Qwen2.5-Max
Open Sourcevon Alibaba Qwen · Veroeffentlicht 2024-01-01
41.0
Durchschn. Score
N/A
Eingabepreis
N/A
Ausgabepreis
N/A
Kontextfenster
text
Typ
Tested on 8 benchmarks with 41.0% average. Top scores: Chatbot Arena Elo — Overall (1374.2%), Lech Mazur Writing (72.9%), MATH level 5 (67.2%).
Benchmark-Ergebnisse
| Benchmark | Kategorie | Score | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1374.2 | |
| Lech Mazur Writing | knowledge | 72.9 | |
| MATH level 5 | math | 67.2 | |
| Fiction.LiveBench | knowledge | 66.7 | |
| GPQA diamond | knowledge | 41.5 | |
| Aider polyglot | coding | 21.8 | |
| OTIS Mock AIME 2024-2025 | math | 16.0 | |
| FrontierMath-2025-02-28-Private | math | 1.0 |
Aehnliche Modelle
Mistral AI
41.2
Alibaba Qwen
41.3
Google DeepMind
41.3
Anthropic
41.3