Compare / Claude Sonnet 5.5 vs Gemini 3.5 Flash
Claude Sonnet 5.5 vs Gemini 3.5 Flash
12 results from 4 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Sonnet 5.5 | Gemini 3.5 Flash |
|---|---|---|---|
| BulletBenchmeasured by us | Cost per gameUS dollars | $0.0080 | $0.0213 |
| BulletBenchmeasured by us | Games lost on time% of games | 91.7% | 33.3% |
| BulletBenchmeasured by us | Invalid moves% of moves | 0.0% | 0.6% |
| BulletBenchmeasured by us | Ladder Eloladder Elo | 33 | 727 |
| BulletBenchmeasured by us | Median move timemilliseconds | 2.1 s | 1.2 s |
| APEX-Agentsreported | Tasks passed% of tasks | 75.5% | 27.5% |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 56.0 | 33.6 |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 55.0% | 42.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 82.7% | 74.3% |
| Artificial Analysisreported | SciCode% of problems | 61.0% | 53.9% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 63.6% | 6.6% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 46.5% | 66.2% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.