Model comparison
Claude 3.7 Sonnet vs Gemini 3 Flash Preview
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 39.5 on the Noometry Index.
Last verified . 32 shared benchmarks.
GoogleSummary
- They share 32 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Gemini 3 Flash Preview in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 18.6.
- The biggest single-benchmark swing is ARC-AGI-1: 28.6% for Claude 3.7 Sonnet and 84.7% for Gemini 3 Flash Preview.
Side by side
| Claude 3.7 Sonnet | Gemini 3 Flash Preview | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.5 | 52.3 |
| Released | 2025-02-24 | 2025-12-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $3 |
| Results tracked | 58 | 59 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 40.6 (#136), Gemini 3 Flash Preview: 50.9 (#42)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| SWE-bench Verified | 61% | 75.4% |
| SWE-bench Verified (bash only) | 52.8% | 75.8% |
| GSO | 3.8% | 9.8% |
| LMArena Coding | 1361 | 1460 |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1439 |
| SWE-bench Multilingual | — | 72.7% |
| WeirdML | — | 61.6% |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,367 |
Agentic & Tool Use Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 34.1 (#50), Gemini 3 Flash Preview: 38.7 (#29)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| DeepResearch Bench | 43.6% | 49.8% |
| Terminal-Bench | — | 64.3% |
| TheAgentCompany | 30.9% | — |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 27.3% |
| τ²-bench Retail | — | 76.8% |
| τ²-bench Telecom | — | 91.2% |
| Cybench | 20% | — |
| OSWorld | 35.8% | — |
| BALROG | — | 48.1% |
| GDP.pdf | — | 10% |
| LMArena Search | — | 1198 |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 3,635 |
Reasoning Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 18.6 (#277), Gemini 3 Flash Preview: 49.2 (#37)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| ARC-AGI-2 | 0.9% | 33.6% |
| SimpleBench | 46.4% | 61.1% |
| ARC-AGI-1 | 28.6% | 84.7% |
| LMArena Hard Prompts | 1333 | 1465 |
| Epoch Capabilities Index | 141.16 | 151.8 |
| ForecastBench | 61.8 | 58.5 |
| NYT Connections (extended) | — | 83.1% |
| Chess Puzzles | — | 40% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 89.1% |
| LiveBench Data Analysis | 74% | — |
| LMCA | — | 43.1% |
| LiveBench | 76.1% | — |
Math Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 37.5 (#153), Gemini 3 Flash Preview: 51.7 (#55)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | 95.6% |
| LMArena Math | 1337 | 1473 |
| FrontierMath (Feb 2025 set) | 4.1% | 35.6% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 17.1% |
| MathArena Final-Answer Competitions | — | 67.6% |
| ProofBench | — | 15% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 39.8 (#130), Gemini 3 Flash Preview: 58.8 (#33)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| GPQA Diamond | 79.7% | 89.4% |
| LMArena Expert | 1321 | 1462 |
| Humanity's Last Exam | 8% | — |
| SimpleQA Verified | — | 66.8% |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| Vectara Hallucination Rate | — | 13.5% |
| GPQA (HELM) | 60.8% | — |
Multimodal Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 33.7 (#95), Gemini 3 Flash Preview: 45.5 (#16)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Vision | 1169 | 1285 |
| GeoBench | 68% | 88% |
| VPCT | 39% | 72.6% |
| Blueprint-Bench 2 | — | 0% |
| LMArena Document | — | 1413 |
| SpatialViz-Bench | 33.9% | — |
Multilingual Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 44.1 (#179), Gemini 3 Flash Preview: 55.7 (#27)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Non-English | 1296 | 1458 |
| LMArena Chinese | 1299 | 1511 |
| LMArena French | 1303 | 1477 |
| LMArena German | 1301 | 1497 |
| LMArena Japanese | 1267 | 1489 |
| LMArena Korean | 1249 | 1443 |
| LMArena Russian | 1311 | 1480 |
| LMArena Spanish | 1298 | 1469 |
Instruction Following Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 72.9 (#125), Gemini 3 Flash Preview: 75.7 (#56)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Instruction Following | 1352 | 1437 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Gemini 3 Flash Preview: 44.4 (#67)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Longer Query | 1373 | 1452 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Gemini 3 Flash Preview leads
Claude 3.7 Sonnet: 54.4 (#150), Gemini 3 Flash Preview: 65.5 (#45)
| Benchmark | Claude 3.7 Sonnet | Gemini 3 Flash Preview |
|---|---|---|
| LMArena Text | 1314 | 1466 |
| LMArena Creative Writing | 1332 | 1457 |
| LMArena Multi-Turn | 1339 | 1471 |
| Short-Story Creative Writing | 81.1% | — |
| EQ-Bench Creative Writing | 1412 | — |
| WildBench | 81.4% | — |
| LiveBench Language | 59.9% | — |
Frequently asked questions
Is Claude 3.7 Sonnet better than Gemini 3 Flash Preview?
Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Gemini 3 Flash Preview better for coding?
Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Gemini 3 Flash Preview share?
32 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Gemini 3 Flash Preview has 59.