Google DeepMind·released 2025-02-051 source
Gemini 2.0 Pro benchmark scores: 4 benchmarks tracked. 50% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 4 benchmarks·best result 83.46 on MATH level 5 (reproduced)·2 of 4 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MATH level 5 | 83.46accuracy (%) | reproduced· optimizedT1 | 2025-02-05Epoch AI |
| GPQA diamond | 54.21accuracy (%) | reproduced· optimizedT1 | 2025-02-05Epoch AI |
| Fiction.LiveBench | 41.7accuracy (%) | unverifiedT1 | 2025-02-05Fiction.live leaderboard |
| Aider polyglot | 35.6accuracy (%) | unverified· optimizedT1 | 2025-02-05https://aider.chat/docs/leaderboards/ |
Claims drawn from cited facts, not live model generation.
This model, developed by Google DeepMind, was released in 2025 as a compact addition to the lab's research lineage.
2 cited facts
The model is assessed on 4 tracked benchmarks and currently holds no top score. These results are independently reproduced, so the scores are corroborated by outside evaluation rather than being mere vendor claims.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 40.89 points.
1 cited fact
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Gemini 2.0 Pro is an AI model developed by Google DeepMind, released 2025-02-05. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Gemini 2.0 Pro has recorded scores on 4 benchmarks, each shown with its evidence status.
Gemini 2.0 Pro has recorded scores on 4 benchmarks — GPQA diamond, MATH level 5, Aider polyglot, Fiction.LiveBench. The full table above shows each score with its evidence status.
2 of 4 recorded scores (50%) are independently reproduced rather than self-reported by the lab.
Gemini 2.0 Pro has 4 tracked claims: 2 independently reproduced, 2 unverified.