Claude Sonnet 5.5 vs Gemini 3 Pro
Claude Sonnet 5.5 
Gemini 3 Pro Verdict
- Claude Sonnet 5.5 (max) leads on quality: 67.6 vs 60.6.
- Claude Sonnet 5.5 (max) is stronger in agents & tools, coding, composite, knowledge, long context, maths, reasoning.
- Gemini 3 Pro is stronger in human preference, instruction following, multimodal.
| Metric | Claude Sonnet 5.5 (max) | Gemini 3 Pro |
|---|---|---|
| BenchLeader Index | 67.6 | 60.6 |
| Agents & tools score | 69.5 | 61.8 |
| Coding score | 69.8 | 57.9 |
| Composite score | 72.6 | – |
| Knowledge score | 65.4 | 56.4 |
| Long context score | 66.6 | – |
| Maths score | 72.9 | 54.4 |
| Reasoning score | 81.1 | 65.8 |
| Human preference score | – | 68.3 |
| Instruction following score | – | 61.0 |
| Multimodal score | – | 65.6 |
| Blended price $/M | $4.00 | – |
| Output speed | 141 tok/s | – |
| Time to first answer | 487.1 s | – |
| Context window | 1M | – |
| GPQA Diamond | 95.6% | 92.6% |
| FrontierMath Tiers 1–3 | 88.8% | – |
| FrontierMath Tier 4 | 80.5% | – |
| OTIS Mock AIME | 100.0% | 91.4% |
| SWE-bench Verified (Epoch) | – | 72.9% |
| SimpleQA Verified | 46.5% | – |
| Humanity's Last Exam | – | 37.5% |
| Terminal-Bench | 61.8% | 69.4% |
| SimpleBench | – | 76.4% |
| GDPval | – | 40.3% |
| SciCode | 61.0% | – |
| Remote Labor Index | – | 1.3% |
| WeirdML | – | 69.9% |
| APEX-Agents | 75.5% | – |
| ProofBench | 100.0% | 20.0% |
| GSO-Bench | – | 18.6% |
| Epoch Capabilities Index | – | 152.9 |
| LMArena Text | – | 1486 |
| LMArena Hard Prompts | – | 1502 |
| LMArena Coding | – | 1517 |
| LMArena WebDev | – | 1440 |
| LMArena Vision | – | 1305 |
| LMArena Agent | 12 | – |
| LiveBench | 75.7% | – |
| LiveBench Reasoning | 91.6% | – |
| LiveBench Coding | 91.4% | – |
| LiveBench Agentic Coding | 56.3% | – |
| LiveBench Mathematics | 96.1% | – |
| LiveBench Data Analysis | 59.5% | – |
| LiveBench Language | 78.0% | – |
| LiveBench Instruction Following | 56.8% | – |
| AA Intelligence Index v4.3.2 | 56 | – |
| AA-LCR | 82.7% | – |
| AA-Omniscience | 32.3 | – |
| Humanity's Last Exam (AA) | 55.0% | – |
| SciCode (AA) | 61.0% | – |
| LiveCodeBench | – | 86.4% |
| MMLU-Pro | – | 90.1% |
| AIME 2026 | – | 91.7% |
| HMMT February 2026 | – | 86.4% |
| MathArena Apex | – | 23.4% |
| SWE-Bench Pro | – | 43.3% |
| MCP Atlas | – | 70.3% |
| MultiChallenge | – | 65.7% |
| PRBench Finance | – | 39.2% |
| PRBench Legal | – | 40.6% |
| VISTA | – | 51.5% |
| MultiNRC | – | 59.0% |
| TutorBench | – | 53.7% |
| MMMU-Pro (official) | – | 81.0% |
| Kagi LLM Benchmark | – | 80.1% |
| IFEval (HELM) | – | 87.6% |
| Omni-MATH (HELM) | – | 55.6% |
| WildBench (HELM) | – | 85.9% |
| MMLU-Pro (HELM) | – | 90.3% |
| GPQA Diamond (HELM) | – | 80.3% |
| HELM Capabilities mean | – | 79.9% |
| SWE-bench Verified (bash only) | – | 74.2% |
| SWE-bench Verified (any scaffold) | – | 74.2% |
| ARC-AGI-1 | – | 75.0% |
| ARC-AGI-2 | – | 54.0% |
| BFCL Overall | – | 72.5% |
| CritPt | 31.4% | – |
| GDPval-AA v2.1 | 67.0% | – |
| Analyst Agent (AA) | 57.5% | – |
| Poker Agent | – | 1078.9% |
| FORTRESS | – | 41.7% |
| MASK | – | 42.6% |
| PropensityBench | – | 52.9% |
| SciPredict | – | 25.3% |
| SWE-Bench Pro (private) | – | 43.3% |
| LMArena Maths | – | 1477 |
| LMArena Creative Writing | – | 1485 |
| LMArena Instruction Following | – | 1473 |
| LMArena Multi-turn | – | 1496 |
| LMArena Longer Queries | – | 1491 |
| LMArena Document | – | 1451 |
| Chess Puzzles | – | 31.0% |
| Mystery Game Puzzles | 65.0% | – |
| BALROG | – | 58.1% |
| GeoBench | – | 84.0% |
| VPCT | – | 91.0% |
| CL-bench | – | 15.8% |
| METR Time Horizons | – | 71.0% |
| ForecastBench | – | 61.2% |
| CursorBench | 55.5% | – |
| ALE-Bench | – | 1176.8 |
| AlgoTune | – | 1.8 |
| Vending-Bench 2 | – | 5478.2 |
| FrontierSWE | 61.9% | – |
| Terminal-Bench 4.0 (AA) | 63.6% | – |
| AutomationBench | 71.8% | – |
| GDP.pdf | 25.8% | – |
| MLCR | 75.0% | – |
| Harvey LAB | 2.8% | – |
| AA-Omniscience: accuracy | 54.0% | – |
| AA-Omniscience: non-hallucination | 53.0% | – |
| AA-Briefcase v1.1 | 1823 | – |
Data as of 2026-10-11. Best configuration of each model; every score links to its source on the model pages.
Claude Sonnet 5.5 vs Gemini 3 Pro: questions
- Is Claude Sonnet 5.5 better than Gemini 3 Pro?
- Claude Sonnet 5.5 (max) leads on quality: 67.6 vs 60.6. The BenchLeader Index combines every independent quality benchmark; Claude Sonnet 5.5 (max) is ahead overall as of 2026-10-11, but check the category scores for your use.
- Is Claude Sonnet 5.5 better than Gemini 3 Pro for coding?
- Claude Sonnet 5.5 scores higher in coding (70 vs 58 on the category index, where 50 is average).
- Is Claude Sonnet 5.5 better than Gemini 3 Pro for agentic tasks?
- Claude Sonnet 5.5 scores higher in agentic tasks (70 vs 62 on the category index, where 50 is average).