Model comparison
Claude Sonnet 5 vs Gemini 3.8 Flash
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 54.6 on the Noometry Index.
Last verified . 43 shared benchmarks.
GoogleSummary
- They share 43 benchmarks with published results for both. Claude Sonnet 5 scores higher in 3 categories and Gemini 3.8 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 49.1.
- The biggest single-benchmark swing is SimpleQA Verified: 33.7% for Claude Sonnet 5 and 69.7% for Gemini 3.8 Flash.
- Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Sonnet 5 | Gemini 3.8 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 54.6 | 61.8 |
| Released | 2026-06-29 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $0.75 |
| Output $ / M tokens | $10 | $3.75 |
| Results tracked | 51 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.8 Flash leads
Claude Sonnet 5: 55.5 (#26), Gemini 3.8 Flash: 59.2 (#15)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| DeepSWE | 53.8% | 73.8% |
| FrontierCode | 42.7% | 41.2% |
| CursorBench | 34.1% | 39.6% |
| LMArena WebDev | 1541 | 1584 |
| SciCode | 54.3% | 56.6% |
| WeirdML | 68.8% | 84.8% |
| LMArena Coding | 1483 | 1510 |
| ALE-Bench | 1,463 | 1,270 |
| FrontierSWE | — | 19.6% |
| GSO | 37.3% | — |
Agentic & Tool Use Too close to call
Claude Sonnet 5: 42.8 (#18), Gemini 3.8 Flash: 41.8 (#21)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | 54.5% | 64.3% |
| Vending-Bench 2 | 6,378 | 5,094 |
| Remote Labor Index | — | 5.8% |
| GBAEval | 65.3% | — |
| GDP.pdf | — | 23.4% |
| LMArena Search | 1194 | — |
Reasoning Gemini 3.8 Flash leads
Claude Sonnet 5: 49.1 (#39), Gemini 3.8 Flash: 76.9 (#5)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| NYT Connections (extended) | 75.1% | 97.4% |
| CritPt | 16.9% | 18.3% |
| Chess Puzzles | 35% | 61% |
| LMArena Hard Prompts | 1461 | 1508 |
| Mystery Game Puzzles | 35% | 47% |
| DTBench | 92.5% | 95.7% |
| LMCA | 50% | 52.9% |
| Surface Evolver Bench | 60% | 76.9% |
| Epoch Capabilities Index | 156.21 | 156.71 |
| ARC-AGI-2 | — | 89.2% |
| SimpleBench | 60.6% | — |
| ARC-AGI-1 | — | 98.5% |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
Math Too close to call
Claude Sonnet 5: 66.2 (#27), Gemini 3.8 Flash: 65.3 (#28)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | 68.4% |
| FrontierMath Tier 4 | 29.3% | 22% |
| OTIS Mock AIME 2024-2025 | 94.7% | 98.9% |
| ProofBench | 77% | 48% |
| LMArena Math | 1467 | 1528 |
Knowledge Gemini 3.8 Flash leads
Claude Sonnet 5: 55.6 (#47), Gemini 3.8 Flash: 74.8 (#2)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | 90.5% | 95.4% |
| SimpleQA Verified | 33.7% | 69.7% |
| LMArena Expert | 1490 | 1524 |
| Humanity's Last Exam | — | 44.5% |
Multimodal Claude Sonnet 5 leads
Claude Sonnet 5: 42.4 (#31), Gemini 3.8 Flash: 40.7 (#45)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | 1274 | 1314 |
| Blueprint-Bench 2 | 24.9% | 38.6% |
| Furniture Assembly | — | 31.7% |
| LMArena Document | 1466 | — |
Multilingual Gemini 3.8 Flash leads
Claude Sonnet 5: 53.8 (#55), Gemini 3.8 Flash: 58.0 (#5)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | 1431 | 1491 |
| LMArena Chinese | 1477 | 1554 |
| LMArena French | 1460 | 1498 |
| LMArena German | 1440 | 1493 |
| LMArena Japanese | 1422 | 1502 |
| LMArena Korean | 1411 | 1459 |
| LMArena Russian | 1451 | 1515 |
| LMArena Spanish | 1437 | 1485 |
Instruction Following Gemini 3.8 Flash leads
Claude Sonnet 5: 76.3 (#41), Gemini 3.8 Flash: 78.0 (#13)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | 1452 | 1490 |
Long Context Gemini 3.8 Flash leads
Claude Sonnet 5: 44.8 (#55), Gemini 3.8 Flash: 46.3 (#24)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | 1463 | 1508 |
Writing & Preference Gemini 3.8 Flash leads
Claude Sonnet 5: 69.2 (#25), Gemini 3.8 Flash: 72.2 (#15)
| Benchmark | Claude Sonnet 5 | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | 1442 | 1499 |
| LMArena Creative Writing | 1416 | 1492 |
| EQ-Bench Creative Writing | 1794 | 1748 |
| LMArena Multi-Turn | 1454 | 1501 |
| EQ-Bench 4 | 1236 | — |
Frequently asked questions
Is Claude Sonnet 5 better than Gemini 3.8 Flash?
Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 54.6 on the Noometry Index.
Which is cheaper, Claude Sonnet 5 or Gemini 3.8 Flash?
Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Sonnet 5 lists at $2 and $10.
Is Claude Sonnet 5 or Gemini 3.8 Flash better for coding?
Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 55.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.8 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Claude Sonnet 5 and Gemini 3.8 Flash share?
43 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Gemini 3.8 Flash has 50.