- Humanity's Last Exam (no tools) 12.1
- GPQA diamond single attempt (pass@1) 78.3
- AIME 2025 single attempt 78
- AIME 2024 single attempt 88
- LiveCodeBench v5 single attempt (10/1/2024-2/1/2025) 63.5
- Aider Polyglot whole 51.1 / diff-fenced 44.2 51.1
- SimpleQA 29.7
- MMMU single attempt 76.7
- Vibe-Eval (Reka) 62
- MRCR 128k (average) (1M pointwise 66.3) 84.6
- Global MMLU (Lite) 88.4
Gemini 2.5 Flash Apr 2025
Gemini 2.5 Flash places in the top three on 3 benchmarks.
Google DeepMind Released 17 Apr 2025 30
Benchmarks with a score
0
Ranked first, out of five or more models
3
In the top three
Google DeepMind Apr 2025 Gemini 2.5 Flash
Apr 2025 snapshot Closed weights
139.9
#124 of 271
Epoch Capabilities Index
- Humanity's Last Exam 12.1% #26 /47
- LiveCodeBench v5 63.5% #19 /44
- CorpFin v2 54.2% #88 /119
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LongBench v2 | 62.1% | #2 of 33 | Official leaderboard | |
| Arena-Hard v2.0 | 68.6% | #4 of 23 | Official leaderboard | |
| Global MMLU Lite | 88.4% | #3 of 16 | Model card | |
| MRCR (Michelangelo, original) | 84.6% | #2 of 9 | Model card | |
| SimpleQA | 29.7% | #25 of 59 | Model card | |
| Humanity's Last Exam | 12.1% | #26 of 47 | Official leaderboard | |
| Lech Mazur Creative Writing | 7.65 | #25 of 44 | Epoch AI | |
| Fiction.LiveBench | 47.2% | #43 of 57 | Epoch AI | |
| Vectara Hallucination Leaderboard (HHEM) | 1.30% | #141 of 148 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2024 | 88% | #24 of 87 | Model card | |
| GPQA Diamond | 78.3% | #122 of 284 | Model card | |
| ForecastBench | 62.7 | #36 of 83 | Epoch AI | |
| OTIS Mock AIME 2024-2025 | 73.1% | #96 of 202 | Epoch AI | |
| AIME 2025 | 78% | #94 of 143 | Model card | |
| ARC-AGI | 32.3% | #75 of 96 | Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v5 | 63.5% | #19 of 44 | Model card | |
| Aider Polyglot | 47.1% | #29 of 54 | Epoch AI | |
| WeirdML | 41% | #76 of 130 | Epoch AI | |
| LiveCodeBench v6 | 60.6% | #13 of 21 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LegalBench | 83.8% | #47 of 138 | Official leaderboard | |
| TaxEval v2 | 71.2% | #77 of 129 | Official leaderboard | |
| CorpFin v2 | 54.2% | #88 of 119 | Official leaderboard | |
| MortgageTax | 58.4% | #67 of 86 | Official leaderboard |
Vision, audio and robotics
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CyberGym | 4.84% | #28 of 33 | Official leaderboard |
Google DeepMind's models over time
Google DeepMind's models in color, against every other model on the Epoch Capabilities Index, by release date.
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 5 of them aren't in the launch post.
Gemini 2.5 Flash Preview Model Card 29 Apr 2025
Capabilities
- Humanity's Last Exam 12.1
- GPQA Diamond 78.3
- AIME 2025 78
- AIME 2024 88
- LiveCodeBench v5 63.5
- Aider Polyglot 51.1
- SimpleQA 29.7
- MMMU 76.7
- Vibe-Eval 62
- MRCR (Michelangelo, original) 84.6
- Global MMLU Lite 88.4