Model comparison
Claude Sonnet 4 vs Gemini 3.7 Flash
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 40.6 on the Noometry Index.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Claude Sonnet 4 scores higher in 0 categories and Gemini 3.7 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.1 to 23.0.
- The biggest single-benchmark swing is ARC-AGI-2: 5.9% for Claude Sonnet 4 and 84.6% for Gemini 3.7 Flash.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 200K.
Side by side
| Claude Sonnet 4 | Gemini 3.7 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.6 | 59.8 |
| Released | 2025-05-22 | 2026-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 64K | 66K |
| Input $ / M tokens | $3 | $0.75 |
| Output $ / M tokens | $15 | $3.75 |
| Results tracked | 58 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.7 Flash leads
Claude Sonnet 4: 44.0 (#70), Gemini 3.7 Flash: 55.7 (#19)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| SciCode | 40% | 59.8% |
| LMArena Coding | 1414 | 1499 |
| ALE-Bench | 655.35 | 904.3 |
| DeepSWE | — | 65.5% |
| FrontierCode | — | 43.6% |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1593 |
| FrontierSWE | — | 20.3% |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
Agentic & Tool Use Gemini 3.7 Flash leads
Claude Sonnet 4: 38.3 (#29), Gemini 3.7 Flash: 42.2 (#18)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | — | 67.8% |
| Remote Labor Index | — | 5% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| GDP.pdf | — | 23.8% |
| METR Time Horizons | 62% | — |
Reasoning Gemini 3.7 Flash leads
Claude Sonnet 4: 23.0 (#169), Gemini 3.7 Flash: 70.1 (#12)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| ARC-AGI-2 | 5.9% | 84.6% |
| ARC-AGI-1 | 40% | 95.5% |
| CritPt | 0.3% | 14.3% |
| LMArena Hard Prompts | 1372 | 1497 |
| DTBench | 77.1% | 96.8% |
| LMCA | 29% | 50.4% |
| Epoch Capabilities Index | 141.69 | 157.72 |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| NYT Connections (extended) | — | 94% |
| Chess Puzzles | — | 47% |
| EnigmaEval | 3.1% | — |
| Mystery Game Puzzles | — | 37% |
| ForecastBench | 60.2 | — |
Math Gemini 3.7 Flash leads
Claude Sonnet 4: 41.5 (#71), Gemini 3.7 Flash: 69.5 (#18)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 97.2% |
| LMArena Math | 1375 | 1511 |
| FrontierMath (Tiers 1-3) | — | 71.6% |
| FrontierMath Tier 4 | — | 36.6% |
| ProofBench | — | 58% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Gemini 3.7 Flash leads
Claude Sonnet 4: 41.6 (#99), Gemini 3.7 Flash: 69.8 (#4)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | 79.2% | 94.8% |
| LMArena Expert | 1371 | 1508 |
| Humanity's Last Exam | 7.8% | — |
| SimpleQA Verified | — | 69.2% |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Gemini 3.7 Flash leads
Claude Sonnet 4: 25.6 (#116), Gemini 3.7 Flash: 36.9 (#69)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | 1191 | 1314 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| Furniture Assembly | — | 26.7% |
| MindCube | 44.8% | — |
Multilingual Gemini 3.7 Flash leads
Claude Sonnet 4: 46.9 (#151), Gemini 3.7 Flash: 57.8 (#7)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1333 | 1485 |
| LMArena Chinese | 1351 | 1553 |
| LMArena French | 1364 | 1512 |
| LMArena German | 1331 | 1485 |
| LMArena Japanese | 1301 | 1506 |
| LMArena Korean | 1293 | 1486 |
| LMArena Russian | 1355 | 1519 |
| LMArena Spanish | 1356 | 1507 |
Instruction Following Gemini 3.7 Flash leads
Claude Sonnet 4: 71.8 (#141), Gemini 3.7 Flash: 78.0 (#12)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1375 | 1486 |
| IFEval | 84% | — |
Long Context Gemini 3.7 Flash leads
Claude Sonnet 4: 33.6 (#254), Gemini 3.7 Flash: 45.8 (#28)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1398 | 1493 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Gemini 3.7 Flash leads
Claude Sonnet 4: 57.3 (#127), Gemini 3.7 Flash: 71.4 (#19)
| Benchmark | Claude Sonnet 4 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 1351 | 1487 |
| LMArena Creative Writing | 1345 | 1490 |
| EQ-Bench Creative Writing | 1483 | 1723 |
| LMArena Multi-Turn | 1376 | 1495 |
| Short-Story Creative Writing | 81.4% | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Gemini 3.7 Flash?
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 40.6 on the Noometry Index.
Which is cheaper, Claude Sonnet 4 or Gemini 3.7 Flash?
Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Gemini 3.7 Flash better for coding?
Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 44.0 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.7 Flash does, with 1.05M tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Gemini 3.7 Flash share?
29 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Gemini 3.7 Flash has 44.