Model comparison
Claude 3.5 Sonnet vs Gemini 3.8 Flash
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 34.6 on the Noometry Index.
Last verified . 25 shared benchmarks.
GoogleSummary
- They share 25 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Gemini 3.8 Flash in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 23.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 98.9% for Gemini 3.8 Flash.
Side by side
| Claude 3.5 Sonnet | Gemini 3.8 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 34.6 | 61.8 |
| Released | 2024-06-20 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $3.75 |
| Results tracked | 60 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 39.0 (#165), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| WeirdML | 40% | 84.8% |
| LMArena Coding | 1342 | 1510 |
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| Aider Polyglot | 51.6% | — |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1584 |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| LiveBench Coding | 67.1% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| ALE-Bench | — | 1,270 |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 32.3 (#67), Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| Remote Labor Index | — | 5.8% |
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| GDP.pdf | — | 23.4% |
| METR Time Horizons | 45.2% | — |
| Vending-Bench 2 | — | 5,094 |
Reasoning Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 23.1 (#183), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| LMArena Hard Prompts | 1305 | 1508 |
| DTBench | 67.8% | 95.7% |
| Epoch Capabilities Index | 133.55 | 156.71 |
| ARC-AGI-2 | — | 89.2% |
| SimpleBench | 41.4% | — |
| NYT Connections (extended) | — | 97.4% |
| ARC-AGI-1 | — | 98.5% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| EnigmaEval | 0.9% | — |
| LiveBench Reasoning | 56.7% | — |
| Mystery Game Puzzles | — | 47% |
| LiveBench Data Analysis | 55% | — |
| LMCA | — | 52.9% |
| Surface Evolver Bench | — | 76.9% |
| ForecastBench | 60.7 | — |
| LiveBench | 59% | — |
Math Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 19.2 (#288), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 98.9% |
| LMArena Math | 1307 | 1528 |
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| ProofBench | — | 48% |
| 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 3.8 Flash leads
Claude 3.5 Sonnet: 28.6 (#245), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | 55.3% | 95.4% |
| Humanity's Last Exam | 4.1% | 44.5% |
| LMArena Expert | 1265 | 1524 |
| SimpleQA Verified | — | 69.7% |
| MMLU-Pro | 77.7% | — |
| Confabulations | 19.9% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 26.5 (#120), Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 1125 | 1314 |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |
Multilingual Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 43.2 (#185), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1283 | 1491 |
| LMArena Chinese | 1272 | 1554 |
| LMArena French | 1305 | 1498 |
| LMArena German | 1297 | 1493 |
| LMArena Japanese | 1234 | 1502 |
| LMArena Korean | 1200 | 1459 |
| LMArena Russian | 1306 | 1515 |
| LMArena Spanish | 1290 | 1485 |
Instruction Following Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 68.8 (#182), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1297 | 1490 |
| LiveBench Instruction Following | 69.3% | — |
| IFEval | 85.5% | — |
Long Context Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 39.9 (#167), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1311 | 1508 |
Writing & Preference Gemini 3.8 Flash leads
Claude 3.5 Sonnet: 52.9 (#164), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | Claude 3.5 Sonnet | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1298 | 1499 |
| LMArena Creative Writing | 1292 | 1492 |
| EQ-Bench Creative Writing | 1451 | 1748 |
| LMArena Multi-Turn | 1326 | 1501 |
| Short-Story Creative Writing | 80.3% | — |
| WildBench | 79.2% | — |
| LiveBench Language | 53.8% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Gemini 3.8 Flash?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 34.6 on the Noometry Index.
Is Claude 3.5 Sonnet or Gemini 3.8 Flash better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 39.0 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Gemini 3.8 Flash share?
25 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Gemini 3.8 Flash has 50.