Model comparison
Claude Opus 5 vs Claude Sonnet 5
Claude Opus 5 is the stronger model overall, scoring 67.8 to 54.6 on the Noometry Index. Claude Sonnet 5 costs 2.5× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 47 shared benchmarks.
Summary
- They share 47 benchmarks with published results for both. Claude Opus 5 scores higher in 10 categories and Claude Sonnet 5 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Opus 5 leads 77.2 to 49.1.
- The biggest single-benchmark swing is FrontierMath Tier 4: 73.2% for Claude Opus 5 and 29.3% for Claude Sonnet 5.
- Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 5.
Side by side
| Claude Opus 5 | Claude Sonnet 5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 67.8 | 54.6 |
| Released | 2026-07-24 | 2026-06-29 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $2 |
| Output $ / M tokens | $25 | $10 |
| Results tracked | 57 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), Claude Sonnet 5: 55.5 (#26)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| DeepSWE | 73.6% | 53.8% |
| FrontierCode | 53.4% | 42.7% |
| CursorBench | 46.6% | 34.1% |
| LMArena WebDev | 1691 | 1541 |
| SciCode | 56.4% | 54.3% |
| WeirdML | 91.8% | 68.8% |
| LMArena Coding | 1534 | 1483 |
| ALE-Bench | 2,165 | 1,463 |
| FrontierSWE | 52% | — |
| GSO | — | 37.3% |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), Claude Sonnet 5: 42.8 (#18)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| APEX-Agents | 65.8% | 54.5% |
| GBAEval | 79.6% | 65.3% |
| Vending-Bench 2 | 11,182 | 6,378 |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GDP.pdf | 24% | — |
| LMArena Search | — | 1194 |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), Claude Sonnet 5: 49.1 (#39)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| SimpleBench | 80.6% | 60.6% |
| NYT Connections (extended) | 94.3% | 75.1% |
| CritPt | 29.1% | 16.9% |
| Chess Puzzles | 42% | 35% |
| LMArena Hard Prompts | 1526 | 1461 |
| Mystery Game Puzzles | 59% | 35% |
| DTBench | 97.9% | 92.5% |
| LMCA | 64.5% | 50% |
| Bench to the Future 3 | 0.12 | 0.14 |
| Epoch Capabilities Index | 162.78 | 156.21 |
| ARC-AGI-2 | 90.4% | — |
| ARC-AGI-1 | 97.5% | — |
| EBR-Bench | 45.7% | — |
| Surface Evolver Bench | — | 60% |
| ForecastBench | — | 61.1 |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), Claude Sonnet 5: 66.2 (#27)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 85.6% | 65.6% |
| FrontierMath Tier 4 | 73.2% | 29.3% |
| OTIS Mock AIME 2024-2025 | 98.9% | 94.7% |
| ProofBench | 99% | 77% |
| LMArena Math | 1531 | 1467 |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), Claude Sonnet 5: 55.6 (#47)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| GPQA Diamond | 93.9% | 90.5% |
| SimpleQA Verified | 59.9% | 33.7% |
| LMArena Expert | 1557 | 1490 |
Multimodal Claude Opus 5 leads
Claude Opus 5: 50.8 (#8), Claude Sonnet 5: 42.4 (#31)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Vision | 1319 | 1274 |
| Blueprint-Bench 2 | 30.4% | 24.9% |
| LMArena Document | 1516 | 1466 |
| Furniture Assembly | 60.8% | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), Claude Sonnet 5: 53.8 (#55)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Non-English | 1501 | 1431 |
| LMArena Chinese | 1574 | 1477 |
| LMArena French | 1519 | 1460 |
| LMArena German | 1524 | 1440 |
| LMArena Japanese | 1516 | 1422 |
| LMArena Korean | 1521 | 1411 |
| LMArena Russian | 1507 | 1451 |
| LMArena Spanish | 1519 | 1437 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), Claude Sonnet 5: 76.3 (#41)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Instruction Following | 1517 | 1452 |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), Claude Sonnet 5: 44.8 (#55)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Longer Query | 1515 | 1463 |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), Claude Sonnet 5: 69.2 (#25)
| Benchmark | Claude Opus 5 | Claude Sonnet 5 |
|---|---|---|
| LMArena Text | 1507 | 1442 |
| LMArena Creative Writing | 1491 | 1416 |
| EQ-Bench Creative Writing | 2133 | 1794 |
| EQ-Bench 4 | 1385 | 1236 |
| LMArena Multi-Turn | 1499 | 1454 |
Frequently asked questions
Is Claude Opus 5 better than Claude Sonnet 5?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 54.6 on the Noometry Index. Claude Sonnet 5 costs 2.5× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5 or Claude Sonnet 5?
Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 5 lists at $5 and $25.
Is Claude Opus 5 or Claude Sonnet 5 better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 55.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Opus 5 and Claude Sonnet 5 share?
47 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Claude Sonnet 5 has 51.