Model comparison
Claude Opus 4 vs Claude Sonnet 5.5
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 43.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Claude Opus 4 scores higher in 0 categories and Claude Sonnet 5.5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 42.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 64.4% for Claude Opus 4 and 100% for Claude Sonnet 5.5.
- Claude Sonnet 5.5 is cheaper at $2 / $10 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- Claude Sonnet 5.5 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Opus 4 | Claude Sonnet 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 43.1 | 61.9 |
| Released | 2025-05-22 | 2026-09-28 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $2 |
| Output $ / M tokens | $75 | $10 |
| Results tracked | 56 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5.5 leads
Claude Opus 4: 47.2 (#62), Claude Sonnet 5.5: 67.3 (#6)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Coding | 1442 | 1513 |
| SWE-bench Verified | 70.7% | — |
| FrontierCode | — | 52.1% |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| CursorBench | — | 55.5% |
| LMArena WebDev | — | 1774 |
| FrontierSWE | — | 61.9% |
| SciCode | — | 61% |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | — | 1,819 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Sonnet 5.5 leads
Claude Opus 4: 34.8 (#42), Claude Sonnet 5.5: 45.0 (#16)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| APEX-Agents | — | 75.5% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Sonnet 5.5 leads
Claude Opus 4: 27.3 (#121), Claude Sonnet 5.5: 54.0 (#28)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| CritPt | 0.3% | 31.4% |
| LMArena Hard Prompts | 1399 | 1495 |
| Epoch Capabilities Index | 142.67 | 165.03 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 74.3% | — |
| NYT Connections (extended) | — | 80.5% |
| ARC-AGI-1 | 35.7% | — |
| EnigmaEval | 5.6% | — |
| Mystery Game Puzzles | — | 65% |
| DTBench | 81.6% | — |
| LMCA | 37.4% | — |
| ForecastBench | 61.1 | — |
Math Claude Sonnet 5.5 leads
Claude Opus 4: 42.0 (#86), Claude Sonnet 5.5: 87.9 (#6)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 100% |
| LMArena Math | 1390 | 1510 |
| FrontierMath (Tiers 1-3) | — | 88.8% |
| FrontierMath Tier 4 | — | 80.5% |
| ProofBench | — | 100% |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
| FrontierMath Erdős | — | 2.9% |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Sonnet 5.5 leads
Claude Opus 4: 44.0 (#88), Claude Sonnet 5.5: 66.0 (#12)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| GPQA Diamond | 76.3% | 95.6% |
| LMArena Expert | 1386 | 1540 |
| Humanity's Last Exam | 10.7% | — |
| SimpleQA Verified | — | 46.5% |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| Vectara Hallucination Rate | 12% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Claude Sonnet 5.5 leads
Claude Opus 4: 31.5 (#106), Claude Sonnet 5.5: 51.5 (#6)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Vision | 1192 | 1289 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
| Furniture Assembly | — | 75% |
Multilingual Claude Sonnet 5.5 leads
Claude Opus 4: 48.8 (#138), Claude Sonnet 5.5: 55.3 (#30)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Non-English | 1362 | 1452 |
| LMArena Chinese | 1386 | 1522 |
| LMArena Russian | 1392 | 1451 |
| LMArena French | 1372 | — |
| LMArena German | 1391 | — |
| LMArena Japanese | 1331 | — |
| LMArena Korean | 1321 | — |
| LMArena Spanish | 1389 | — |
Instruction Following Claude Sonnet 5.5 leads
Claude Opus 4: 77.1 (#28), Claude Sonnet 5.5: 78.3 (#11)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1495 |
| IFEval | 91.8% | — |
Long Context Claude Sonnet 5.5 leads
Claude Opus 4: 39.6 (#172), Claude Sonnet 5.5: 45.9 (#28)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Longer Query | 1422 | 1498 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Claude Sonnet 5.5 leads
Claude Opus 4: 61.2 (#89), Claude Sonnet 5.5: 66.0 (#40)
| Benchmark | Claude Opus 4 | Claude Sonnet 5.5 |
|---|---|---|
| LMArena Text | 1377 | 1471 |
| LMArena Creative Writing | 1387 | 1465 |
| LMArena Multi-Turn | 1396 | 1474 |
| Short-Story Creative Writing | 83.6% | — |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than Claude Sonnet 5.5?
Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 43.1 on the Noometry Index.
Which is cheaper, Claude Opus 4 or Claude Sonnet 5.5?
Claude Sonnet 5.5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Claude Sonnet 5.5 better for coding?
Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 47.2 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 5.5 does, with 1M tokens against 200K.
How many benchmarks do Claude Opus 4 and Claude Sonnet 5.5 share?
17 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Claude Sonnet 5.5 has 32.