Model comparison
Claude 3.5 Sonnet vs Gemini 3.6 Flash
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 34.6 on the Noometry Index.
Last verified . 24 shared benchmarks.
GoogleSummary
- They share 24 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Gemini 3.6 Flash in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.6 Flash leads 67.8 to 28.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 94.2% for Gemini 3.6 Flash.
Side by side
| Claude 3.5 Sonnet | Gemini 3.6 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 34.6 | 54.1 |
| Released | 2024-06-20 | 2026-07-21 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $3.75 |
| Results tracked | 60 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 39.0 (#165), Gemini 3.6 Flash: 50.0 (#48)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| WeirdML | 40% | 56.1% |
| LMArena Coding | 1342 | 1491 |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| Aider Polyglot | 51.6% | — |
| LMArena WebDev | — | 1538 |
| SciCode | — | 52.7% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 715.52 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Too close to call
Claude 3.5 Sonnet: 32.3 (#67), Gemini 3.6 Flash: 32.3 (#65)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| APEX-Agents | — | 46.9% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| GDP.pdf | — | 14% |
| METR Time Horizons | 45.2% | — |
Reasoning Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 23.1 (#183), Gemini 3.6 Flash: 58.8 (#22)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1485 |
| DTBench | 67.8% | 95.5% |
| Epoch Capabilities Index | 133.55 | 154.25 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | 41.4% | — |
| NYT Connections (extended) | — | 89% |
| ARC-AGI-1 | — | 91.2% |
| CritPt | — | 10.6% |
| Chess Puzzles | — | 43% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 30% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 44.9% |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 19.2 (#288), Gemini 3.6 Flash: 57.3 (#40)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 94.2% |
| LMArena Math | 1307 | 1505 |
| FrontierMath (Tiers 1-3) | — | 58.9% |
| FrontierMath Tier 4 | — | 22% |
| MathArena Final-Answer Competitions | — | 70.8% |
| ProofBench | — | 36% |
| Omni-MATH | 27.6% | — |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
| FrontierMath (Feb 2025 set) | 2.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 28.6 (#245), Gemini 3.6 Flash: 67.8 (#8)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | 55.3% | 94.1% |
| LMArena Expert | 1265 | 1488 |
| Humanity's Last Exam | 4.1% | — |
| SimpleQA Verified | — | 66.2% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 26.5 (#120), Gemini 3.6 Flash: 38.5 (#64)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | 1125 | 1298 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 23.3% |
| LMArena Document | — | 1456 |
Multilingual Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 43.2 (#185), Gemini 3.6 Flash: 56.5 (#19)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1283 | 1469 |
| LMArena Chinese | 1272 | 1531 |
| LMArena French | 1305 | 1504 |
| LMArena German | 1297 | 1478 |
| LMArena Japanese | 1234 | 1476 |
| LMArena Korean | 1200 | 1431 |
| LMArena Russian | 1306 | 1487 |
| LMArena Spanish | 1290 | 1475 |
Instruction Following Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 68.8 (#182), Gemini 3.6 Flash: 77.0 (#33)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1297 | 1466 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 39.9 (#167), Gemini 3.6 Flash: 45.1 (#50)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1311 | 1474 |
Writing & Preference Gemini 3.6 Flash leads
Claude 3.5 Sonnet: 52.9 (#164), Gemini 3.6 Flash: 68.2 (#27)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1298 | 1479 |
| LMArena Creative Writing | 1292 | 1465 |
| EQ-Bench Creative Writing | 1451 | 1604 |
| LMArena Multi-Turn | 1326 | 1481 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Gemini 3.6 Flash?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Gemini 3.6 Flash better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 50.0 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Gemini 3.6 Flash share?
24 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Gemini 3.6 Flash has 46.