Claude Opus 5.5
Anthropic · Flagship · Sep 22, 2026New
The current Opus: frontier coding and knowledge work at a lower price than its predecessor, and the top independent overall score in this catalogue.
- Artificial Analysis Intelligence Index
- 57.6#1 of 29 · max effort
- API price per 1M tokens
- $4 / $20input / output · $8 blended
- Context window
- 1Mup to 128K output tokens
- Output speed
- 95 t/s12m 12s to first answer at max effort
Benchmark results
Each row shows this model (blue) against every other model in the catalogue (grey), worst on the left, best on the right.
Overall capability
- Artificial Analysis Intelligence Index57.6#1 of 29
Max effort, default refusal fallback enabled
- Epoch Capabilities Index167.3#1 of 16
- LiveBench83.2%#2 of 23
Max effort
Coding
- Terminal-Bench 4.064.8%#1 of 13
Claude Code harness, max effort
- Arena WebDev1,814#1 of 27
Max effort
Agents & professional work
- GDPval-AA1,866#1 of 18
- Vending-Bench 2$9,235#4 of 9
Reasoning
- ARC-AGI-293.3%#3 of 11
High effort
- FrontierMath (Tiers 1–3)91.2%#3 of 14
Max effort
- MathArena83.3%#3 of 10
High effort
- SimpleBench88.4%#1 of 12
Knowledge & science
- Humanity's Last Exam (Diamond)55%#2 of 9
- GPQA Diamond90.6%#12 of 14
Max effort
Human preference
- Arena Text1,504#2 of 24
High effort
Reasoning effort trade-offs
The same model at different thinking budgets. More effort buys a higher intelligence score at a higher cost per task and a longer wait. Measured by Artificial Analysis.
| Effort | Score | Cost / task | First answer | Speed |
|---|---|---|---|---|
| Low | 42.3 | $0.55 | 8.7s | 79 t/s |
| Medium | 51.2 | $1.34 | 23s | 77 t/s |
| High | 53.6 | $1.82 | 38s | 76 t/s |
| Xhigh | 56 | $3.46 | 2m 12s | 80 t/s |
| Max (headline score) | 57.6 | $5.98 | 12m 12s | 95 t/s |
Specs & pricing
- Developer
- Anthropic
- Released
- Sep 22, 2026
- Availability
- Generally available
- API model ID
claude-opus-5-5- Weights
- Proprietary (API only)
- Reasoning
- Always on
- Knowledge cutoff
- Jun 2026
- Accepts
- Text, Image
- Produces
- Text
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Input price
- $4 / 1M tokens
- Output price
- $20 / 1M tokens
- Cached input
- $0.20 / 1M tokens
Closest alternatives
Models from other labs nearest to Claude Opus 5.5 on Artificial Analysis Intelligence Index.
GPT-6 Astra
OpenAI
Intelligence 52.7 · $10 / $50
Compare side by sideGemini 4 Argon
Google
Intelligence 52.6 · $2 / $10
Compare side by sideGPT-6.1 Sol
OpenAI
Intelligence 51.8 · $2 / $10
Compare side by side