Model comparison
Claude 3.7 Sonnet vs Gemini 4 Argon
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 39.5 on the Noometry Index.
Last verified . 13 shared benchmarks.
GoogleSummary
- They share 13 benchmarks with published results for both. Claude 3.7 Sonnet scores higher in 1 category and Gemini 4 Argon in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 4 Argon leads 73.9 to 37.5.
Side by side
| Claude 3.7 Sonnet | Gemini 4 Argon | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 39.5 | 56.5 |
| Released | 2025-02-24 | 2026-09-30 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 58 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 4 Argon leads
Claude 3.7 Sonnet: 40.6 (#136), Gemini 4 Argon: 62.0 (#9)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Coding | 1361 | 1550 |
| SWE-bench Verified | 61% | — |
| SWE-bench Verified (bash only) | 52.8% | — |
| Aider Polyglot | 64.9% | — |
| LMArena WebDev | — | 1678 |
| FrontierSWE | — | 55% |
| SciCode | — | 61.8% |
| GSO | 3.8% | — |
| LiveBench Coding | 74.5% | — |
| CadEval | 54% | — |
Agentic & Tool Use Gemini 4 Argon leads
Claude 3.7 Sonnet: 34.1 (#50), Gemini 4 Argon: 49.2 (#8)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | — | 82.2% |
| TheAgentCompany | 30.9% | — |
| Cybench | 20% | — |
| DeepResearch Bench | 43.6% | — |
| OSWorld | 35.8% | — |
| METR Time Horizons | 60% | — |
| Vending-Bench 2 | — | 13,718 |
Reasoning Gemini 4 Argon leads
Claude 3.7 Sonnet: 18.6 (#277), Gemini 4 Argon: 44.2 (#47)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1548 |
| ARC-AGI-2 | 0.9% | — |
| SimpleBench | 46.4% | — |
| ARC-AGI-1 | 28.6% | — |
| CritPt | — | 27.1% |
| EnigmaEval | 4.2% | — |
| LiveBench Reasoning | 87.8% | — |
| LiveBench Data Analysis | 74% | — |
| Epoch Capabilities Index | 141.16 | — |
| ForecastBench | 61.8 | — |
| LiveBench | 76.1% | — |
Math Gemini 4 Argon leads
Claude 3.7 Sonnet: 37.5 (#153), Gemini 4 Argon: 73.9 (#17)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Math | 1337 | 1536 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| ProofBench | — | 99% |
| Omni-MATH | 33% | — |
| LiveBench Math | 79% | — |
| MATH Level 5 | 91.2% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
Knowledge Gemini 4 Argon leads
Claude 3.7 Sonnet: 39.8 (#130), Gemini 4 Argon: 43.9 (#89)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1321 | 1553 |
| GPQA Diamond | 79.7% | — |
| Humanity's Last Exam | 8% | — |
| MMLU-Pro | 78.4% | — |
| Confabulations | 14.7% | — |
| GPQA (HELM) | 60.8% | — |
Multimodal Gemini 4 Argon leads
Claude 3.7 Sonnet: 33.7 (#95), Gemini 4 Argon: 46.5 (#14)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Vision | 1169 | — |
| GeoBench | 68% | — |
| VPCT | 39% | — |
| Blueprint-Bench 2 | — | 54.4% |
| SpatialViz-Bench | 33.9% | — |
Multilingual Gemini 4 Argon leads
Claude 3.7 Sonnet: 44.1 (#179), Gemini 4 Argon: 60.3 (#1)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1296 | 1523 |
| LMArena Chinese | 1299 | 1610 |
| LMArena Russian | 1311 | 1537 |
| LMArena Spanish | 1298 | 1497 |
| LMArena French | 1303 | — |
| LMArena German | 1301 | — |
| LMArena Japanese | 1267 | — |
| LMArena Korean | 1249 | — |
Instruction Following Gemini 4 Argon leads
Claude 3.7 Sonnet: 72.9 (#125), Gemini 4 Argon: 80.1 (#2)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1352 | 1538 |
| LiveBench Instruction Following | 81.3% | — |
| IFEval | 83.4% | — |
Long Context Claude 3.7 Sonnet leads
Claude 3.7 Sonnet: 50.3 (#10), Gemini 4 Argon: 47.6 (#15)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1373 | 1549 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Gemini 4 Argon leads
Claude 3.7 Sonnet: 54.4 (#150), Gemini 4 Argon: 71.4 (#19)
| Benchmark | Claude 3.7 Sonnet | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1314 | 1534 |
| LMArena Creative Writing | 1332 | 1531 |
| LMArena Multi-Turn | 1339 | 1557 |
| 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 4 Argon?
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 39.5 on the Noometry Index.
Is Claude 3.7 Sonnet or Gemini 4 Argon better for coding?
Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 40.6 in the Noometry coding category.
How many benchmarks do Claude 3.7 Sonnet and Gemini 4 Argon share?
13 benchmarks have published results for both models. Claude 3.7 Sonnet has 58 scored results on Noometry and Gemini 4 Argon has 21.