Claude Opus 4.8 vs Claude Opus 5
Different efforts: max · medium · Compare all at high
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Opus 4.821.7
Opus 534.3
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 4.859
Opus 568.9
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Opus 4.8 · high1,556
Opus 5 · max1,689
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math)
Opus 4.854.4
Opus 551.5
SWE-bench Pro (v2 full) SWE-bench Pro (v2 full): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate
Opus 4.8—
Opus 5 · xhigh99.4
SWE-bench Pro (v2 hard) SWE-bench Pro (v2 hard): Agents resolve repository issues under the network-locked v2 protocol; full and 51-task Hard results are separate
Opus 4.8—
Opus 5 · xhigh98
DeepSWE 1 DeepSWE 1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Opus 4.858.2
Opus 5—
Terminal-Bench Science 0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal
Opus 4.8—
Opus 5 · max28.6
Terminal-Bench Hard (version unstated) Terminal-Bench Hard (version unstated): Agents solve difficult software, system-administration and data-processing tasks in a terminal
Opus 4.858.3
Opus 5—
| Benchmark | Opus 4.8 | Opus 5 |
|---|---|---|
| Terminal-Bench 4.0 | 21.7 | 34.3 |
| DeepSWE 1.1 | 59 | 68.9 |
| WebDev Arena | 1,556 · high | 1,689 · max |
| SciCode | 54.4 | 51.5 |
| SWE-bench Pro (v2 full) | — | 99.4 · xhigh |
| SWE-bench Pro (v2 hard) | — | 98 · xhigh |
| DeepSWE 1 | 58.2 | — |
| Terminal-Bench Science 0.1 | — | 28.6 · max |
| Terminal-Bench Hard (version unstated) | 58.3 | — |
Specs
| Spec | Opus 4.8 | Opus 5 |
|---|---|---|
| Input, per 1M | $5 | $5 |
| Output, per 1M | $25 | $25 |
| Cost per task? | $4.08 | $2.19 |
| Speed, tok/s | 66 | 55 |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | May 2026 | Jul 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 4.8 → Opus 5
Nothing known.
Opus 5 → Opus 4.8
Nothing known.