Anthropic · Benchmarks

Claude Opus 5.5 benchmarks

Claude Opus 5.5 has 6 published scores in this dataset, from a Anthropic release dated 2026-09-22. Its composite index is 98.4, which places it 1st of 22 ranked models. Its strongest area is reasoning (index 100.0) and its weakest is agentic (index 96.7). Its best placing is on Humanity's Last Exam, where its 64.4 ranks 1st of 23 models with a published score.

Closed APIOfficial page

Category profile

Index 0–100: each score relative to the best published score on that test.

ReasoningCodingAgenticKnowledge
Reasoning
100.01 test · not ranked
Coding
97.0#1 of 13 · 2 tests
Agentic
96.71 test · not ranked
Knowledge
100.01 test · not ranked

Model facts

Lab
Anthropic
Type
Closed API
Released
2026-09-22
Context
1M
API price / 1M tokens
$4 in · $20 out

Claude Opus 5.5 pricing and open alternatives

Claude Opus 5.5 is only available through Anthropic's API, so it cannot be self-hosted; it costs $4 per million input tokens and $20 per million output tokens.

Open-weight alternatives

The highest-ranked open models, which you can run on your own GPU.

Claude Opus 5.5 speed and pricing

Measured figures link to their source; estimates are labelled.

API output speed
96 tok/sArtificial Analysis median · Artificial Analysis
Time to first token
2.75 sOpenRouter model page provider stats
API price per 1M tokens
$4.00 in · $20.00 outlab list price · Anthropic pricing docs
Compare speed and price across all models

Score by test

Rank is among every model with a published score on that test.

Humanity's Last Exam64.4%Humanity's Last Exam, no tools; max effort#1 of 23 · top scoreHumanity's Last Exam (with tools)67.7%Humanity's Last Exam, with tools (web search/fetch, code execution); max effort#2 of 17 · 2.3 behind Kimi K3.1 ProSWE-bench Pro89.9%SWE-bench Pro; adaptive thinking max effort; avg of 5 trials#1 of 9 · top scoreTerminal-Bench 4.066.4%Terminal-Bench 4.0; xhigh effort (66.36% in text, safeguards enabled)#2 of 16 · 4.2 behind Claude Sonnet 5.5MMMU-Pro87.7%MMMU-Pro (not original MMMU); AA independent run (Max, Default Fallback)#1 of 9 · top scoreLMArena Text Elo1509LMArena Text, Overall; snapshot Oct 27, 2026; Claude Opus 5.5 (High); +/-7#2 of 21 · 11 behind Gemini 4 Argon

Nearby in the composite ranking

Models with the closest composite index.

  1. 1Claude Opus 5.598.4
  2. 2Kimi K3.1 Pro94.4
  3. 3Claude Sonnet 5.591.9
  4. 4GPT-6 Astra91.4

Head-to-head comparisons

Side-by-side pages built from the tests both models report.

Sources

ModelTestScoreSettingSource
Claude Opus 5.5Humanity's Last Exam64.4Humanity's Last Exam, no tools; max effortAnthropic Claude Opus 5.5 System Card (Table 8.1.A)
Claude Opus 5.5Humanity's Last Exam (with tools)67.7Humanity's Last Exam, with tools (web search/fetch, code execution); max effortAnthropic Claude Opus 5.5 System Card (Table 8.1.A); also in launch post
Claude Opus 5.5SWE-bench Pro89.9SWE-bench Pro; adaptive thinking max effort; avg of 5 trialsAnthropic Claude Opus 5.5 System Card (Table 8.1.A / sec 8.2)
Claude Opus 5.5Terminal-Bench 4.066.4Terminal-Bench 4.0; xhigh effort (66.36% in text, safeguards enabled)Anthropic Claude Opus 5.5 System Card (Table 8.1.A / sec 8.5)
Claude Opus 5.5MMMU-Pro87.7MMMU-Pro (not original MMMU); AA independent run (Max, Default Fallback)Artificial Analysis
Claude Opus 5.5LMArena Text Elo1509LMArena Text, Overall; snapshot Oct 27, 2026; Claude Opus 5.5 (High); +/-7LMArena (arena.ai) Text leaderboard

Scores are published results from model cards, lab reports, and public leaderboards, each linked to its source. Settings such as thinking mode or test version differ between sources and are shown next to each score. OpenLLM Buddy catalog models are uncensored fine-tunes; their scores are those of the official base model. Data collected 2026-10-30. How the index works