Codesota · Models · Claude 3.7 SonnetAnthropic10 results · 10 benchmarks
Model card

Claude 3.7 Sonnet.

Anthropicapi
§ 02 · Benchmarks

Every benchmark Claude 3.7 Sonnet has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01RE-BenchAgentic AI · RE-Benchnormalized-score0.3%#2/52025-04-01source ↗
02HCASTAgentic AI · HCASTsuccess-rate38.0%#3/62025-04-01source ↗
03METR Time HorizonAgentic AI · Time Horizontask-horizon-minutes14.0%#3/52025-04-01source ↗
04WebArenaAgentic AI · Web & Desktop Agentssuccess-rate35.1%#5/62025-02-24source ↗
05ARC-AGI-1Reasoning · Logical Reasoningaccuracy30.0%#5/5source ↗
06AIME 2024Reasoning · Mathematical Reasoningaccuracy80.0%#8/11source ↗
07MATHReasoning · Mathematical Reasoningaccuracy96.2%#9/46source ↗
08OSWorldAgentic AI · Web & Desktop Agentssuccess-rate28.0%#19/28source ↗
09SWE-Bench VerifiedComputer Code · Code Generationresolve-rate63.7%#27/39source ↗
10SWE-bench VerifiedAgentic AI · SWE-benchresolve-rate70.3%#38/81source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Claude 3.7 Sonnet actually performs.

Reasoning
3
benchmarks
avg rank #7.3
Agentic AI
6
benchmarks
avg rank #11.7
Computer Code
1
benchmark
avg rank #27.0
§ 04 · Papers

2 papers with results for Claude 3.7 Sonnet.

  1. 2025-04-01· Agentic AI· 3 results

    METR: Measuring Autonomy in AI Systems (2025 Update)

  2. 2025-02-24· Agentic AI· 1 result

    Claude 3.7 Sonnet System Card

§ 05 · Related models

Other Anthropic models scored on Codesota.

Claude Opus 4
Undisclosed params · 14 results · 2 SOTA
Claude Sonnet 5
Undisclosed params · 2 results · 2 SOTA
Claude Sonnet 4
11 results · 1 SOTA
Claude Opus 4.5
4 results · 1 SOTA
Claude Opus 4.7
2 results · 1 SOTA
Claude Mythos Preview
1 result · 1 SOTA
Claude 3.5 Sonnet
Undisclosed params · 28 results
Claude Opus 4.5
Undisclosed params · 12 results
§ 06 · Sources & freshness

Where these numbers come from.

arxiv
3
results
official-leaderboard
2
results
anthropic-blog
2
results
arcprize-leaderboard
1
result
anthropic-model-card
1
result
editorial
1
result
8 of 10 rows marked verified. · first result 2025-02-24, latest 2025-04-01.