Skip to content
Leaders Board.
Models/AnthropicClosed

Claude 3.7 Sonnet

Ranked on the boards below.
-
Overall rank
-
Podium score
0
Board wins
Feb 24, 2025
Released
·Reasoning·Coding

Reasoning

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

29
HLE
8.0% · of 42
as “Claude 3.7 Sonnet (Thinking)”
39
MMLU-Pro
84.0% · of 100 · stale since 2026-03-11
as “Claude-3.7-Sonnet-Thinking”
100
Epoch ECI
141.2 · of 100
as “Claude 3.7 Sonnet”

Coding

Fixing real repositories, building web apps, editing code.

28
SWE-bench Verified
52.8% · of 39 · stale since 2026-02-26
as “Claude 3.7 Sonnet (20250219)”

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.