> Claude Opus 5.5 is a closed AI model from Anthropic, released 22 Sep 2026. Index score 200 (GPT-4 = 100), rank 1 of 229 ranked models. API price $4.0 in / $20 out per million tokens, 1M context. [Models](https://themodelindex.org/models/) /[Anthropic](https://themodelindex.org/labs/anthropic/) # Claude Opus 5.5 Anthropic Released 22 Sep 2026 Closed Flagship Date verified [Compare](https://themodelindex.org/compare/claude-opus-5-5-vs-kimi-k3/) [Announcement](https://www.anthropic.com/claude-opus-5-5) 200188–211 Index score #1 of 229 models 4/ 8 Core tests taken 4 of 6 areas · plus 13 anchor tests Frontier Versus the frontier at release set or matched the record $4.0/ $20 Price per million tokens input / output, list price 1M Context window tokens it reads at once ## Where it sits · on the frontier _Chart: Model Index score of every scored model since late 2022, with the best closed and best open model over time_ Among the first models to reach this score. ## Test results · by area · tick = best by any model Show 11 anchor tests Reasoning & knowledge evidence GPQA Diamond 91% Humanity's Last Exam no result Maths evidence FrontierMath T1-3 91% Coding evidence SWE-bench Verified no result Terminal-Bench no result Agents evidence APEX-Agents 74% Novel problems evidence ARC-AGI-2 93% Long tasks no evidence yet METR time horizon no result Independent results from the Epoch AI benchmarking hub, best reasoning setting. The core tests are shown here; anchor tests also inform the score and can be shown above. ## What others say · rank on each leaderboard The Model Index independent tests, our method #1 of 219 · 200 Epoch Capabilities Index overall capability from many benchmarks #1 of 239 · 167.3 Artificial Analysis Intelligence Index overall capability across ten evaluations #1 of 207 · 58 LMArena · Creative writing creative writing #2 of 386 · 1515 LMArena · WebDev building web apps and front ends #1 of 123 · 1818 LMArena · Text overall chat quality, judged by people #4 of 388 · 1504 LMArena · Maths maths questions in chat #8 of 373 · 1510 LMArena · Coding coding questions in chat #11 of 383 · 1538 LiveBench · Overall overall, with fresh questions to limit contamination #2 of 58 · 83.2 Further left is better. Leaderboards measure different things: LMArena is people voting blind between two answers, the others are test scores. Click any row for the source. ## Best at · top three among current models 1st building web apps and front ends LMArena · WebDev 1st coding questions LiveBench · Coding 1st agentic coding questions LiveBench · Agentic Coding 1st mathematics questions LiveBench · Mathematics 2nd creative writing LMArena · Creative writing 2nd APEX-Agents Epoch AI · independent 2nd ARC-AGI-2 Epoch AI · independent 3rd reasoning questions LiveBench · Reasoning 3rd FrontierMath T1-3 Epoch AI · independent Where this model places in the top three of today's models, on category leaderboards and on our core tests. ## Where to use it · prices checked 1 Oct 2026 #### From the lab Claude app · subscription ↗ Claude API API ↗ #### API providers · 5 · per million tokens, in / out A Amazon Bedrock $4.4 / $22 cheapest A Azure $4.4 / $22 ↗ G Google $4.4 / $22 ↗ C Claude Platform on AWS $4.0 / $20 ↗ A Anthropic $8.0 / $40 ↗ Provider prices come from OpenRouter's live listing; going direct to a provider can differ. Subscriptions are the lab's own apps. ## Facts and sources Released 22 Sep 2026 Announcement [anthropic.com ↗](https://www.anthropic.com/claude-opus-5-5) Release entry Claude Opus 5.5 Scored as Claude Opus 5.5 Artificial Analysis index 58 · max with fallback Output speed 90 tokens/s Hugging Face closed weights ## Anthropic releases · around this one Claude Fable 5.1 Closed 1 SEP 2026 index 192 Claude Mythos 5.1 Closed 1 SEP 2026 Claude Opus 5.5 Closed 22 SEP 2026 index 200 Claude Sonnet 5.5 Closed 28 SEP 2026 index 193 --- Source: https://themodelindex.org/models/claude-opus-5-5/ · The Model Index · data as of 2026-10-01