Claude Opus 4.5 vs Claude Opus 4.6
Different efforts: non-thinking · high · Compare all at high
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Opus 4.5 · high1,494
Opus 4.61,547
SWE-bench Pro (private) SWE-bench Pro (private): Agents resolve long-horizon professional repository tasks; public and private splits are separate
Opus 4.523.4
Opus 4.647.1
Terminal-Bench Hard (version unstated) Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal
Opus 4.540.9
Opus 4.648.5
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 4.5—
Opus 4.6 · max31.9
DeepSWE 1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 4.5—
Opus 4.6 · max27.6
| Benchmark | Opus 4.5 | Opus 4.6 |
|---|---|---|
| WebDev Arena | 1,494 · high | 1,547 |
| SWE-bench Pro (private) | 23.4 | 47.1 |
| Terminal-Bench Hard (version unstated) | 40.9 | 48.5 |
| DeepSWE 1.1 | — | 31.9 · max |
| DeepSWE 1 | — | 27.6 · max |
Specs
| Spec | Opus 4.5 | Opus 4.6 |
|---|---|---|
| Input, per 1M | $5 | $5 |
| Output, per 1M | $25 | $25 |
| Speed, tok/s | 51 | 45 |
| Context | 200K | 1M |
| Weights | Closed | Closed |
| Released | Nov 2025 | Feb 2026 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | Partial |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
Opus 4.5 → Opus 4.6
Nothing known.
Opus 4.6 → Opus 4.5