Google DeepMind·released 2025-11-181 source
Gemini 3 Pro benchmark scores: 22 benchmarks tracked, leading 2. 27% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 2 of 22 benchmarks·best result 91.38 on OTIS Mock AIME 2024-2025 (reproduced)·6 of 22 independently reproduced·$2/$12 per M tokens
Head-to-headGemini 3 Pro vs Muse SparkConsensus: LiteLLM · See every model’s pricing →
Leads on: FrontierMath-Tier-4-2025-07-01-Private, VPCT
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 91.38accuracy (%) | reproduced· optimizedT1 | 2025-11-18Epoch AI |
| GPQA diamond | 90.15accuracy (%) | reproduced· optimizedT1 | 2025-11-18Epoch AI |
| VPCT | 86.5accuracy (%) | unverifiedT1 | 2025-11-18VPCT leaderboard |
| GeoBench | 84accuracy (%) | unverifiedT1 | 2025-11-18GeoBench leaderboard |
| ARC-AGI | 75accuracy (%) | unverified· optimizedT1 | 2025-11-18ARC Prize Leaderboard |
| SWE-Bench verified | 72.93accuracy (%) | reproduced· optimizedT1 | 2025-11-18Epoch AI |
| SimpleBench | 71.68accuracy (%) | unverifiedT1 | 2025-11-18https://lmcouncil.ai/benchmarks |
| METR Time Horizons | 70.98accuracy (%) | unverifiedT2 | 2025-11-18 |
| WeirdML | 69.93accuracy (%) | unverifiedT1 | 2025-11-18https://htihle.github.io/weirdml.html |
| Terminal Bench | 69.43accuracy (%) | unverifiedT1 | 2025-11-18https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| FrontierMath-2025-02-28-Private | 65.96accuracy (%) | reproduced· optimizedT1 | 2025-11-18Epoch AI |
| Balrog | 58.1accuracy (%) | unverifiedT1 | 2025-11-18https://balrogai.com/ |
| DeepResearch Bench | 46.3accuracy (%) | unverifiedT1 | 2025-11-18https://evals.futuresearch.ai/#drb |
| GDPval | 40.3accuracy (%) | unverifiedT2 | 2025-11-18 |
| HLE | 34.37accuracy (%) | unverifiedT2 | 2025-11-18 |
| FrontierMath-Tier-4-2025-07-01-Private | 31.25accuracy (%) | reproducedT1 | 2025-11-18Epoch AI |
| ARC-AGI-2 | 31.11accuracy (%) | unverifiedT2 | 2025-11-18 |
| Chess Puzzles | 27.4accuracy (%) | reproducedT1 | 2025-11-18Epoch AI |
| ProofBench | 20accuracy (%) | unverifiedT1 | 2025-11-18https://www.vals.ai/benchmarks/proof_bench |
| GSO-Bench | 18.63accuracy (%) | unverifiedT1 | 2025-11-18https://gso-bench.github.io/index.html |
| CL-bench | 15.8accuracy (%) | unverifiedT2 | 2025-11-18 |
| Remote Labor Index | 1.25accuracy (%) | unverifiedT2 | 2025-11-18 |
Claims drawn from cited facts, not live model generation.
This model originates from Google DeepMind, the developer behind its design and training. Its vintage is 2025, placing it within the most recent generation of releases.
2 cited facts
This model is scored on 22 tracked benchmarks and currently holds 2 top scores. Its record is independently reproduced, meaning outside evaluation backs those scores up.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 20.23 points.
1 cited fact
5 facts cross-checked across data sources: 5 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: curated_capability_claims, epoch_benchmarks, litellm_prices
Gemini 3 Pro is an AI model developed by Google DeepMind, released 2025-11-18. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Gemini 3 Pro has recorded scores on 22 benchmarks, each shown with its evidence status.
Gemini 3 Pro has recorded scores on 22 benchmarks — GPQA diamond, OTIS Mock AIME 2024-2025, WeirdML, Chess Puzzles, SimpleBench, METR Time Horizons, and 16 more. The full table above shows each score with its evidence status.
6 of 22 recorded scores (27%) are independently reproduced rather than self-reported by the lab.
Gemini 3 Pro has 22 tracked claims: 6 independently reproduced, 16 unverified.
Listed API pricing: $2 per million input tokens, $12 per million output tokens. See the pricing block for the full breakdown.