Model comparison
Claude Opus 4.6 vs Claude Opus 5.5
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 58.2 on the Noometry Index.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. Claude Opus 4.6 scores higher in 2 categories and Claude Opus 5.5 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5.5 leads 91.8 to 63.0.
- The biggest single-benchmark swing is FrontierMath Tier 4: 26.8% for Claude Opus 4.6 and 95% for Claude Opus 5.5.
- Claude Opus 5.5 is cheaper at $4 / $20 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
Side by side
| Claude Opus 4.6 | Claude Opus 5.5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 58.2 | 68.6 |
| Released | 2026-02-04 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 128K |
| Input $ / M tokens | $5 | $4 |
| Output $ / M tokens | $25 | $20 |
| Results tracked | 68 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5.5 leads
Claude Opus 4.6: 57.2 (#20), Claude Opus 5.5: 71.9 (#3)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| FrontierCode | 26.6% | 54.6% |
| LMArena WebDev | 1547 | 1813 |
| LMArena Coding | 1536 | 1547 |
| ALE-Bench | 996.5 | 2,147 |
| SWE-bench Verified | 78.7% | — |
| SWE-bench Verified (bash only) | 75.6% | — |
| CursorBench | — | 57.8% |
| SWE-bench Multilingual | 72% | — |
| FrontierSWE | — | 62.3% |
| SciCode | — | 66.9% |
| GSO | 41.2% | — |
| WeirdML | 78% | — |
| MirrorCode | — | 77.4% |
| AlgoTune | 1.47 | — |
Agentic & Tool Use Claude Opus 4.6 leads
Claude Opus 4.6: 51.1 (#4), Claude Opus 5.5: 45.3 (#15)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| APEX-Agents | 46.3% | 73.5% |
| Vending-Bench 2 | 8,018 | 9,235 |
| Terminal-Bench | 79.8% | — |
| Remote Labor Index | 4.2% | — |
| τ²-bench Banking | 27.3% | — |
| Cybench | 93% | — |
| DeepResearch Bench | 55.3% | — |
| GBAEval | 44.1% | — |
| GDP.pdf | — | 30.6% |
| LMArena Search | 1253 | — |
| METR Time Horizons | 78.9% | — |
Reasoning Claude Opus 5.5 leads
Claude Opus 4.6: 57.8 (#23), Claude Opus 5.5: 80.2 (#3)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| ARC-AGI-2 | 69.2% | 93.3% |
| NYT Connections (extended) | 92.1% | 88.5% |
| ARC-AGI-1 | 94% | 98.5% |
| EBR-Bench | 12.7% | 71.4% |
| LMArena Hard Prompts | 1527 | 1535 |
| Mystery Game Puzzles | 25% | 71% |
| DTBench | 91.2% | 98.9% |
| LMCA | 55.8% | 68.2% |
| Epoch Capabilities Index | 155.24 | 167.33 |
| SimpleBench | 67.6% | — |
| Kagi LLM Benchmark | 83.6% | — |
| CritPt | — | 31.7% |
| Chess Puzzles | 17% | — |
| EnigmaEval | 7.6% | — |
| Thematic Generalization | 80.6% | — |
| ForecastBench | 60 | — |
Math Claude Opus 5.5 leads
Claude Opus 4.6: 63.0 (#31), Claude Opus 5.5: 91.8 (#3)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 91.2% |
| FrontierMath Tier 4 | 26.8% | 95% |
| OTIS Mock AIME 2024-2025 | 94.4% | 100% |
| ProofBench | 50% | 100% |
| LMArena Math | 1519 | 1506 |
| MathArena Final-Answer Competitions | 78.5% | — |
| FrontierMath (Feb 2025 set) | 40.7% | — |
| FrontierMath Erdős | — | 2.9% |
| FrontierMath Tier 4 (v1) | 22.9% | — |
Knowledge Claude Opus 5.5 leads
Claude Opus 4.6: 61.9 (#26), Claude Opus 5.5: 66.4 (#10)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| GPQA Diamond | 90.5% | 90.6% |
| SimpleQA Verified | 47% | 72.2% |
| LMArena Expert | 1546 | 1547 |
| Humanity's Last Exam | 34.4% | — |
| Vectara Hallucination Rate | 12.2% | — |
Multimodal Claude Opus 5.5 leads
Claude Opus 4.6: 37.3 (#74), Claude Opus 5.5: 57.8 (#1)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| LMArena Vision | 1316 | 1321 |
| Furniture Assembly | 28.3% | 83.3% |
| Blueprint-Bench 2 | — | 51.2% |
| LMArena Document | 1507 | — |
Multilingual Claude Opus 5.5 leads
Claude Opus 4.6: 57.9 (#6), Claude Opus 5.5: 59.1 (#2)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| LMArena Non-English | 1489 | 1507 |
| LMArena Chinese | 1551 | 1588 |
| LMArena French | 1513 | 1514 |
| LMArena Russian | 1497 | 1520 |
| LMArena Spanish | 1510 | 1507 |
| LMArena German | 1502 | — |
| LMArena Japanese | 1484 | — |
| LMArena Korean | 1464 | — |
Instruction Following Too close to call
Claude Opus 4.6: 79.5 (#4), Claude Opus 5.5: 80.0 (#3)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| LMArena Instruction Following | 1523 | 1537 |
Long Context Claude Opus 4.6 leads
Claude Opus 4.6: 48.1 (#13), Claude Opus 5.5: 47.1 (#19)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| LMArena Longer Query | 1520 | 1532 |
| CL-bench | 20.7% | — |
| CL-bench Life | 17% | — |
Writing & Preference Claude Opus 5.5 leads
Claude Opus 4.6: 73.5 (#10), Claude Opus 5.5: 78.2 (#3)
| Benchmark | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| LMArena Text | 1503 | 1515 |
| LMArena Creative Writing | 1505 | 1533 |
| EQ-Bench Creative Writing | 1809 | 2050 |
| LMArena Multi-Turn | 1513 | 1499 |
| EQ-Bench 4 | 1223 | — |
Frequently asked questions
Is Claude Opus 4.6 better than Claude Opus 5.5?
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 58.2 on the Noometry Index.
Which is cheaper, Claude Opus 4.6 or Claude Opus 5.5?
Claude Opus 5.5 is cheaper. It lists at $4 per million input tokens and $20 per million output tokens; Claude Opus 4.6 lists at $5 and $25.
Is Claude Opus 4.6 or Claude Opus 5.5 better for coding?
Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 57.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Opus 4.6 and Claude Opus 5.5 share?
36 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Claude Opus 5.5 has 44.