Gemini 1.5 Pro (Sept 2024)
par Google · Sorti le 2024-01-01
31.3
score moyen
N/A
Prix d'entrée
N/A
Prix de sortie
N/A
Fenêtre de contexte
text
Type
Tested on 10 benchmarks with 31.3% average. Top scores: MMLU (82.5%), MATH level 5 (70.4%), GPQA diamond (43.0%).
Scores de benchmark
| Benchmark | Catégorie | Score | Bar |
|---|---|---|---|
| MMLU | knowledge | 82.5 | |
| MATH level 5 | math | 70.4 | |
| GPQA diamond | knowledge | 43.0 | |
| CadEval | coding | 34.0 | |
| OTIS Mock AIME 2024-2025 | math | 23.0 | |
| WeirdML | coding | 22.2 | |
| Balrog | knowledge | 21.0 | |
| SimpleBench | reasoning | 12.5 | |
| The Agent Company | agentic | 3.4 | |
| ARC-AGI-2 | reasoning | 0.8 |
Modèles similaires
OpenAI
31.6
OpenAI
31.6
OpenAI
31.6
OpenAI
31.6