Google DeepMind·released 2025-03-251 source
Gemini 2.5 Pro (Mar 2025) benchmark scores: 12 benchmarks tracked. 17% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 12 benchmarks·best result 95.56 on MATH level 5 (reproduced)·2 of 12 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MATH level 5 | 95.56accuracy (%) | reproduced· optimizedT1 | 2025-03-31Epoch AI |
| GeoBench | 81accuracy (%) | unverifiedT1 | 2025-03-25GeoBench leaderboard |
| Lech Mazur Writing | 80.5accuracy (%) | unverifiedT1 | 2025-03-25lechmazur/writing Github repository |
| GPQA diamond | 78.45accuracy (%) | reproduced· optimizedT1 | 2025-03-25Epoch AI |
| Aider polyglot | 72.9accuracy (%) | unverified· optimizedT1 | 2025-03-31https://aider.chat/docs/leaderboards/ |
| Fiction.LiveBench | 66.7accuracy (%) | unverifiedT1 | 2025-03-31Fiction.live leaderboard |
| CadEval | 64accuracy (%) | unverifiedT1 | 2025-03-31CadEval Dashboard |
| Balrog | 43.3accuracy (%) | unverifiedT1 | 2025-03-25https://balrogai.com/ |
| SimpleBench | 41.92accuracy (%) | unverifiedT1 | 2025-03-31SimpleBench Leaderboard |
| ARC-AGI | 33accuracy (%) | unverified· optimizedT1 | 2025-03-31ARC Prize Leaderboard |
| VPCT | 22accuracy (%) | unverifiedT1 | 2025-03-31VPCT leaderboard |
| HLE | 14.03accuracy (%) | unverifiedT2 | 2025-03-25 |
Claims drawn from cited facts, not live model generation.
This model originates from Google DeepMind, and its release year is 2025.
2 cited facts
This model is scored on 12 tracked benchmarks. It currently holds no top score on any of them. Because the results have been independently reproduced, these numbers can be treated as verified.
3 cited facts
Based on an average SOTA gap of 24.68 points, the model trails the leading score by a wide margin, placing it well behind the front of the pack rather than at the frontier. It holds the top score on none of the SOTA leaderboards, so it shows no category-leading results yet.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Gemini 2.5 Pro (Mar 2025) is an AI model developed by Google DeepMind, released 2025-03-25. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Gemini 2.5 Pro (Mar 2025) has recorded scores on 12 benchmarks, each shown with its evidence status.
Gemini 2.5 Pro (Mar 2025) has recorded scores on 12 benchmarks — Lech Mazur Writing, GPQA diamond, MATH level 5, CadEval, SimpleBench, Aider polyglot, and 6 more. The full table above shows each score with its evidence status.
2 of 12 recorded scores (17%) are independently reproduced rather than self-reported by the lab.
Gemini 2.5 Pro (Mar 2025) has 12 tracked claims: 2 independently reproduced, 10 unverified.