Skip to content
Leaders Board.
Models/AnthropicClosed

Claude Opus 4.1

Ranked on the boards below.
-
Overall rank
-
Podium score
0
Board wins
Aug 5, 2025
Released
·Chat·Reasoning·Coding·Agents and tools

Chat

Which model people prefer in blind head-to-head conversations.

14
MultiChallenge
57.2% · of 29
as “claude-opus-4-1-20250805-thinking”
57
Text Arena
1,450 · of 100
as “claude-opus-4-1-20250805-thinking-16k”

Reasoning

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

23
HLE
11.5% · of 42
as “claude-opus-4-1-20250805-thinking”
78
GPQA Diamond
77.3% · of 100
as “claude-opus-4-1-20250805_16K”
82
Epoch ECI
144.1 · of 100
as “Claude Opus 4.1”

Coding

Fixing real repositories, building web apps, editing code.

70
WebDev Arena
1,389 · of 100
as “claude-opus-4-1-20250805”

Agents and tools

Calling functions and tools, using MCP servers, searching the web.

25
Search Arena
1,148 · of 33
as “claude-opus-4-1-search”

More from Anthropic

Claude Opus 5.5Claude Fable 5.1Claude Opus 5Claude Sonnet 5Claude Fable 5Claude Opus 4.8Claude Opus 4.7Claude Sonnet 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.