Gemini 3.1 Flash Lite Preview
Gemini / Google
49scores
46benchmarks
$0.25 / $1.5 per 1M tokenscost in/out
Metadata
Gemini Closed/API
Aliases: gemini-3.1-flash-lite-preview, gemini-3.1-flash-lite-preview-20260303, google-gemini-3.1-flash-lite-preview, google-gemini-3.1-flash-lite-preview-20260303, google/gemini-3.1-flash-lite-preview, google/gemini-3.1-flash-lite-preview-20260303
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| APEX-Agents-AA | Agentic | 13 | 12.2% | 2026-05-11 |
| AutoBench | Agentic | 19 | 2.82 | 2026-05-06 |
| Gert Labs Rankings | Agentic | 48 | 0.37 | 2026-05-11 |
| MultiChallenge | Agentic | 7 | 60.61 | 2026-05-06 |
| Tau2-Bench Telecom | Agentic | 236 | 31.3% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 124 | 24.2% | 2026-05-11 |
| Arena AI Code | Coding | 62 | 1240 | 2026-05-06 |
| LiveCodeBench | Coding | 44 | 80.116% | 2026-05-28 |
| SciCode | Coding | 71 | 41.9% | 2026-05-11 |
| SWE-bench Verified | Coding | 40 | 62.8% | 2026-05-28 |
| Terminal-Bench 2.0 | Coding | 51 | 24.719% | 2026-05-28 |
| Vibe Code Bench v1.1 | Coding | 45 | 0% | 2026-05-28 |
| SAGE | Education | 12 | 49.54% | 2026-05-28 |
| TutorBench | Education | 9 | 51.50 | 2026-05-06 |
| Vectara HHEM Hallucination Leaderboard | Factuality | 39 | 91.80 | 2026-05-06 |
| CorpFin v2 | Finance | 56 | 59.363% | 2026-05-28 |
| Finance Agent v1.1 | Finance | 33 | 46.123% | 2026-05-04 |
| Finance Agent v2 | Finance | 18 | 29.988% | 2026-05-28 |
| MortgageTax | Finance | 14 | 68.044% | 2026-05-28 |
| TaxEval v2 | Finance | 49 | 71.79% | 2026-05-28 |
| MedCode | Healthcare | 16 | 47.602% | 2026-05-28 |
| MedScribe | Healthcare | 56 | 63.902% | 2026-05-28 |
| Artificial Analysis Intelligence Index | Intelligence | 119 | 33.52 | 2026-05-11 |
| GPQA Diamond | Intelligence | 37 | 81.06% | 2026-05-28 |
| Humanity's Last Exam | Intelligence | 89 | 16.2% | 2026-05-11 |
| MMLU Pro | Intelligence | 26 | 86.24% | 2026-05-28 |
| MMMU Pro | Intelligence | 20 | 82.486% | 2026-05-28 |
| Vals Index | Intelligence | 19 | 35.236% | 2026-05-28 |
| Vals Multimodal Index | Intelligence | 14 | 40.466% | 2026-05-28 |
| CaseLaw v2 | Legal | 36 | 54.984% | 2026-05-04 |
| LegalBench | Legal | 24 | 83.764% | 2026-05-28 |
| MRCR v2 (8-needle) | Long Context | 3 | 0.60 | 2026-05-06 |
| AIME | Math | 43 | 83.333% | 2026-04-16 |
| CharXiv-R | Multimodal | 18 | 0.73 | 2026-05-06 |
| Design Arena | Multimodal | 87 | 1134 | 2026-05-06 |
| VideoMMMU | Multimodal | 5 | 0.85 | 2026-05-06 |
| Visual-Language Understanding | Multimodal | 9 | 46.93 | 2026-05-06 |
| CAIS Text Capabilities Index | Reasoning | 30 | 15.8 | 2026-05-27 |
| Context Arena | Reasoning | 38 | 34.90 | 2026-05-06 |
| Context Arena | Reasoning | 42 | 31.82 | 2026-05-06 |
| Context Arena | Reasoning | 53 | 26.94 | 2026-05-06 |
| Context Arena | Reasoning | 65 | 18.23 | 2026-05-06 |
| EnigmaEval | Reasoning | 23 | 3.04 | 2026-05-06 |
| GPQA Diamond | Reasoning | 85 | 82.2% | 2026-05-11 |
| Humanity's Last Exam (Text Only) | Reasoning | 33 | 8.02 | 2026-05-06 |
| MultiNRC | Reasoning | 21 | 25.02 | 2026-05-06 |
| CAIS Risk Index | Safety | 34 | 61.7 | 2026-05-27 |
| CritPt | Science | 80 | 1.1% | 2026-05-11 |
| CAIS Vision Capabilities Index | Vision | 24 | 44.8 | 2026-05-27 |
No matching rows.