023-04-01 | 267 | 274 | 46 | |||
| US | Anthropic | Claude-3-7-sonnet-thinking | 1,059 | 24.7 | 1,527 | 27 | 3.00 | 15.00 | 2025-02-24 | 2024-10-31 | 17 | 267 | 46 | ||
| US | xAI | Grok-3-fast | 1,063 | 5.9 | 1,568 | 12 | 5.00 | 25.00 | 2025-04-11 | 2023-10-01 | Yes | 518 | 243 | 46 | |
| CN | DeepSeek | V3 | 1,130 | 16.9 | 1,197 | 14 | 0.27 | 1.10 | 2024-12-26 | 2024-12-27 | 0 | 417 | 46 | ||
| US | Anthropic | Claude-4-sonnet-thinking | 1,161 | 14.3 | 1,370 | 24 | 15.00 | 75.00 | 2024-05-22 | Yes | 135 | 109 | 46 | ||
| CN | DeepSeek | R1 | 1,330 | 55.0 | 2,265 | 23 | 0.55 | 2.19 | 2025-01-20 | 2023-12-01 | Yes | 808 | 679 | 46 | |
| US | OpenAI | o4-mini | 1,407 | 8.2 | 1,596 | 22 | 1.10 | 4.40 | 2025-04-16 | 2024-06-01 | Yes | 266 | 263 | 46 | |
| US | OpenAI | o3 | 1,518 | 13.4 | 1,927 | 26 | 10.00 | 40.00 | 2025-04-16 | 2023-10-01 | 20 | 236 | 46 |