‹ PublicAI Index
The LLM benchmark aggregator.
Claude 3.7 Sonnet
Anthropic
Strongest in Jailbreak resistance (#2 of 268), weakest in Secure code (#222 of 270). Above par in 15 of 23 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of DeepSeek V4 Flash and Grok 4.1 Fast.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Coding54.5−11.7#43/1791/6
Agentic coding55−11.9#39/1731/5
Safety55.2−6.2#49/3292/3
Jailbreak resistance64.4−0.6#2/2681/1
Harm refusal58.9−2.6#17/2922/2
Toxicity avoidance58−1#31/2681/1
Safe-prompt compliance55.1−5.3#34/821/1
Fairness49.3−20.7#123/2922/2
Secure code37.9−28.3#222/2701/1
Professional53.6−8.8#51/1941/2
Finance54.7−7.7#53/1621/1
Medical53.6−12.9#59/1491/1
Legal53.2−12.7#64/1731/1
Knowledge50.8−11.7#104/1971/3
Academic knowledge51.9−12#73/1231/1
Reasoning45.2−20.2#140/1953/5
Science49.4−14.1#78/1221/1
Reasoning43.7−25.3#96/1472/3
Mathematics44.2−19.6#111/1521/2
Human preference55.5−13.3#145/3541/1
Human preference55.5−13.3#145/3541/1
Agents47.7−18.7#167/2981/6
Computer use45.4−22.7#45/681/2
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Claude 3.7 Sonnet, left for the other.
§ 3 · Sources
Where the numbers come from
8 publications, 24 figures. Every one links to the page it was read from.
LMArena Text 1388
ARC-AGI-2 0.7%
Aider polyglot 64.9%
OSWorld 35.8%
SimpleBench 46.4%
Vals · LegalBench 82.52%Vals · CorpFin 60.41%Vals · TaxEval 74.04%Vals · MortgageTax 66.85%Vals · MedQA 90.22%Vals · GPQA Diamond 75.25%Vals · MMLU Pro 82.73%Vals · AIME 44.58%
HELM Safety · HarmBench 84.3%HELM Safety · SimpleSafetyTests 100%HELM Safety · Anthropic Red Team 99.7%HELM Safety · BBQ 92.1%HELM Safety · XSTest 96.4%
Enkrypt · Jailbreak risk 0.7%Enkrypt · Harmful content risk 1.7%Enkrypt · CBRN risk 4.8%Enkrypt · Toxicity risk 0.7%Enkrypt · Bias risk 84%Enkrypt · Insecure code risk 57.8%
Badge
[](https://publicai.io/model-index/m/claude-3-7-sonnet)