Model comparison
Claude 3 Sonnet vs Gemini 3.6 Flash
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 28.8 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Gemini 3.6 Flash in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 3.6 Flash leads 57.0 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 94.2% for Gemini 3.6 Flash.
Side by side
| Claude 3 Sonnet | Gemini 3.6 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 28.8 | 54.1 |
| Released | 2024-02-29 | 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 | 30 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.6 Flash leads
Claude 3 Sonnet: 29.2 (#296), Gemini 3.6 Flash: 49.6 (#45)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| WeirdML | 10.2% | 56.1% |
| LMArena Coding | 1223 | 1492 |
| DeepSWE | — | 46.7% |
| FrontierCode | — | 34.4% |
| LMArena WebDev | — | 1536 |
| SciCode | — | 52.7% |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| ALE-Bench | — | 715.52 |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Sonnet: —, Gemini 3.6 Flash: 32.4 (#56)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| APEX-Agents | — | 46.9% |
| GDP.pdf | — | 14% |
Reasoning Gemini 3.6 Flash leads
Claude 3 Sonnet: 19.7 (#232), Gemini 3.6 Flash: 58.9 (#20)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1486 |
| DTBench | 53.6% | 95.5% |
| Epoch Capabilities Index | 120.69 | 154.36 |
| ARC-AGI-2 | — | 60.4% |
| NYT Connections (extended) | — | 89% |
| ARC-AGI-1 | — | 91.2% |
| CritPt | — | 10.6% |
| Chess Puzzles | — | 43% |
| Mystery Game Puzzles | — | 30% |
| LMCA | — | 44.9% |
| WinoGrande | 75.1% | — |
Math Gemini 3.6 Flash leads
Claude 3 Sonnet: 10.0 (#305), Gemini 3.6 Flash: 57.0 (#33)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 94.2% |
| LMArena Math | 1213 | 1504 |
| FrontierMath (Tiers 1-3) | — | 58.9% |
| FrontierMath Tier 4 | — | 22% |
| MathArena Final-Answer Competitions | — | 70.8% |
| ProofBench | — | 36% |
| MATH Level 5 | 18.2% | — |
Knowledge Gemini 3.6 Flash leads
Claude 3 Sonnet: 21.1 (#271), Gemini 3.6 Flash: 67.8 (#7)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| GPQA Diamond | 40.6% | 94.1% |
| LMArena Expert | 1173 | 1489 |
| SimpleQA Verified | — | 66.2% |
| MMLU | 75.9% | — |
Multimodal Gemini 3.6 Flash leads
Claude 3 Sonnet: 24.7 (#120), Gemini 3.6 Flash: 38.7 (#55)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Vision | 984 | 1297 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 23.3% |
| LMArena Document | — | 1456 |
Multilingual Gemini 3.6 Flash leads
Claude 3 Sonnet: 38.0 (#229), Gemini 3.6 Flash: 56.8 (#17)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Non-English | 1205 | 1470 |
| LMArena Chinese | 1188 | 1530 |
| LMArena French | 1228 | 1501 |
| LMArena German | 1204 | 1478 |
| LMArena Japanese | 1131 | 1477 |
| LMArena Korean | 1128 | 1435 |
| LMArena Russian | 1227 | 1490 |
| LMArena Spanish | 1204 | 1477 |
Instruction Following Gemini 3.6 Flash leads
Claude 3 Sonnet: 63.1 (#230), Gemini 3.6 Flash: 77.2 (#27)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Instruction Following | 1200 | 1467 |
Long Context Gemini 3.6 Flash leads
Claude 3 Sonnet: 36.7 (#223), Gemini 3.6 Flash: 45.1 (#47)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Longer Query | 1211 | 1475 |
Writing & Preference Gemini 3.6 Flash leads
Claude 3 Sonnet: 42.3 (#233), Gemini 3.6 Flash: 68.3 (#26)
| Benchmark | Claude 3 Sonnet | Gemini 3.6 Flash |
|---|---|---|
| LMArena Text | 1218 | 1478 |
| LMArena Creative Writing | 1186 | 1464 |
| LMArena Multi-Turn | 1227 | 1481 |
| EQ-Bench Creative Writing | — | 1604 |
Frequently asked questions
Is Claude 3 Sonnet better than Gemini 3.6 Flash?
Gemini 3.6 Flash is the stronger model overall, scoring 54.1 to 28.8 on the Noometry Index.
Is Claude 3 Sonnet or Gemini 3.6 Flash better for coding?
Gemini 3.6 Flash scores higher on coding benchmarks: 49.6 versus 29.2 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Gemini 3.6 Flash share?
23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Gemini 3.6 Flash has 46.