Model comparison
Claude 3.5 Sonnet vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 34.6 on the Noometry Index.
Last verified . 33 shared benchmarks.
GoogleSummary
- They share 33 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Gemini 3.1 Pro Preview in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 23.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 95.6% for Gemini 3.1 Pro Preview.
Side by side
| Claude 3.5 Sonnet | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 34.6 | 56.7 |
| Released | 2024-06-20 | 2026-02-19 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $12 |
| Results tracked | 60 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 39.0 (#165), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| GSO | 4.6% | 22.6% |
| WeirdML | 40% | 72.1% |
| LMArena Coding | 1342 | 1484 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1447 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| MirrorCode | — | 8.9% |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 1,161 |
| AlgoTune | — | 2.02 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 32.3 (#67), Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| BALROG | 32.6% | 57% |
| METR Time Horizons | 45.2% | 77% |
| Terminal-Bench | — | 80.2% |
| APEX-Agents | — | 35.3% |
| TheAgentCompany | 24% | — |
| τ²-bench Banking | — | 26% |
| Cybench | 17.5% | — |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| GDP.pdf | — | 17% |
| LMArena Search | — | 1211 |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 23.1 (#183), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| SimpleBench | 41.4% | 79.6% |
| EnigmaEval | 0.9% | 36.8% |
| LMArena Hard Prompts | 1305 | 1485 |
| DTBench | 67.8% | 97.1% |
| Epoch Capabilities Index | 133.55 | 154.77 |
| ForecastBench | 60.7 | 59 |
| ARC-AGI-2 | — | 77.1% |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98% |
| CritPt | — | 17.7% |
| Chess Puzzles | — | 55% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 34% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 53.8% |
| LiveBench | 59% | — |
Math Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 19.2 (#288), Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 95.6% |
| LMArena Math | 1307 | 1485 |
| FrontierMath (Feb 2025 set) | 2.1% | 36.9% |
| FrontierMath Tier 4 (v1) | 0% | 16.7% |
| FrontierMath (Tiers 1-3) | — | 59.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 86.5% |
| ProofBench | — | 26% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
Knowledge Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 28.6 (#245), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 55.3% | 94.4% |
| Humanity's Last Exam | 4.1% | 46.4% |
| LMArena Expert | 1265 | 1485 |
| SimpleQA Verified | — | 73.5% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| Vectara Hallucination Rate | — | 10.4% |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 26.5 (#120), Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | 1125 | 1296 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| Blueprint-Bench 2 | — | 26.5% |
| Furniture Assembly | — | 26.7% |
| LMArena Document | — | 1444 |
Multilingual Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 43.2 (#185), Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1283 | 1477 |
| LMArena Chinese | 1272 | 1529 |
| LMArena French | 1305 | 1487 |
| LMArena German | 1297 | 1491 |
| LMArena Japanese | 1234 | 1493 |
| LMArena Korean | 1200 | 1455 |
| LMArena Russian | 1306 | 1498 |
| LMArena Spanish | 1290 | 1479 |
Instruction Following Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 68.8 (#182), Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1297 | 1466 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 39.9 (#167), Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1311 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
Writing & Preference Gemini 3.1 Pro Preview leads
Claude 3.5 Sonnet: 52.9 (#164), Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1298 | 1481 |
| LMArena Creative Writing | 1292 | 1482 |
| EQ-Bench Creative Writing | 1451 | 1491 |
| LMArena Multi-Turn | 1326 | 1488 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| EQ-Bench 4 | — | 1142 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Gemini 3.1 Pro Preview better for coding?
Gemini 3.1 Pro Preview scores higher on coding benchmarks: 42.5 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Gemini 3.1 Pro Preview share?
33 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Gemini 3.1 Pro Preview has 71.