- Humanity's Last Exam (no tools) 18.8
- GPQA diamond, single attempt (pass@1) 84
- AIME 2025, single attempt (pass@1) 86.7
- AIME 2024, single attempt (pass@1) 92
- LiveCodeBench v5, single attempt (pass@1) 70.4
- Aider Polyglot, whole (diff = 68.6%) 74
- SWE-bench verified 63.8
- SimpleQA 52.9
- MMMU, single attempt (pass@1) 81.7
- Vibe-Eval (Reka) 69.4
- Best of MRCR, 128k (average) / MRCR, 1M (pointwise) 94.5
- Global MMLU (Lite) 89.8
Gemini 2.5 Pro Mar 2025
Gemini 2.5 Pro ranks first on 10 of the 63 benchmarks it has scores on.
68
Benchmarks with a score
10
Ranked first, out of five or more models
22
In the top three
Google DeepMind Mar 2025 Gemini 2.5 Pro
Mar 2025 snapshot Closed weights Flagship
144.0
#98 of 271
Epoch Capabilities Index
- Humanity's Last Exam 18.2% #22 /47
- GPQA Diamond 83.8% #75 /219
- LiveCodeBench v5 70.4% #12 /44
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 | |
|---|---|---|---|---|
| MMBench-CN v1.1 | 88.1% | #1 of 178 | Official leaderboard | |
| LongBench v2 | 63.3% | #1 of 33 | Official leaderboard | |
| LLM Confabulation Leaderboard | 10.8% | #3 of 58 | Official leaderboard | |
| Global MMLU Lite | 89.8% | #1 of 16 | Model card | |
| FaithJudge | 7.63% | #3 of 37 | Official leaderboard | |
| MRCR (Michelangelo, original) | 94.5% | #1 of 9 | Model card | |
| Arena-Hard v2.0 | 79% | #3 of 23 | Official leaderboard | |
| SimpleQA | 52.9% | #12 of 59 | Model card | |
| Lech Mazur Creative Writing | 8.05 | #17 of 44 | Epoch AI | |
| Fiction.LiveBench | 66.7% | #23 of 57 | Epoch AI | |
| Humanity's Last Exam | 18.2% | #22 of 47 | Official leaderboard | |
| Vectara Hallucination Leaderboard (HHEM) | 1.10% | #144 of 148 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PolyMath | 52.2% | #2 of 38 | Official leaderboard | |
| AIME 2024 | 92% | #9 of 87 | Model card | |
| MATH Level 5 | 95.6% | #11 of 94 | Epoch AI | |
| PHYBench | 36.9% | #5 of 28 | Official leaderboard | |
| USAMO 2025 | 24.4% | #2 of 10 | Official leaderboard | |
| Misguided Attention | 55.2% | #12 of 45 | Official leaderboard | |
| GPQA Diamond | 83.8% | #75 of 219 | Epoch AI | |
| PutnamBench | 0.45% | #5 of 14 | Official leaderboard | |
| HMMT 2025 | 82.5% | #22 of 53 | Official leaderboard | |
| AIME 2025 | 86.7% | #65 of 143 | Model card | |
| SMT 2025 | 84.9% | #20 of 40 | Official leaderboard | |
| SimpleBench | 51.6% | #52 of 100 | Official leaderboard | |
| BRUMO 2025 | 90% | #22 of 42 | Official leaderboard | |
| ForecastBench | 64.4 | #63 of 83 | Epoch AI | |
| ARC-AGI | 33% | #74 of 96 | Epoch AI | |
| CMIMC 2025 | 58.1% | #32 of 33 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench-Hard | 33.1% | #6 of 96 | Official leaderboard | |
| Multi-SWE-bench | 14.2% | #1 of 11 | Official leaderboard | |
| Aider Polyglot | 72.9% | #9 of 54 | Epoch AI | |
| LiveCodeBench v5 | 70.4% | #12 of 44 | Model card | |
| SWE-bench Verified | 63.8% | #99 of 150 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ToolComp | 68.8% | #2 of 32 | Official leaderboard | |
| Galileo Agent Leaderboard | 0.94 | #2 of 31 | Official leaderboard | |
| Step Race | 4 | #9 of 59 | Official leaderboard | |
| VideoGameBench | 0.48% | #1 of 5 | Official leaderboard | |
| BALROG | 43.3% | #11 of 35 | Official leaderboard | |
| LLM Chess | -144 | #87 of 124 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CadEval | 64% | #2 of 15 | Epoch AI | |
| Vending-Bench | $789 | #9 of 9 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMBench-EN v1.1 | 88.5% | #1 of 178 | Official leaderboard | |
| MMStar | 73.6% | #2 of 173 | Official leaderboard | |
| VISTA | 54.6% | #1 of 54 | Official leaderboard | |
| MMMU | 81.7% | #12 of 97 | Model card | |
| GeoBench | 84% | #7 of 48 | Official leaderboard | |
| MATH-Vision (MathVision) | 73.3% | #22 of 105 | Official leaderboard | |
| Vibe-Eval | 69.4% | #2 of 9 | Model card | |
| VPCT | 48% | #8 of 28 | Epoch AI | |
| EnigmaEval | 4.14% | #25 of 41 | Epoch AI |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| InterCode-CTF | 98.7% | #1 of 4 | Model card | |
| Virology Capabilities Test (VCT) | 37.6% | #2 of 7 | Official leaderboard | |
| Hack the Box challenge set (Google DeepMind) | 7.70% | #2 of 4 | Model card | |
| In-house CTF suite (Phuong et al. 2024) | 76.9% | #2 of 4 | Model card | |
| WMDP Chemistry | 75.3% | #3 of 5 | Model card | |
| WMDP Biology | 84.3% | #5 of 7 | Model card | |
| LAB-Bench CloningScenarios | 44.1% | #8 of 11 | Model card | |
| LAB-Bench ProtocolQA | 69% | #11 of 15 | Model card | |
| Cyber key skills benchmark v1 | 33.3% | #3 of 4 | Model card | |
| SecureBio VMQA, single choice | 50.8% | #3 of 4 | Model card | |
| FORTRESS | 54.9% | #56 of 66 | Official leaderboard | |
| GDM Situational Awareness | 18.2% | #7 of 8 | Model card | |
| LAB-Bench SeqQA | 63.9% | #11 of 12 | Model card | |
| GDM Stealth | 20% | #6 of 6 | Model card |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OpenVLM Leaderboard | 80.1 | #1 of 173 | Official leaderboard | |
| LiveBench | 82.3% | #1 of 48 | Epoch AI | |
| CAIS Risk Index | 59.0 | #47 of 65 | Official leaderboard | |
| CAIS Text Capabilities Index | 18.8 | #51 of 66 | 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. 19 of them aren't in the launch post.
Capabilities
- Humanity's Last Exam 18.8
- GPQA Diamond 84
- AIME 2025 86.7
- AIME 2024 92
- LiveCodeBench v5 70.4
- Aider Polyglot 74
- SWE-bench Verified 63.8
- SimpleQA 52.9
- MMMU 81.7
- Vibe-Eval 69.4
- MRCR (Michelangelo, original) 94.5
- Global MMLU Lite 89.8
Safety
Alignment
- GDM Stealth 20
- GDM Situational Awareness 18.2