Model comparison
Claude Opus 4.6 vs Gemini 3.7 Flash
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 58.3 on the Noometry Index.
Last verified . 39 shared benchmarks.
GoogleSummary
- They share 39 benchmarks with published results for both. Claude Opus 4.6 scores higher in 7 categories and Gemini 3.7 Flash in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.1 to 57.7.
- The biggest single-benchmark swing is Chess Puzzles: 17% for Claude Opus 4.6 and 47% for Gemini 3.7 Flash.
- Gemini 3.7 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
- Gemini 3.7 Flash accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Opus 4.6 | Gemini 3.7 Flash | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 58.3 | 59.8 |
| Released | 2026-02-04 | 2026-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 66K |
| Input $ / M tokens | $5 | $0.75 |
| Output $ / M tokens | $25 | $3.75 |
| Results tracked | 68 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.6 leads
Claude Opus 4.6: 57.7 (#15), Gemini 3.7 Flash: 55.7 (#19)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| FrontierCode | 26.6% | 43.6% |
| LMArena WebDev | 1546 | 1593 |
| LMArena Coding | 1535 | 1499 |
| ALE-Bench | 996.5 | 904.3 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | — | 65.5% |
| SWE-bench Verified (bash only) | 75.6% | — |
| SWE-bench Multilingual | 72% | — |
| FrontierSWE | — | 20.3% |
| SciCode | — | 59.8% |
| GSO | 41.2% | — |
| WeirdML | 78% | — |
| AlgoTune | 1.47 | — |
Agentic & Tool Use Claude Opus 4.6 leads
Claude Opus 4.6: 51.0 (#4), Gemini 3.7 Flash: 42.2 (#18)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| APEX-Agents | 46.3% | 67.8% |
| Remote Labor Index | 4.2% | 5% |
| Terminal-Bench | 79.8% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| GBAEval | 44.1% | — |
| GDP.pdf | — | 23.8% |
| LMArena Search | 1253 | — |
| METR Time Horizons | 78.9% | — |
| Vending-Bench 2 | 8,018 | — |
Reasoning Gemini 3.7 Flash leads
Claude Opus 4.6: 57.7 (#21), Gemini 3.7 Flash: 70.1 (#12)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| ARC-AGI-2 | 69.2% | 84.6% |
| NYT Connections (extended) | 92.1% | 94% |
| ARC-AGI-1 | 94% | 95.5% |
| Chess Puzzles | 17% | 47% |
| LMArena Hard Prompts | 1527 | 1497 |
| Mystery Game Puzzles | 25% | 37% |
| DTBench | 91.2% | 96.8% |
| LMCA | 55.8% | 50.4% |
| Epoch Capabilities Index | 155.36 | 157.72 |
| SimpleBench | 67.6% | — |
| Kagi LLM Benchmark | 83.6% | — |
| CritPt | — | 14.3% |
| EnigmaEval | 7.6% | — |
| Thematic Generalization | 80.6% | — |
| EBR-Bench | 12.7% | — |
| ForecastBench | 60 | — |
Math Gemini 3.7 Flash leads
Claude Opus 4.6: 62.7 (#25), Gemini 3.7 Flash: 69.5 (#18)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 71.6% |
| FrontierMath Tier 4 | 26.8% | 36.6% |
| OTIS Mock AIME 2024-2025 | 94.4% | 97.2% |
| ProofBench | 50% | 58% |
| LMArena Math | 1517 | 1511 |
| MathArena Final-Answer Competitions | 78.5% | — |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Tier 4 (v1) | 22.9% | — |
Knowledge Gemini 3.7 Flash leads
Claude Opus 4.6: 61.8 (#23), Gemini 3.7 Flash: 69.8 (#4)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| GPQA Diamond | 90.5% | 94.8% |
| SimpleQA Verified | 47% | 69.2% |
| LMArena Expert | 1546 | 1508 |
| Humanity's Last Exam | 34.4% | — |
| Vectara Hallucination Rate | 12.2% | — |
Multimodal Too close to call
Claude Opus 4.6: 37.0 (#67), Gemini 3.7 Flash: 36.9 (#69)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Vision | 1316 | 1314 |
| Furniture Assembly | 28.3% | 26.7% |
| LMArena Document | 1507 | — |
Multilingual Too close to call
Claude Opus 4.6: 58.2 (#4), Gemini 3.7 Flash: 57.8 (#7)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1490 | 1485 |
| LMArena Chinese | 1551 | 1553 |
| LMArena French | 1513 | 1512 |
| LMArena German | 1504 | 1485 |
| LMArena Japanese | 1484 | 1506 |
| LMArena Korean | 1465 | 1486 |
| LMArena Russian | 1497 | 1519 |
| LMArena Spanish | 1512 | 1507 |
Instruction Following Claude Opus 4.6 leads
Claude Opus 4.6: 79.7 (#3), Gemini 3.7 Flash: 78.0 (#12)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1523 | 1486 |
Long Context Claude Opus 4.6 leads
Claude Opus 4.6: 48.1 (#13), Gemini 3.7 Flash: 45.8 (#28)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1520 | 1493 |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |
Writing & Preference Claude Opus 4.6 leads
Claude Opus 4.6: 73.7 (#9), Gemini 3.7 Flash: 71.4 (#19)
| Benchmark | Claude Opus 4.6 | Gemini 3.7 Flash |
|---|---|---|
| LMArena Text | 1504 | 1487 |
| LMArena Creative Writing | 1506 | 1490 |
| EQ-Bench Creative Writing | 1809 | 1723 |
| LMArena Multi-Turn | 1514 | 1495 |
| EQ-Bench 4 | 1223 | — |
Frequently asked questions
Is Claude Opus 4.6 better than Gemini 3.7 Flash?
Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 58.3 on the Noometry Index.
Which is cheaper, Claude Opus 4.6 or Gemini 3.7 Flash?
Gemini 3.7 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Claude Opus 4.6 lists at $5 and $25.
Is Claude Opus 4.6 or Gemini 3.7 Flash better for coding?
Claude Opus 4.6 scores higher on coding benchmarks: 57.7 versus 55.7 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.7 Flash does, with 1.05M tokens against 1M.
How many benchmarks do Claude Opus 4.6 and Gemini 3.7 Flash share?
39 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Gemini 3.7 Flash has 44.