- SWE-Bench Verified (48.9% -> 54%) 54
- Artificial Analysis Intelligence Index (scatter chart, no printed value)
- Humanity's Last Exam (no tools), model card 13.2
- GPQA diamond single attempt, model card 80.8
- AIME 2025 single attempt, model card 75.6
- LiveCodeBench v5 single attempt, model card 71.7
- SimpleQA, model card 25.3
- SimpleQA Verified, model card 27.8
- FACTS Grounding, model card 87.5
- MMMU single attempt, model card 80.3
- Vibe-Eval (Reka), model card 62
- MRCR v2 (8-needle) 128k (average), model card 52.4
- Global MMLU (Lite), model card 87.9
Gemini 2.5 Flash Sep 2025
Gemini 2.5 Flash places in the top three on 4 benchmarks.
Google DeepMind Released 25 Sep 2025 83
Benchmarks with a score
0
Ranked first, out of five or more models
4
In the top three
Google DeepMind Sep 2025 Gemini 2.5 Flash
Sep 2025 snapshot Closed weights
142.9
#106 of 271
Epoch Capabilities Index
- Toolathlon 3.70% #50 /50
- ZeroBench 3.00% #51 /66
- AMO-Bench 18.1% #13 /21
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 | |
|---|---|---|---|---|
| HELM Arabic | 82.5 | #2 of 28 | Official leaderboard | |
| FACTS Grounding | 87.5% | #3 of 15 | Model card | |
| IndicGenBench | 56.9 | #4 of 13 | Official leaderboard | |
| LMArena (Elo) | 1,403 | #124 of 333 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 7.80% | #39 of 104 | Official leaderboard | |
| HELM Arabic Enterprise | 68.2 | #9 of 23 | Official leaderboard | |
| FACTS Multimodal | 41% | #16 of 39 | Official leaderboard | |
| Global MMLU Lite | 91.5% | #19 of 43 | Official leaderboard | |
| SimpleQA | 25.3% | #29 of 59 | Model card | |
| EQ-Bench 3 | 1,178 | #45 of 78 | Official leaderboard | |
| FACTS Benchmark Suite | 41% | #24 of 40 | Official leaderboard | |
| Phare | 63.6% | #41 of 62 | Official leaderboard | |
| Judgemark v2.1 | 63.0 | #30 of 42 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 48.6 | #86 of 119 | Official leaderboard | |
| Creative Writing v3 | 58.7 | #87 of 120 | Official leaderboard | |
| BullshitBench V2 | 19% | #89 of 122 | Official leaderboard | |
| BullshitBench | 14.6% | #84 of 107 | Official leaderboard | |
| MRCR v2 | 52.4% | #22 of 27 | Model card | |
| SimpleQA Verified | 27.8% | #18 of 22 | Model card | |
| Humanity's Last Exam | 13.2% | #123 of 147 | Model card | |
| FACTS Search | 60% | #26 of 31 | Official leaderboard | |
| Slop Score | 77.7 | #16 of 17 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HiPhO | 61.5% | #11 of 35 | Official leaderboard | |
| GPQA Diamond | 80.8% | #107 of 284 | Model card | |
| ForecastBench | 62.5 | #41 of 86 | Official leaderboard | |
| AMO-Bench | 18.1% | #13 of 21 | Official leaderboard | |
| SimpleBench | 41.2% | #66 of 100 | Official leaderboard | |
| HMMT 2025 | 64.2% | #35 of 53 | Official leaderboard | |
| AIME 2025 | 75.6% | #102 of 143 | Model card | |
| miniCTX-v2 | 26.6% | #3 of 4 | Official leaderboard | |
| BRUMO 2025 | 83.3% | #34 of 42 | Official leaderboard | |
| SMT 2025 | 75.5% | #34 of 40 | Official leaderboard | |
| CMIMC 2025 | 54.4% | #33 of 33 | Official leaderboard | |
| General365 | 39.6% | #23 of 23 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v5 | 71.7% | #7 of 44 | Model card | |
| LiveSQLBench | 23.8% | #20 of 36 | Official leaderboard | |
| WeirdML | 41.9% | #70 of 112 | Official leaderboard | |
| SWE-bench Verified | 54% | #120 of 150 | Model card | |
| SWE-fficiency | 4.06% | #14 of 17 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 31 | #30 of 183 | Official leaderboard | |
| BFCL V4 | 56.2% | #12 of 65 | Official leaderboard | |
| ITBench | 51.7% | #6 of 13 | Official leaderboard | |
| GAIA | 58.8% | #27 of 57 | Official leaderboard | |
| MCP-Universe | 21.6% | #23 of 30 | Official leaderboard | |
| MCPMark | 9.06% | #23 of 28 | Official leaderboard | |
| VitaBench 2.0 | 28.2% | #17 of 20 | Official leaderboard | |
| PinchBench | 50.6% | #42 of 48 | Official leaderboard | |
| Terminal-Bench 2.0 | 17.1% | #40 of 43 | Epoch AI | |
| Terminal-Bench | 16.9% | #17 of 18 | Epoch AI | |
| Toolathlon | 3.70% | #50 of 50 | Official leaderboard | |
| CompileBench | 60% | #20 of 20 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| TheAgentCompany | 41.1% | #2 of 14 | Epoch AI | |
| FailureSensorIQ | 65.5% | #9 of 24 | Official leaderboard | |
| TaxEval v2 | 72.7% | #57 of 129 | Official leaderboard | |
| LegalBench | 82.6% | #66 of 138 | Official leaderboard | |
| Vals Finance Agent v1 | 31.2% | #23 of 47 | Official leaderboard | |
| MortgageTax | 62.6% | #50 of 86 | Official leaderboard | |
| CorpFin v2 | 59.8% | #71 of 119 | Official leaderboard | |
| MedScribe | 78.5% | #60 of 98 | Official leaderboard | |
| MedCode | 40.5% | #60 of 96 | Official leaderboard | |
| Vending-Bench 2 | $549 | #55 of 66 | Official leaderboard | |
| Vending-Bench Arena | $281 | #31 of 32 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMMU | 80.3% | #19 of 97 | Model card | |
| MMAU v05.15.25 | 71.8% | #2 of 9 | Official leaderboard | |
| VisualPuzzles | 44.6% | #10 of 29 | Official leaderboard | |
| VPCT | 46.2% | #10 of 28 | Epoch AI | |
| OCR Arena | 1,700 | #5 of 11 | Official leaderboard | |
| Vision Arena | 1,230 | #62 of 136 | Official leaderboard | |
| AHELM | 49.7 | #5 of 10 | Official leaderboard | |
| RoboRewardBench | 0.94 | #11 of 19 | Official leaderboard | |
| Blueprint-Bench | 0.36 | #5 of 8 | Official leaderboard | |
| Vibe-Eval | 62% | #6 of 9 | Model card | |
| ClockBench | 11.1% | #27 of 37 | Official leaderboard | |
| ZeroBench | 3.00% | #51 of 66 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIR-Bench 2024 | 68.7% | #35 of 82 | Official leaderboard | |
| HELM Safety | 91.2 | #39 of 75 | Official leaderboard | |
| KORA | 36.4% | #24 of 42 | Official leaderboard | |
| Anthropic Red Team | 98.8% | #43 of 75 | Official leaderboard | |
| Spiral-Bench v1.0 | 49.1 | #8 of 13 | Official leaderboard | |
| Spiral-Bench v1.2 | 36.5 | #13 of 21 | Official leaderboard | |
| SimpleSafetyTests | 98% | #48 of 75 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SAGE (Vals) | 44.1% | #46 of 81 | Official leaderboard | |
| HELM Capabilities | 62.6 | #37 of 60 | 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 & 2.5 Flash Image Model Card 26 Sep 2025
Capabilities
- Humanity's Last Exam 13.2
- GPQA Diamond 80.8
- AIME 2025 75.6
- LiveCodeBench v5 71.7
- SWE-bench Verified 54
- SimpleQA 25.3
- SimpleQA Verified 27.8
- MMMU 80.3
- Vibe-Eval 62
- MRCR v2 52.4
- Global MMLU Lite 87.9
Hallucination
- FACTS Grounding 87.5