Model comparison
Claude Sonnet 4 vs Gemini 4 Argon
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 40.8 on the Noometry Index.
Last verified . 15 shared benchmarks.
GoogleSummary
- They share 15 benchmarks with published results for both. Claude Sonnet 4 scores higher in 0 categories and Gemini 4 Argon in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 4 Argon leads 73.9 to 43.3.
- The biggest single-benchmark swing is CritPt: 0.3% for Claude Sonnet 4 and 27.1% for Gemini 4 Argon.
Side by side
| Claude Sonnet 4 | Gemini 4 Argon | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 40.8 | 56.5 |
| Released | 2025-05-22 | 2026-09-30 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| 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 Sonnet 4: 43.5 (#88), Gemini 4 Argon: 62.0 (#9)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| SciCode | 40% | 61.8% |
| LMArena Coding | 1414 | 1550 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| LMArena WebDev | — | 1678 |
| FrontierSWE | — | 55% |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Gemini 4 Argon leads
Claude Sonnet 4: 38.5 (#31), Gemini 4 Argon: 49.2 (#8)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | — | 82.2% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
| Vending-Bench 2 | — | 13,718 |
Reasoning Gemini 4 Argon leads
Claude Sonnet 4: 22.9 (#187), Gemini 4 Argon: 44.2 (#47)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| CritPt | 0.3% | 27.1% |
| LMArena Hard Prompts | 1372 | 1548 |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| Kagi LLM Benchmark | 73% | — |
| ARC-AGI-1 | 40% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Gemini 4 Argon leads
Claude Sonnet 4: 43.3 (#80), Gemini 4 Argon: 73.9 (#17)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| LMArena Math | 1375 | 1536 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | — | 99% |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Gemini 4 Argon leads
Claude Sonnet 4: 41.8 (#108), Gemini 4 Argon: 43.9 (#89)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1372 | 1553 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Gemini 4 Argon leads
Claude Sonnet 4: 26.2 (#121), Gemini 4 Argon: 46.5 (#14)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| Blueprint-Bench 2 | — | 54.4% |
| MindCube | 44.8% | — |
Multilingual Gemini 4 Argon leads
Claude Sonnet 4: 46.7 (#156), Gemini 4 Argon: 60.3 (#1)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1333 | 1523 |
| LMArena Chinese | 1350 | 1610 |
| LMArena Russian | 1355 | 1537 |
| LMArena Spanish | 1357 | 1497 |
| LMArena French | 1363 | — |
| LMArena German | 1331 | — |
| LMArena Japanese | 1302 | — |
| LMArena Korean | 1291 | — |
Instruction Following Gemini 4 Argon leads
Claude Sonnet 4: 71.7 (#145), Gemini 4 Argon: 80.1 (#2)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1376 | 1538 |
| IFEval | 84% | — |
Long Context Gemini 4 Argon leads
Claude Sonnet 4: 33.7 (#259), Gemini 4 Argon: 47.6 (#15)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1398 | 1549 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Gemini 4 Argon leads
Claude Sonnet 4: 57.1 (#132), Gemini 4 Argon: 71.4 (#19)
| Benchmark | Claude Sonnet 4 | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1351 | 1534 |
| LMArena Creative Writing | 1345 | 1531 |
| LMArena Multi-Turn | 1376 | 1557 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Gemini 4 Argon?
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 40.8 on the Noometry Index.
Is Claude Sonnet 4 or Gemini 4 Argon better for coding?
Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 43.5 in the Noometry coding category.
How many benchmarks do Claude Sonnet 4 and Gemini 4 Argon share?
15 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Gemini 4 Argon has 21.