Model comparison
Claude Opus 4.1 vs Claude Sonnet 4.6
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 41.0 on the Noometry Index.
Last verified . 35 shared benchmarks.
Summary
- They share 35 benchmarks with published results for both. Claude Opus 4.1 scores higher in 0 categories and Claude Sonnet 4.6 in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 22.3.
- The biggest single-benchmark swing is WeirdML: 45.9% for Claude Opus 4.1 and 66.1% for Claude Sonnet 4.6.
- Claude Sonnet 4.6 is cheaper at $3 / $15 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Opus 4.1 | Claude Sonnet 4.6 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 41.0 | 50.3 |
| Released | 2025-08-05 | 2026-02-17 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $3 |
| Output $ / M tokens | $75 | $15 |
| Results tracked | 48 | 57 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Opus 4.1: 44.4 (#73), Claude Sonnet 4.6: 46.3 (#67)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| SWE-bench Verified | 73.3% | 75.2% |
| LMArena WebDev | 1390 | 1522 |
| WeirdML | 45.9% | 66.1% |
| LMArena Coding | 1479 | 1504 |
| ALE-Bench | 674.77 | 1,327 |
| DeepSWE | — | 29.9% |
| FrontierCode | — | 24.3% |
| SciCode | — | 46.8% |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Sonnet 4.6 leads
Claude Opus 4.1: 35.0 (#41), Claude Sonnet 4.6: 39.1 (#28)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| Terminal-Bench | 38% | 53.4% |
| DeepResearch Bench | 48.3% | 54.9% |
| LMArena Search | 1148 | 1221 |
| APEX-Agents | — | 43% |
| OSWorld 2.0 | — | 9.3% |
| GDPval | 43.6% | — |
| Cybench | 42% | — |
| OSWorld | — | 72.1% |
| ExploitBench | — | 23.6% |
| GBAEval | — | 48.8% |
| GDP.pdf | — | 18% |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | 7,204 |
Reasoning Claude Sonnet 4.6 leads
Claude Opus 4.1: 32.2 (#76), Claude Sonnet 4.6: 46.1 (#45)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| Chess Puzzles | 7% | 13% |
| LMArena Hard Prompts | 1443 | 1484 |
| Mystery Game Puzzles | 21% | 16% |
| DTBench | 80% | 89.9% |
| LMCA | 37.1% | 46.5% |
| Epoch Capabilities Index | 144.12 | 152.24 |
| ForecastBench | 62 | 62 |
| ARC-AGI-2 | — | 60.4% |
| SimpleBench | 60% | — |
| NYT Connections (extended) | — | 80.9% |
| ARC-AGI-1 | — | 86.5% |
| CritPt | — | 3.1% |
| EnigmaEval | 7.2% | — |
| Thematic Generalization | — | 76.3% |
| EBR-Bench | 7.9% | — |
Math Claude Sonnet 4.6 leads
Claude Opus 4.1: 22.3 (#277), Claude Sonnet 4.6: 52.9 (#49)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 68.9% | 85.8% |
| LMArena Math | 1431 | 1462 |
| FrontierMath (Feb 2025 set) | 7.2% | 32.4% |
| FrontierMath Tier 4 (v1) | 4.2% | 8.3% |
| FrontierMath (Tiers 1-3) | 12.6% | — |
| FrontierMath Tier 4 | 2.4% | — |
| ProofBench | — | 45% |
Knowledge Claude Sonnet 4.6 leads
Claude Opus 4.1: 42.0 (#101), Claude Sonnet 4.6: 51.7 (#65)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| GPQA Diamond | 77.3% | 87.4% |
| Vectara Hallucination Rate | 11.8% | 10.6% |
| LMArena Expert | 1439 | 1500 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 35.5% |
| Confabulations | 17.1% | — |
Multimodal Claude Sonnet 4.6 leads
Claude Opus 4.1: 26.8 (#119), Claude Sonnet 4.6: 38.0 (#68)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| VPCT | 35% | — |
| Blueprint-Bench 2 | — | 6.7% |
| LMArena Document | — | 1482 |
Multilingual Claude Sonnet 4.6 leads
Claude Opus 4.1: 52.0 (#95), Claude Sonnet 4.6: 54.4 (#41)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Non-English | 1405 | 1440 |
| LMArena Chinese | 1427 | 1491 |
| LMArena French | 1431 | 1465 |
| LMArena German | 1413 | 1428 |
| LMArena Japanese | 1378 | 1420 |
| LMArena Korean | 1380 | 1411 |
| LMArena Russian | 1422 | 1440 |
| LMArena Spanish | 1448 | 1464 |
Instruction Following Claude Sonnet 4.6 leads
Claude Opus 4.1: 75.6 (#58), Claude Sonnet 4.6: 77.4 (#25)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Instruction Following | 1435 | 1475 |
Long Context Too close to call
Claude Opus 4.1: 44.5 (#63), Claude Sonnet 4.6: 45.3 (#44)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Longer Query | 1455 | 1479 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Opus 4.1: 62.4 (#74), Claude Sonnet 4.6: 70.2 (#22)
| Benchmark | Claude Opus 4.1 | Claude Sonnet 4.6 |
|---|---|---|
| LMArena Text | 1419 | 1458 |
| LMArena Creative Writing | 1412 | 1435 |
| LMArena Multi-Turn | 1444 | 1464 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 1810 |
| EQ-Bench 4 | — | 1207 |
Frequently asked questions
Is Claude Opus 4.1 better than Claude Sonnet 4.6?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 41.0 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or Claude Sonnet 4.6?
Claude Sonnet 4.6 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Claude Sonnet 4.6 better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 44.4 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4.6 does, with 1M tokens against 200K.
How many benchmarks do Claude Opus 4.1 and Claude Sonnet 4.6 share?
35 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Claude Sonnet 4.6 has 57.