Model comparison
Claude Opus 4.1 vs Claude Opus 5
Claude Opus 5 is the stronger model overall, scoring 67.7 to 40.8 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. Claude Opus 4.1 scores higher in 0 categories and Claude Opus 5 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.1 to 22.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 12.6% for Claude Opus 4.1 and 85.6% for Claude Opus 5.
- Claude Opus 5 is cheaper at $5 / $25 per million input/output tokens, against $15 / $75 for Claude Opus 4.1.
- Claude Opus 5 accepts more context: 1M tokens versus 200K.
Side by side
| Claude Opus 4.1 | Claude Opus 5 | |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Noometry Index | 40.8 | 67.7 |
| Released | 2025-08-05 | 2026-07-24 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 32K | 128K |
| Input $ / M tokens | $15 | $5 |
| Output $ / M tokens | $75 | $25 |
| Results tracked | 48 | 57 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 4.1: 44.3 (#69), Claude Opus 5: 67.0 (#5)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| LMArena WebDev | 1390 | 1694 |
| WeirdML | 45.9% | 91.8% |
| LMArena Coding | 1479 | 1533 |
| ALE-Bench | 674.77 | 2,165 |
| SWE-bench Verified | 73.3% | — |
| DeepSWE | — | 73.6% |
| FrontierCode | — | 53.4% |
| CursorBench | — | 46.6% |
| FrontierSWE | — | 52% |
| SciCode | — | 56.4% |
| AlgoTune | 1.34 | — |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 4.1: 34.8 (#38), Claude Opus 5: 55.5 (#1)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| Terminal-Bench | 38% | — |
| APEX-Agents | — | 65.8% |
| OSWorld 2.0 | — | 31.4% |
| GDPval | 43.6% | — |
| τ²-bench Banking | — | 48.7% |
| Cybench | 42% | — |
| DeepResearch Bench | 48.3% | — |
| PostTrainBench | — | 35% |
| BALROG | — | 63.4% |
| GBAEval | — | 79.6% |
| GDP.pdf | — | 24% |
| LMArena Search | 1148 | — |
| METR Time Horizons | 66.8% | — |
| Vending-Bench 2 | — | 11,182 |
Reasoning Claude Opus 5 leads
Claude Opus 4.1: 31.6 (#70), Claude Opus 5: 77.1 (#3)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| SimpleBench | 60% | 80.6% |
| Chess Puzzles | 7% | 42% |
| EBR-Bench | 7.9% | 45.7% |
| LMArena Hard Prompts | 1443 | 1525 |
| Mystery Game Puzzles | 21% | 59% |
| DTBench | 80% | 97.9% |
| LMCA | 37.1% | 64.5% |
| Epoch Capabilities Index | 144.11 | 162.67 |
| ARC-AGI-2 | — | 90.4% |
| NYT Connections (extended) | — | 94.3% |
| ARC-AGI-1 | — | 97.5% |
| CritPt | — | 29.1% |
| EnigmaEval | 7.2% | — |
| Bench to the Future 3 | — | 0.12 |
| ForecastBench | 62 | — |
Math Claude Opus 5 leads
Claude Opus 4.1: 22.0 (#267), Claude Opus 5: 86.1 (#6)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 12.6% | 85.6% |
| FrontierMath Tier 4 | 2.4% | 73.2% |
| OTIS Mock AIME 2024-2025 | 68.9% | 98.9% |
| LMArena Math | 1430 | 1533 |
| ProofBench | — | 99% |
| FrontierMath (Feb 2025 set) | 7.2% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 5 leads
Claude Opus 4.1: 41.9 (#93), Claude Opus 5: 66.8 (#8)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| GPQA Diamond | 77.3% | 93.9% |
| LMArena Expert | 1439 | 1558 |
| Humanity's Last Exam | 11.5% | — |
| SimpleQA Verified | — | 59.9% |
| Confabulations | 17.1% | — |
| Vectara Hallucination Rate | 11.8% | — |
Multimodal Claude Opus 5 leads
Claude Opus 4.1: 26.2 (#114), Claude Opus 5: 51.1 (#6)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| LMArena Vision | — | 1321 |
| VPCT | 35% | — |
| Blueprint-Bench 2 | — | 30.4% |
| Furniture Assembly | — | 60.8% |
| LMArena Document | — | 1516 |
Multilingual Claude Opus 5 leads
Claude Opus 4.1: 52.1 (#90), Claude Opus 5: 58.8 (#3)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| LMArena Non-English | 1405 | 1500 |
| LMArena Chinese | 1427 | 1575 |
| LMArena French | 1432 | 1522 |
| LMArena German | 1412 | 1522 |
| LMArena Japanese | 1378 | 1510 |
| LMArena Korean | 1381 | 1526 |
| LMArena Russian | 1421 | 1507 |
| LMArena Spanish | 1448 | 1519 |
Instruction Following Claude Opus 5 leads
Claude Opus 4.1: 75.8 (#53), Claude Opus 5: 79.3 (#5)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| LMArena Instruction Following | 1436 | 1516 |
Long Context Claude Opus 5 leads
Claude Opus 4.1: 44.5 (#60), Claude Opus 5: 46.5 (#20)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| LMArena Longer Query | 1455 | 1516 |
Writing & Preference Claude Opus 5 leads
Claude Opus 4.1: 62.6 (#70), Claude Opus 5: 79.3 (#2)
| Benchmark | Claude Opus 4.1 | Claude Opus 5 |
|---|---|---|
| LMArena Text | 1419 | 1506 |
| LMArena Creative Writing | 1412 | 1491 |
| LMArena Multi-Turn | 1444 | 1496 |
| Short-Story Creative Writing | 84.7% | — |
| EQ-Bench Creative Writing | — | 2133 |
| EQ-Bench 4 | — | 1385 |
Frequently asked questions
Is Claude Opus 4.1 better than Claude Opus 5?
Claude Opus 5 is the stronger model overall, scoring 67.7 to 40.8 on the Noometry Index.
Which is cheaper, Claude Opus 4.1 or Claude Opus 5?
Claude Opus 5 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; Claude Opus 4.1 lists at $15 and $75.
Is Claude Opus 4.1 or Claude Opus 5 better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.0 versus 44.3 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5 does, with 1M tokens against 200K.
How many benchmarks do Claude Opus 4.1 and Claude Opus 5 share?
31 benchmarks have published results for both models. Claude Opus 4.1 has 48 scored results on Noometry and Claude Opus 5 has 57.