Model comparison
Claude Sonnet 4.6 vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 50.3 on the Noometry Index.
Last verified . 54 shared benchmarks.
GoogleSummary
- They share 54 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 5 categories and Gemini 3.1 Pro Preview in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 46.1.
- The biggest single-benchmark swing is GBAEval: 48.8% for Claude Sonnet 4.6 and 0.8% for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview is cheaper at $2 / $12 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 4.6 | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 50.3 | 56.7 |
| Released | 2026-02-17 | 2026-02-19 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $12 |
| Results tracked | 57 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.3 (#67), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| SWE-bench Verified | 75.2% | 75.6% |
| DeepSWE | 29.9% | 11.7% |
| LMArena WebDev | 1522 | 1447 |
| SciCode | 46.8% | 58.9% |
| WeirdML | 66.1% | 72.1% |
| LMArena Coding | 1504 | 1484 |
| ALE-Bench | 1,327 | 1,161 |
| FrontierCode | 24.3% | — |
| GSO | — | 22.6% |
| MirrorCode | — | 8.9% |
| AlgoTune | — | 2.02 |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 39.1 (#28), Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| Terminal-Bench | 53.4% | 80.2% |
| APEX-Agents | 43% | 35.3% |
| DeepResearch Bench | 54.9% | 47.8% |
| ExploitBench | 23.6% | 26.1% |
| GBAEval | 48.8% | 0.8% |
| GDP.pdf | 18% | 17% |
| LMArena Search | 1221 | 1211 |
| Vending-Bench 2 | 7,204 | 3,774 |
| OSWorld 2.0 | 9.3% | — |
| τ²-bench Banking | — | 26% |
| OSWorld | 72.1% | — |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| METR Time Horizons | — | 77% |
Reasoning Gemini 3.1 Pro Preview leads
Claude Sonnet 4.6: 46.1 (#45), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| ARC-AGI-2 | 60.4% | 77.1% |
| NYT Connections (extended) | 80.9% | 97.4% |
| ARC-AGI-1 | 86.5% | 98% |
| CritPt | 3.1% | 17.7% |
| Chess Puzzles | 13% | 55% |
| Thematic Generalization | 76.3% | 79.4% |
| LMArena Hard Prompts | 1484 | 1485 |
| Mystery Game Puzzles | 16% | 34% |
| DTBench | 89.9% | 97.1% |
| LMCA | 46.5% | 53.8% |
| Epoch Capabilities Index | 152.24 | 154.77 |
| ForecastBench | 62 | 59 |
| SimpleBench | — | 79.6% |
| EnigmaEval | — | 36.8% |
| EBR-Bench | — | 14.3% |
Math Gemini 3.1 Pro Preview leads
Claude Sonnet 4.6: 52.9 (#49), Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | 95.6% |
| ProofBench | 45% | 26% |
| LMArena Math | 1462 | 1485 |
| FrontierMath (Feb 2025 set) | 32.4% | 36.9% |
| FrontierMath Tier 4 (v1) | 8.3% | 16.7% |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
Knowledge Gemini 3.1 Pro Preview leads
Claude Sonnet 4.6: 51.7 (#65), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 87.4% | 94.4% |
| SimpleQA Verified | 35.5% | 73.5% |
| Vectara Hallucination Rate | 10.6% | 10.4% |
| LMArena Expert | 1500 | 1485 |
| Humanity's Last Exam | — | 46.4% |
Multimodal Too close to call
Claude Sonnet 4.6: 38.0 (#68), Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | 1283 | 1296 |
| Blueprint-Bench 2 | 6.7% | 26.5% |
| LMArena Document | 1482 | 1444 |
| Furniture Assembly | — | 26.7% |
Multilingual Gemini 3.1 Pro Preview leads
Claude Sonnet 4.6: 54.4 (#41), Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1440 | 1477 |
| LMArena Chinese | 1491 | 1529 |
| LMArena French | 1465 | 1487 |
| LMArena German | 1428 | 1491 |
| LMArena Japanese | 1420 | 1493 |
| LMArena Korean | 1411 | 1455 |
| LMArena Russian | 1440 | 1498 |
| LMArena Spanish | 1464 | 1479 |
Instruction Following Too close to call
Claude Sonnet 4.6: 77.4 (#25), Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1475 | 1466 |
Long Context Gemini 3.1 Pro Preview leads
Claude Sonnet 4.6: 45.3 (#44), Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1479 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.2 (#22), Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | Claude Sonnet 4.6 | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1458 | 1481 |
| LMArena Creative Writing | 1435 | 1482 |
| EQ-Bench Creative Writing | 1810 | 1491 |
| EQ-Bench 4 | 1207 | 1142 |
| LMArena Multi-Turn | 1464 | 1488 |
Frequently asked questions
Is Claude Sonnet 4.6 better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 50.3 on the Noometry Index.
Which is cheaper, Claude Sonnet 4.6 or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Gemini 3.1 Pro Preview better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 42.5 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 4.6 and Gemini 3.1 Pro Preview share?
54 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Gemini 3.1 Pro Preview has 71.