Claude Opus 5 vs Claude Opus 5.5
EBR Bench?
Opus 5at max45.7
Opus 5.5at max71.4
Harvey LAB-AA 1.1?
Opus 5—
Opus 5.5at max4.2
SpireClimb?
Opus 5—
Opus 5.5at max3.3
SpireClimb StS1 A20 Heart?
Opus 5—
Opus 5.5at max0
SpireClimb StS2 A10?
Opus 5—
Opus 5.5at max6.7
| Benchmark | Opus 5 | Opus 5.5 |
|---|---|---|
| AutomationBench-AA | 54.3 | 61.2 |
| GDPval-AA (work tasks) 2.1 | 1,491.2 | 1,593.3 |
| AA Analyst Agent | 53.8 · max | 56.3 · max |
| Terminal-Bench 4.0 | 34.3 | 52.5 |
| Terminal-Bench Science 0.1 | 28.6 · max | 43.3 |
| AA-Briefcase 1.1 · Elo | 1,432.7 | 1,620.9 |
| AA-LCR (long context) 1.1 | 82 | 84.3 |
| DeepSWE 1.1 | 68.9 | 72.3 · max |
| EBR Bench | 45.7 · max | 71.4 · max |
| Furniture Assembly | 60.8 · max | 83.3 · max |
| τ³-bench · banking · 1.0.1 | 48.7 · max | — |
| τ³-Banking · AA | 38.6 | — |
| ITBench SRE | — | 38.2 · max |
| EnterpriseOps-Gym-AA | 47.5 · max | — |
| FrontierCode 1.1 | — | 57.1 |
| Harvey LAB-AA 1.1 | — | 4.2 · max |
| SWE-bench Pro (v2 full) | 99.4 · xhigh | — |
| SWE-bench Pro (v2 hard) | 98 · xhigh | — |
| SpireClimb | — | 3.3 · max |
| SpireClimb StS1 A20 Heart | — | 0 · max |
| SpireClimb StS2 A10 | — | 6.7 · max |
Specs
| Spec | Opus 5 | Opus 5.5 |
|---|---|---|
| Input, per 1M | $5 | $4 |
| Output, per 1M | $25 | $20 |
| Cost per task? | $2.19 | $1.34 |
| Speed, tok/s | 51 | 82 |
| Context | 1M | 1M |
| Weights | Closed | Closed |
| Released | Jul 2026 | Sep 2026 |
| See images | ✓ | ✓ |
| Read PDFs | Partial | ✓ |
| Hear audio | — | — |
| Watch video | — | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | — |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ✓ |
| Run code | ? | ✓ |
| Use a computer | ? | ✓ |
What breaks when you switch
Opus 5 → Opus 5.5
No forced tool use›
Forced tool_choice any or tool returns HTTP 400; remove the forced choice.
Thinking is always on›
Disabled thinking or a manual budget returns HTTP 400; omit thinking or use adaptive thinking.
Remove sampling parameters›
Non-default temperature, top_p or top_k returns HTTP 400; omit these parameters and use prompting.
No assistant prefill›
Assistant prefill returns HTTP 400; use structured outputs or system instructions, with system instructions on Bedrock.
Old computer tool rejected · Claude API / Google Cloud›
The computer_20251124 tool returns HTTP 400 on the Claude API and Google Cloud; use computer_toolset_20260801 there.
Return thinking blocks unmodified›
Edited, reordered or partially dropped thinking blocks return HTTP 400; echo assistant messages complete and unmodified with tool results.
Opus 5.5 → Opus 5
Nothing known.