Claude Opus 5 vs GPT-5.6 Sol
Humanity's Last Exam Humanity's Last Exam: Very hard expert questions across many fields, written to stump today’s models
Opus 551.3
GPT-5.6 Sol42.2
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 534.3
GPT-5.6 Sol14.6
AutomationBench-AA AutomationBench-AA: Agents orchestrate SaaS workflows through APIs; objectives receive credit only when the task has no guardrail violation
Opus 554.3
GPT-5.6 Sol51.3
Arena Text · creative writing Arena Text · creative writing: Human pairwise preferences in the stated text vote pool
Opus 5 · max1,471
GPT-5.6 Sol · xhigh1,469
MMMU-Pro (vision) MMMU-Pro (vision): College-level questions that require understanding images: charts, diagrams, photos
Opus 581.6
GPT-5.6 Sol81.4
| Benchmark | Opus 5 | GPT-5.6 Sol |
|---|---|---|
| Humanity's Last Exam | 51.3 | 42.2 |
| Terminal-Bench 4.0 | 34.3 | 14.6 |
| AutomationBench-AA | 54.3 | 51.3 |
| Arena Text · creative writing | 1,471 · max | 1,469 · xhigh |
| MMMU-Pro (vision) | 81.6 | 81.4 |
Specs
| Spec | Opus 5 | GPT-5.6 Sol |
|---|---|---|
| Input, per 1M | $5 | $4 |
| Output, per 1M | $25 | $20 |
| Cost per task? | $2.19 | $0.50 |
| Speed, tok/s | 55 | 85 |
| Context | 1M | 1.05M |
| Weights | Closed | Closed |
| Released | Jul 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 5 → GPT-5.6 Sol
Nothing known.
GPT-5.6 Sol → Opus 5