Model comparison
Claude Sonnet 4 vs Gemini 2.0 Flash (Feb 2025)
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 35.1 on the Noometry Index.
Last verified . 43 shared benchmarks.
GoogleSummary
- They share 43 benchmarks with published results for both. Claude Sonnet 4 scores higher in 6 categories and Gemini 2.0 Flash (Feb 2025) in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 4 leads 43.5 to 28.4.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 64.9% for Claude Sonnet 4 and 13.5% for Gemini 2.0 Flash (Feb 2025).
Side by side
| Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.8 | 35.1 |
| Released | 2025-05-22 | 2024-12-06 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 58 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Gemini 2.0 Flash (Feb 2025): 28.4 (#315)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 64.9% | 13.5% |
| Aider Polyglot | 61.3% | 38.2% |
| WeirdML | 46.1% | 25.8% |
| LMArena Coding | 1414 | 1350 |
| SciCode | 40% | — |
| GSO | 4.9% | — |
| BigCodeBench Instruct | — | 45.9% |
| LiveBench Coding | — | 63.4% |
| BigCodeBench Complete | — | 59.9% |
| CadEval | — | 30% |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), Gemini 2.0 Flash (Feb 2025): 28.1 (#92)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| TheAgentCompany | 33.1% | 11.4% |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Gemini 2.0 Flash (Feb 2025): 15.2 (#318)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| ARC-AGI-2 | 5.9% | 1.3% |
| SimpleBench | 45.5% | 31.1% |
| Kagi LLM Benchmark | 73% | 37.8% |
| EnigmaEval | 3.1% | 1.1% |
| LMArena Hard Prompts | 1372 | 1346 |
| DTBench | 77.1% | 63.2% |
| Epoch Capabilities Index | 141.69 | 135.36 |
| ARC-AGI-1 | 40% | — |
| CritPt | 0.3% | — |
| LiveBench Reasoning | — | 78.2% |
| LiveBench Data Analysis | — | 69.4% |
| LMCA | 29% | — |
| ForecastBench | 60.2 | — |
| LiveBench | — | 66.9% |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Gemini 2.0 Flash (Feb 2025): 37.9 (#146)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 57.8% |
| Omni-MATH | 60.2% | 45.9% |
| LMArena Math | 1375 | 1352 |
| MATH Level 5 | 84.4% | 82.2% |
| FrontierMath (Feb 2025 set) | 4.1% | 1.7% |
| LiveBench Math | — | 75.8% |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Gemini 2.0 Flash (Feb 2025): 32.0 (#213)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| GPQA Diamond | 79.2% | 64.1% |
| Humanity's Last Exam | 7.8% | 6.6% |
| MMLU-Pro | 84.3% | 73.7% |
| Confabulations | 13.2% | 12.4% |
| GPQA (HELM) | 70.6% | 55.6% |
| LMArena Expert | 1372 | 1339 |
| Vectara Hallucination Rate | 10.3% | — |
| MMLU | — | 79.7% |
Multimodal Gemini 2.0 Flash (Feb 2025) leads
Claude Sonnet 4: 26.2 (#121), Gemini 2.0 Flash (Feb 2025): 36.5 (#79)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Vision | 1191 | 1158 |
| GeoBench | 37% | 77% |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Too close to call
Claude Sonnet 4: 46.7 (#156), Gemini 2.0 Flash (Feb 2025): 47.4 (#149)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Non-English | 1333 | 1342 |
| LMArena Chinese | 1350 | 1373 |
| LMArena French | 1363 | 1391 |
| LMArena German | 1331 | 1353 |
| LMArena Japanese | 1302 | 1294 |
| LMArena Korean | 1291 | 1313 |
| LMArena Russian | 1355 | 1351 |
| LMArena Spanish | 1357 | 1363 |
Instruction Following Gemini 2.0 Flash (Feb 2025) leads
Claude Sonnet 4: 71.7 (#145), Gemini 2.0 Flash (Feb 2025): 74.4 (#97)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| IFEval | 84% | 84.1% |
| LMArena Instruction Following | 1376 | 1336 |
| LiveBench Instruction Following | — | 85.8% |
Long Context Gemini 2.0 Flash (Feb 2025) leads
Claude Sonnet 4: 33.7 (#259), Gemini 2.0 Flash (Feb 2025): 38.1 (#203)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Fiction.LiveBench | 46.9% | 61.1% |
| LMArena Longer Query | 1398 | 1344 |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Gemini 2.0 Flash (Feb 2025): 49.5 (#190)
| Benchmark | Claude Sonnet 4 | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Text | 1351 | 1354 |
| LMArena Creative Writing | 1345 | 1340 |
| Short-Story Creative Writing | 81.4% | 73.8% |
| EQ-Bench Creative Writing | 1483 | 1128 |
| WildBench | 83.8% | 80% |
| LMArena Multi-Turn | 1376 | 1350 |
| LiveBench Language | — | 51.3% |
Frequently asked questions
Is Claude Sonnet 4 better than Gemini 2.0 Flash (Feb 2025)?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 35.1 on the Noometry Index.
Is Claude Sonnet 4 or Gemini 2.0 Flash (Feb 2025) better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 28.4 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and Gemini 2.0 Flash (Feb 2025) share?
43 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Gemini 2.0 Flash (Feb 2025) has 54.