AI.info
Benchmarks
Every benchmark the tracker carries, each a leaderboard of the models its measurer ran, with the measurer’s own names, settings and days, under its licence.
En inglés
- Text Arena — Arena, 80 models; highest: Gemini 4 Argon, 1,520
- Code Arena (WebDev) — Arena, 57 models; highest: Claude Fable 5.2, 1,823
- Vision Arena — Arena, 52 models; highest: Claude Fable 5, 1,309
- Epoch Capabilities Index — Epoch AI, 115 models; highest: Claude Fable 5.2, 173.5
- GPQA Diamond — Epoch AI, 108 models; highest: Gemini 4 Argon, 96.4%
- FrontierMath, tiers 1–3 — Epoch AI, 63 models; highest: Claude Fable 5.2, 95.1%
- FrontierMath, tier 4 — Epoch AI, 52 models; highest: GPT-6.1 Sol, 100.0%
- SWE-bench Verified — Epoch AI, 23 models; highest: Claude Opus 4.7, 83.5%
- OTIS Mock AIME 2024–2025 — Epoch AI, 106 models; highest: Gemini 4 Argon, 100.0%
- SimpleQA Verified — Epoch AI, 57 models; highest: Claude Fable 5.2, 94.0%