Model comparison
Claude Sonnet 5.5 vs Gemini 3.1 Pro Preview
Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 56.7 on the Noometry Index.
Last verified . 13 shared benchmarks.
GoogleSummary
- They share 13 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 4 categories and Gemini 3.1 Pro Preview in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 88.7 to 61.8.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Sonnet 5.5 and 26% for Gemini 3.1 Pro Preview.
- Claude Sonnet 5.5 is cheaper at $2 / $10 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 5.5 | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 60.5 | 56.7 |
| Released | 2026-09-28 | 2026-02-19 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $2 |
| Output $ / M tokens | $10 | $12 |
| Results tracked | 16 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 65.5 (#6), Gemini 3.1 Pro Preview: 42.7 (#88)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena WebDev | 1699 | 1446 |
| SciCode | 61% | 58.9% |
| ALE-Bench | 1,819 | 1,161 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| FrontierCode | 52.1% | — |
| CursorBench | 55.5% | — |
| FrontierSWE | 61.9% | — |
| GSO | — | 22.6% |
| WeirdML | — | 72.1% |
| LMArena Coding | — | 1483 |
| MirrorCode | — | 8.9% |
| AlgoTune | — | 2.02 |
Agentic & Tool Use Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 44.9 (#14), Gemini 3.1 Pro Preview: 37.7 (#33)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| APEX-Agents | 75.5% | 35.3% |
| Terminal-Bench | — | 80.2% |
| τ²-bench Banking | — | 26% |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
Claude Sonnet 5.5: 52.4 (#29), Gemini 3.1 Pro Preview: 71.7 (#9)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| CritPt | 31.4% | 17.7% |
| Mystery Game Puzzles | 65% | 34% |
| ARC-AGI-2 | — | 77.1% |
| SimpleBench | — | 79.6% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| Chess Puzzles | — | 55% |
| EnigmaEval | — | 36.8% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| LMArena Hard Prompts | — | 1484 |
| DTBench | — | 97.1% |
| LMCA | — | 53.8% |
| Epoch Capabilities Index | — | 154.92 |
| ForecastBench | — | 59 |
Math Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 88.7 (#4), Gemini 3.1 Pro Preview: 61.8 (#28)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 88.8% | 59.6% |
| FrontierMath Tier 4 | 80.5% | 26.8% |
| OTIS Mock AIME 2024-2025 | 100% | 95.6% |
| ProofBench | 100% | 26% |
| MathArena Final-Answer Competitions | — | 86.5% |
| LMArena Math | — | 1485 |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |
Knowledge Gemini 3.1 Pro Preview leads
Claude Sonnet 5.5: 66.0 (#11), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 95.6% | 94.4% |
| SimpleQA Verified | 46.5% | 73.5% |
| Humanity's Last Exam | — | 46.4% |
| Vectara Hallucination Rate | — | 10.4% |
| LMArena Expert | — | 1484 |
Multimodal Claude Sonnet 5.5 leads
Claude Sonnet 5.5: 53.2 (#5), Gemini 3.1 Pro Preview: 38.1 (#60)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| Furniture Assembly | 75% | 26.7% |
| LMArena Vision | — | 1296 |
| Blueprint-Bench 2 | — | 26.5% |
| LMArena Document | — | 1444 |
Multilingual Not comparable
Claude Sonnet 5.5: —, Gemini 3.1 Pro Preview: 57.1 (#11)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | — | 1475 |
| LMArena Chinese | — | 1528 |
| LMArena French | — | 1488 |
| LMArena German | — | 1491 |
| LMArena Japanese | — | 1494 |
| LMArena Korean | — | 1458 |
| LMArena Russian | — | 1496 |
| LMArena Spanish | — | 1480 |
Instruction Following Not comparable
Claude Sonnet 5.5: —, Gemini 3.1 Pro Preview: 77.1 (#31)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | — | 1465 |
Long Context Not comparable
Claude Sonnet 5.5: —, Gemini 3.1 Pro Preview: 47.3 (#17)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
| LMArena Longer Query | — | 1482 |
Writing & Preference Not comparable
Claude Sonnet 5.5: —, Gemini 3.1 Pro Preview: 66.3 (#36)
| Benchmark | Claude Sonnet 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | — | 1480 |
| LMArena Creative Writing | — | 1482 |
| EQ-Bench Creative Writing | — | 1491 |
| EQ-Bench 4 | — | 1142 |
| LMArena Multi-Turn | — | 1486 |
Frequently asked questions
Is Claude Sonnet 5.5 better than Gemini 3.1 Pro Preview?
Claude Sonnet 5.5 is the stronger model overall, scoring 60.5 to 56.7 on the Noometry Index.
Which is cheaper, Claude Sonnet 5.5 or Gemini 3.1 Pro Preview?
Claude Sonnet 5.5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.
Is Claude Sonnet 5.5 or Gemini 3.1 Pro Preview better for coding?
Claude Sonnet 5.5 scores higher on coding benchmarks: 65.5 versus 42.7 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Pro Preview does, with 1.05M tokens against 1M.
How many benchmarks do Claude Sonnet 5.5 and Gemini 3.1 Pro Preview share?
13 benchmarks have published results for both models. Claude Sonnet 5.5 has 16 scored results on Noometry and Gemini 3.1 Pro Preview has 71.