Kimi K2 0711 vs o3
Côte à côte. Chaque métrique. Chaque benchmark.
| Type | Kimi K2 0711 | o3 |
|---|---|---|
| Provider |  moonshotai |  OpenAI |
| score moyen | 56.2 | 55.2 |
| Prix d'entrée | $0.57 | $2.00 |
| Prix de sortie | $2.30 | $8.00 |
| Fenêtre de contexte | 131K tokens (~66 books) | 200K tokens (~100 books) |
| Sorti le | 2025-07-11 | 2025-04-16 |
| Code source ouvert | Open Source | Proprietary |
Scores de benchmark
11 benchmarks · Kimi K2 0711: 2, o3: 9
| Benchmark | Catégorie | Kimi K2 0711 | o3 |
|---|---|---|---|
| Aider polyglot | coding | 59.1 | 81.3 |
| Fiction.LiveBench | knowledge | 61.1 | 88.9 |
| GSO-Bench | coding | 4.9 | 8.8 |
| HELM — GPQA | knowledge | 65.2 | 75.3 |
| HELM — IFEval | language | 85.0 | 86.9 |
| HELM — MMLU-Pro | knowledge | 81.9 | 85.9 |
| HELM — Omni-MATH | math | 65.4 | 71.4 |
| HELM — WildBench | reasoning | 86.2 | 86.1 |
| Lech Mazur Writing | knowledge | 86.9 | 83.9 |
| SimpleBench | reasoning | 11.6 | 43.7 |
| WeirdML | coding | 39.4 | 52.4 |