Model comparison
Claude 3.5 Sonnet vs Gemini 2.5 Flash
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 34.6 on the Noometry Index.
Last verified . 41 shared benchmarks.
GoogleSummary
- They share 41 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 3 categories and Gemini 2.5 Flash in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 2.5 Flash leads 39.9 to 19.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 73.1% for Gemini 2.5 Flash.
Side by side
| Claude 3.5 Sonnet | Gemini 2.5 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 34.6 | 39.3 |
| Released | 2024-06-20 | 2025-04-17 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 60 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.0 (#165), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| Aider Polyglot | 51.6% | 55.1% |
| WeirdML | 40% | 41.9% |
| LMArena Coding | 1342 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 661.88 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 32.3 (#67), Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| TheAgentCompany | 24% | 41.1% |
| BALROG | 32.6% | 33.5% |
| Terminal-Bench | — | 17.1% |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| Cybench | 17.5% | — |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 548.84 |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 23.1 (#183), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| SimpleBench | 41.4% | 41.2% |
| EnigmaEval | 0.9% | 2.7% |
| LMArena Hard Prompts | 1305 | 1422 |
| DTBench | 67.8% | 76.5% |
| Epoch Capabilities Index | 133.55 | 143.03 |
| ForecastBench | 60.7 | 60.6 |
| ARC-AGI-2 | — | 2.5% |
| Kagi LLM Benchmark | — | 56.8% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | 56.7% | — |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 27.5% |
| LiveBench | 59% | — |
Math Gemini 2.5 Flash leads
Claude 3.5 Sonnet: 19.2 (#288), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 73.1% |
| Omni-MATH | 27.6% | 38.5% |
| LMArena Math | 1307 | 1415 |
| FrontierMath (Feb 2025 set) | 2.1% | 4.8% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| LiveBench Math | 52.3% | — |
| MATH Level 5 | 56.9% | — |
Knowledge Gemini 2.5 Flash leads
Claude 3.5 Sonnet: 28.6 (#245), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| Humanity's Last Exam | 4.1% | 12.1% |
| MMLU-Pro | 77.7% | 63.9% |
| Confabulations | 19.9% | 16.8% |
| GPQA (HELM) | 56.5% | 39% |
| LMArena Expert | 1265 | 1426 |
| GPQA Diamond | 55.3% | — |
| Vectara Hallucination Rate | — | 7.8% |
| MMLU | 87.3% | — |
Multimodal Gemini 2.5 Flash leads
Claude 3.5 Sonnet: 26.5 (#120), Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | 1125 | 1253 |
| GeoBench | 62% | 76% |
| VPCT | 33% | 46.2% |
| Video-MME | 60% | — |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
Claude 3.5 Sonnet: 43.2 (#185), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1283 | 1409 |
| LMArena Chinese | 1272 | 1450 |
| LMArena French | 1305 | 1433 |
| LMArena German | 1297 | 1418 |
| LMArena Japanese | 1234 | 1405 |
| LMArena Korean | 1200 | 1385 |
| LMArena Russian | 1306 | 1415 |
| LMArena Spanish | 1290 | 1421 |
Instruction Following Gemini 2.5 Flash leads
Claude 3.5 Sonnet: 68.8 (#182), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| IFEval | 85.5% | 89.8% |
| LMArena Instruction Following | 1297 | 1405 |
| LiveBench Instruction Following | 69.3% | — |
Long Context Gemini 2.5 Flash leads
Claude 3.5 Sonnet: 39.9 (#167), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1311 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Too close to call
Claude 3.5 Sonnet: 52.9 (#164), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | Claude 3.5 Sonnet | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1298 | 1417 |
| LMArena Creative Writing | 1292 | 1400 |
| Short-Story Creative Writing | 80.3% | 76.5% |
| EQ-Bench Creative Writing | 1451 | 1137 |
| WildBench | 79.2% | 81.7% |
| LMArena Multi-Turn | 1326 | 1408 |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Gemini 2.5 Flash?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Gemini 2.5 Flash better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.0 versus 35.8 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Gemini 2.5 Flash share?
41 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Gemini 2.5 Flash has 54.