Claude Sonnet 5 vs Gemini 3.6 Flash
Claude Sonnet 5 
Gemini 3.6 Flash Verdict
- Claude Sonnet 5 (high) and Gemini 3.6 Flash are level on quality (61.4 vs 60.8).
- Claude Sonnet 5 (high) is stronger in agents & tools, coding, human preference, reasoning.
- Gemini 3.6 Flash is stronger in composite, knowledge, long context, multimodal, maths.
- Gemini 3.6 Flash is 2.7× cheaper ($1.50 vs $4.00 per 1M blended).
- Gemini 3.6 Flash streams 3.3× faster (194 vs 60 tokens per second).
| Metric | Claude Sonnet 5 (high) | Gemini 3.6 Flash |
|---|---|---|
| BenchLeader Index | 61.4 | 60.8 |
| Agents & tools score | 61.8 | – |
| Coding score | 61.6 | 49.8 |
| Composite score | 69.5 | 72.4 |
| Human preference score | 66.2 | – |
| Knowledge score | 62.4 | 74.7 |
| Long context score | 64.8 | 66.6 |
| Multimodal score | 63.1 | 67.8 |
| Reasoning score | 66.8 | – |
| Maths score | – | 54.8 |
| Blended price $/M | $4.00 | $1.50 |
| Output speed | 60 tok/s | 194 tok/s |
| Time to first answer | 10.0 s | 16.8 s |
| Context window | 1M | 1.0M |
| SciCode | 48.6% | – |
| WeirdML | 68.8% | – |
| FrontierCode | – | 34.4% |
| ProofBench | – | 36.0% |
| Epoch Capabilities Index | – | 154.3 |
| LMArena Text | 1462 | – |
| LMArena Hard Prompts | 1490 | – |
| LMArena Coding | 1521 | – |
| LMArena WebDev | 1538 | – |
| LMArena Vision | 1278 | – |
| LMArena Agent | 6.3 | – |
| AA Intelligence Index | 32.0 | 34.3 |
| AA-LCR | 76.7% | 80.0% |
| MMMU-Pro | – | 83.2% |
| AA-Omniscience | -3.7 | 22.1 |
| GPQA Diamond (AA) | – | 92.8% |
| Humanity's Last Exam (AA) | 35.7% | 40.8% |
| SciCode (AA) | 54.3% | 53.4% |
| AIME 2026 | – | 96.7% |
| HMMT February 2026 | – | 89.4% |
| MathArena Apex | – | 26.0% |
Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.
Claude Sonnet 5 vs Gemini 3.6 Flash: questions
- Is Claude Sonnet 5 better than Gemini 3.6 Flash?
- Claude Sonnet 5 (high) and Gemini 3.6 Flash are level on quality (61.4 vs 60.8). The BenchLeader Index combines every independent quality benchmark; Claude Sonnet 5 (high) is ahead overall as of 2026-09-10, but check the category scores for your use.
- Is Claude Sonnet 5 better than Gemini 3.6 Flash for coding?
- Claude Sonnet 5 scores higher in coding (62 vs 50 on the category index, where 50 is average).
- Which is cheaper, Claude Sonnet 5 or Gemini 3.6 Flash?
- Gemini 3.6 Flash is cheaper: $1.50 against $4.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Sonnet 5 or Gemini 3.6 Flash?
- Gemini 3.6 Flash streams faster: 194 against 60 output tokens per second.
- Which has the larger context window?
- Gemini 3.6 Flash accepts more context: 1.0M against 1M tokens.