Gemini 3.1 Pro Preview
por Google DeepMind 路 Publicado el 2026-02-19
67.4
puntuaci贸n promedio
$2.00/1M
Precio de entrada
$12.00/1M
Precio de salida
1.0M tokens (~524 books)
Ventana de contexto
multimodal
Tipo
Tested on 12 benchmarks with 67.4% average. Top scores: ARC-AGI (98.0%), OTIS Mock AIME 2024-2025 (95.6%), GPQA diamond (92.1%).
Puntuaciones de benchmark
| Benchmark | Categor铆a | Puntuaci贸n | Bar |
|---|---|---|---|
| ARC-AGI | reasoning | 98.0 | |
| OTIS Mock AIME 2024-2025 | math | 95.6 | |
| GPQA diamond | knowledge | 92.1 | |
| Terminal Bench | coding | 78.4 | |
| SimpleQA Verified | knowledge | 77.3 | |
| ARC-AGI-2 | reasoning | 77.1 | |
| SimpleBench | reasoning | 75.5 | |
| WeirdML | coding | 72.1 | |
| Chess Puzzles | knowledge | 55.0 | |
| FrontierMath-2025-02-28-Private | math | 36.9 | |
| APEX-Agents | agentic | 33.5 | |
| FrontierMath-Tier-4-2025-07-01-Private | math | 16.7 |
Modelos similares
Microsoft
67.4
T
Falcon-180BTII
66.7
Alibaba Qwen
65.6
U
Stable Beluga 2unknown
69.3