Artificial Intelligence Models are all here
Model Toplist by Intelligence Index(the higher the better)
| Number | Model | Intelligence |
| 1 | o3-pro | 71 |
| 2 | Gemini 2.5 Pro | 70 |
| 3 | o3 | 70 |
| 4 | o4-mini (high) | 70 |
| 5 | Gemini 2.5 Pro (Mar '25) | 69 |
| 6 | DeepSeek R1 0528 (May '25) | 68 |
| 7 | Gemini 2.5 Pro (May' 25) | 68 |
| 8 | Grok 3 mini Reasoning (high) | 67 |
| 9 | o3-mini (high) | 66 |
| 10 | Gemini 2.5 Flash (Reasoning) | 65 |
Model Latency LeaderBoard(the lower the better)
Chat Model Toplist by ArenaElo(the higher the better)
| Number | Model | ArenaElo |
| 1 | Gemini-2.5-Pro | 1477 |
| 2 | o3-2025-04-16 | 1428 |
| 3 | ChatGPT-4o-latest (2025-03-26) | 1428 |
| 4 | DeepSeek-R1-0528 | 1424 |
| 5 | Grok-3-Preview-02-24 | 1422 |
| 6 | Gemini-2.5-Flash | 1420 |
| 7 | GPT-4.5-Preview | 1415 |
| 8 | Gemini-2.0-Flash-Thinking-Exp-01-21 | 1398 |
| 9 | Gemini-2.0-Pro-Exp-02-05 | 1397 |
| 10 | Qwen3-235B-A22B-no-thinking | 1388 |
Model Votes LeaderBoard(the higher the better)
Coding Model Toplist by HumanEvalPlus(the higher the better)
| Number | Model | HumanEvalPlus |
| 1 | O1 Preview (Sept 2024) | 89 |
| 2 | O1 Mini (Sept 2024) | 89 |
| 3 | GPT 4o (Aug 2024) | 87.2 |
| 4 | Qwen2.5-Coder-32B-Instruct | 87.2 |
| 5 | DeepSeek-V3 (Nov 2024) | 86.6 |
| 6 | GPT-4-Turbo (April 2024) | 86.6 |
| 7 | DeepSeek-V2.5 (Nov 2024) | 83.5 |
| 8 | GPT 4o Mini (July 2024) | 83.5 |
| 9 | DeepSeek-Coder-V2-Instruct | 82.3 |
| 10 | Claude Sonnet 3.5 (June 2024) | 81.7 |