Up to four models
Gemini 3.5 Flash-Lite vs Claude Opus 4.1
On the index (GPT-4 = 100), Gemini 3.5 Flash-Lite scores 141 and Claude Opus 4.1 140. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
141125–156
WeightsClosed
ReleasedJul 2026
Price in / out$0.30 / $2.5
Context1.05M
Core tests taken5 of 9
Claude Opus 4.1
140124–156
WeightsClosed
ReleasedAug 2025
Price in / out$15 / $75
Context200K
Core tests taken5 of 9
Gemini 3.5 Flash-Lite and Claude Opus 4.1 are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests, and costs 35× less.
Test by testthird-party results
Every result as a table
| Test | Gemini 3.5 Flash-Lite | Claude Opus 4.1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 83.3% | 77.3% |
| GPQA Diamond (Vals AI) | 83.8% | 76.3% |
| MMLU Pro | 85.8% | 87.9% |
| MMMU Pro | 83.6% | 77.5% |
| Maths | ||
| FrontierMath (tiers 1-3) | 26.0% | 12.6% |
| AIME-style maths (OTIS mock) | 71.1% | 68.9% |
| FrontierMath (tier 4) | 0.0% | 2.4% |
| Coding | ||
| LiveCodeBench | 79.0% | 66.5% |
| WeirdML | 39.0% | 45.9% |
| Agents | ||
| DTBench | 83.5% | 80.0% |
| LMCA | 37.6% | 37.1% |
| Mystery game puzzles | 19.0% | 21.0% |
| Professional work | ||
| LegalBench | 84.1% | 83.5% |
| MedCode | 43.5% | 47.2% |
| MedScribe | 70.9% | 73.9% |
| MortgageTax | 68.7% | 61.1% |
| TaxEval v2 | 72.6% | 73.7% |
Task length · METR40 sec
Tests at least two of these models have taken. Bold rows are the core tests.