Skip to content
Leaders Board.
Models/AnthropicClosed

Claude Opus 5.5

#5 of all models across the language-model boards, #1 on 2 boards.
#5
Overall rank
25.3
Podium score
2
Board wins
Sep 17, 2026
Released
3Reasoning5Coding8Speed·Price

Reasoning

Hard questions with checkable answers: science, math, puzzles, expert exams.

1
AA Intelligence
57.6 · of 100
as “Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)”
2
ARC-AGI-2
93.3% · of 78
as “Claude Opus 5.5 (High)”
2
LiveBench
83.2% · of 59
as “claude-opus-5-5-max-effort”

Coding

Fixing real repositories, building web apps, editing code.

1
WebDev Arena
1,818 · of 100
as “claude-opus-5.5-max”

Speed

Output tokens per second on the vendor API.

8
AA Speed
92 tok/s · of 24
as “Claude Opus 5.5 (Adaptive Reasoning, Xhigh Effort, Default Fallback)”

Price

Blended API price per million tokens, cheapest first.

25
AA Price
$8.00 · of 27
as “Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)”

More from Anthropic

Claude Fable 5.1Claude Opus 5Claude Sonnet 5Claude Fable 5Claude Opus 4.8Claude Opus 4.7Claude Sonnet 4.6Claude Opus 4.6

Scores as published by each board on the capture date. Model names and logos belong to their owners; logos via logo.dev.

Weekly: the AI leaderboards with a new #1, Saturday mornings.