Gemini 3.5 Flash-Lite.
Google DeepMind Jul 2026 Closed weights Small
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.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,456 | #56 of 333 | Official leaderboard | |
| BullshitBench V2 | 66% | #23 of 122 | Official leaderboard | |
| BullshitBench | 52.7% | #27 of 107 | Official leaderboard | |
| Creative Writing v3 | 72.3 | #42 of 120 | Official leaderboard | |
| FACTS Benchmark Suite | 47.4% | #18 of 40 | Official leaderboard | |
| SimpleQA Verified | 33.1% | #27 of 56 | Official leaderboard | |
| FACTS Parametric | 43.4% | #23 of 45 | Official leaderboard | |
| Global MMLU Lite | 89.5% | #22 of 43 | Official leaderboard | |
| MRCR v2 | 72.2% | #15 of 27 | Model card | |
| Extended NYT Connections | 60.4% | #59 of 97 | Official leaderboard | |
| FACTS Multimodal | 35.8% | #26 of 39 | Official leaderboard | |
| FACTS Parametric V2 | 43% | #16 of 20 | Official leaderboard | |
| FACTS Search V2 | 63.4% | #20 of 21 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 83.3% | #80 of 219 | Epoch AI | |
| DTBench | 72.5% | #73 of 178 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 71.1% | #99 of 202 | Epoch AI | |
| ARC-AGI-2 | 10.3% | #56 of 95 | Official leaderboard | |
| ProofBench | 13% | #40 of 59 | Official leaderboard | |
| ARC-AGI | 53.5% | #63 of 92 | Official leaderboard | |
| FrontierMath Tiers 1-3 v2 | 26% | #72 of 89 | Epoch AI | |
| Human Behavior Bench | 75.9 | #9 of 11 | Official leaderboard | |
| CritPt | 0% | #159 of 160 | Epoch AI | |
| FrontierMath Tier 4 v2 | 0% | #71 of 71 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| IOI (Vals) | 26.2% | #18 of 55 | Official leaderboard | |
| MLE-bench | 39.2% | #6 of 18 | Model card | |
| WebDev Arena | 1,447 | #55 of 105 | Epoch AI | |
| Code Arena | 1,434 | #74 of 124 | Official leaderboard | |
| Vibe Code Bench | 37.2% | #70 of 115 | Official leaderboard | |
| ALE-Bench | 765 | #76 of 121 | Epoch AI | |
| SWE-Bench Pro | 54.2% | #53 of 77 | Model card | |
| WeirdML | 39% | #83 of 112 | Official leaderboard | |
| Image-to-WebDev Arena | 1,448 | #43 of 55 | Official leaderboard | |
| AndroidBench | 50.6% | #28 of 32 | Official leaderboard | |
| Code Migration | 6.15% | #70 of 78 | Official leaderboard | |
| SWE-sweep | 0.10% | #10 of 10 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OSWorld-Verified | 74% | #17 of 37 | Model card | |
| Toolathlon-Verified | 57.1% | #15 of 25 | Official leaderboard | |
| Mystery Game Puzzles | 19% | #50 of 80 | Epoch AI | |
| Chess Puzzles | 21% | #61 of 83 | Epoch AI | |
| Terminal-Bench 2.1 | 54% | #46 of 53 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MortgageTax | 68.7% | #14 of 86 | Official leaderboard | |
| LegalBench | 84.1% | #41 of 138 | Official leaderboard | |
| ProfBench | 51.6% | #26 of 72 | Official leaderboard | |
| MedCode | 43.5% | #42 of 96 | Official leaderboard | |
| TaxEval v2 | 72.6% | #59 of 129 | Official leaderboard | |
| CorpFin v2 | 60.7% | #65 of 119 | Official leaderboard | |
| PolicyBench | 81.5% | #29 of 50 | Official leaderboard | |
| Vals Finance Agent v2 | 47.4% | #53 of 80 | Official leaderboard | |
| Excel Modeling Benchmark | 43.2% | #60 of 76 | Official leaderboard | |
| Legal Research Bench | 13.9% | #75 of 88 | Official leaderboard | |
| MedScribe | 70.9% | #84 of 98 | Official leaderboard | |
| Public Benefits Bench | 51.8% | #44 of 50 | Official leaderboard | |
| GDPval-AA v2 | 1,140 | #23 of 26 | Model card | |
| Tax Agent Bench | 7.25% | #70 of 79 | Official leaderboard | |
| APEX-Agents | 29.3% | #51 of 56 | Epoch AI | |
| Harvey LAB (Legal Agent Benchmark) | 0% | #77 of 80 | Official leaderboard | |
| Immigration Bench | 55.7% | #24 of 24 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vision Arena | 1,267 | #31 of 136 | Official leaderboard | |
| ZeroBench | 14% | #22 of 66 | Official leaderboard | |
| 1H-VideoQA | 75.3% | #10 of 20 | Official leaderboard | |
| CharXiv | 76.5% | #43 of 67 | Model card | |
| ParseBench | 59.7% | #27 of 42 | Official leaderboard | |
| GDP.pdf | 10% | #37 of 39 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CyberBench (Vals) | 72.3% | #11 of 26 | Official leaderboard | |
| CyberBench v1.1 (Vals) | 59.1% | #33 of 43 | Official leaderboard | |
| DeepsecBench | 2.13 | #28 of 28 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ACCoRD | 68.0 | #57 of 150 | Official leaderboard | |
| SAGE (Vals) | 47.3% | #32 of 81 | Official leaderboard | |
| LMCA | 37.6% | #59 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 50.7 | #66 of 149 | Official leaderboard | |
| SAGE v1.1 (Vals) | 79.5% | #25 of 28 | Official leaderboard |
Google DeepMind's models in color, against every other model on the Epoch Capabilities Index, by release date.
The benchmarks the lab chose to headline, with the scores it gave.
Every result in the longer documents the lab published with it. 5 of them aren't in the launch post.