Elimination Game
Resultados de evaluaciones comparativas de IA y rendimiento de modelos
Tipo: numerical
Resultados registrados
56
Puntuación media
4.07
Rango de puntuaciones
0.30 - 7.52
Modelo líder
7.52 - GPT 5.2
Puntuaciones a lo largo del tiempo
Puntuaciones individuales de la evaluación a lo largo del tiempo.
Resultados de modelos
| Organización | Modelos | Fecha del resultado | Mejor puntuación | Información | Autodeclarado | Fuente |
|---|---|---|---|---|---|---|
| GPT 5.2 | 11 dic 2025 | 7,52 | Medium reasoning; sigma 0.276; games 331; avg points 0.705 | No | Fuente | |
| GPT 5 | 07 ago 2025 | 5,97 | Medium reasoning; sigma 0.212; games 556; avg points 0.611 | No | Fuente | |
| GPT 5 Mini | 07 ago 2025 | 5,73 | Medium reasoning; sigma 0.226; games 465; avg points 0.603 | No | Fuente | |
| Claude Opus 4.5 | 24 nov 2025 | 5,66 | 16K thinking; sigma 0.264; games 341; avg points 0.594 | No | Fuente | |
| Gemini 3 Flash Preview | 17 dic 2025 | 5,66 | sigma 0.244; games 398; avg points 0.598 | No | Fuente | |
| Grok 3 Mini Beta | 19 feb 2025 | 5,53 | High reasoning; sigma 0.216; games 511; avg points 0.597 | No | Fuente | |
| DeepSeek R1 (2025-05-28) | 28 may 2025 | 5,35 | sigma 0.204; games 565; avg points 0.581 | No | Fuente | |
| Claude 3.7 Sonnet | 24 feb 2025 | 5,28 | 16K thinking; sigma 0.158; games 947; avg points 0.593 | No | Fuente | |
| Claude Opus 4.1 | 05 ago 2025 | 5,21 | No reasoning; sigma 0.290; games 276; avg points 0.578 | No | Fuente | |
| Claude Sonnet 4.5 | 29 sept 2025 | 5,19 | 16K thinking; sigma 0.262; games 348; avg points 0.559 | No | Fuente | |
| Grok 4 | 10 jul 2025 | 5,15 | sigma 0.228; games 455; avg points 0.565 | No | Fuente | |
| GPT 4.5 Preview | 27 feb 2025 | 5,12 | sigma 0.217; games 499; avg points 0.597 | No | Fuente | |
| Claude 3.5 Sonnet (2024-10-22) | 22 oct 2024 | 5,10 | sigma 0.180; games 731; avg points 0.597 | No | Fuente | |
| Grok 3 Beta | 19 feb 2025 | 5,10 | No reasoning; sigma 0.207; games 539; avg points 0.579 | No | Fuente | |
| Gemini 3 Pro Preview | 18 nov 2025 | 4,89 | sigma 0.271; games 324; avg points 0.544 | No | Fuente | |
| Gemini 2.5 Flash | 17 jun 2025 | 4,73 | sigma 0.202; games 578; avg points 0.548 | No | Fuente | |
| Claude Sonnet 4 | 21 may 2025 | 4,64 | No reasoning; sigma 0.252; games 369; avg points 0.539 | No | Fuente | |
| MiniMax M2 | 27 oct 2025 | 4,57 | sigma 0.280; games 291; avg points 0.522 | No | Fuente | |
| Qwen 3 Max Thinking | 26 ene 2026 | 4,49 | sigma 0.285; games 286; avg points 0.516 | No | Fuente | |
| o3 | 16 abr 2025 | 4,48 | Medium reasoning; sigma 0.192; games 656; avg points 0.523 | No | Fuente | |
| Claude Opus 4 | 21 may 2025 | 4,41 | No reasoning; sigma 0.292; games 273; avg points 0.527 | No | Fuente | |
| Qwen 3 A235 A22B Instruct 2507 | - | 4,41 | Instruct 2507; sigma 0.274; games 305; avg points 0.507 | No | Fuente | |
| o3 mini | 30 ene 2025 | 4,37 | Medium reasoning; sigma 0.139; games 1194; avg points 0.531 | No | Fuente | |
| Kimi K2 Thinking | 06 nov 2025 | 4,33 | 64K thinking; sigma 0.311; games 238; avg points 0.504 | No | Fuente | |
| GLM 4.5 | 28 jul 2025 | 4,25 | sigma 0.251; games 368; avg points 0.505 | No | Fuente |