‹ PublicAI Index
The LLM benchmark aggregator.
Claude Opus 4
Anthropic
Strongest in Jailbreak resistance (#12 of 268), weakest in Secure code (#136 of 270). Above par in 20 of 25 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of Gemini 2.5 Pro and Qwen3.7 Max.
§ 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.
Core abilities57.4−7.9#26/1991/4
General intelligence60.6−8.8#23/1781/3
Safety56.4−5#36/3293/3
Jailbreak resistance62.9−2.1#12/2681/1
Safe-prompt compliance56.4−4#25/821/1
Fairness62.6−7.4#27/2922/2
Toxicity avoidance57.8−1.2#34/2681/1
Harm refusal55.6−5.9#58/2922/2
Factual grounding44.8−25.9#77/1041/1
Secure code51.6−14.6#136/2701/1
Coding54.6−11.6#41/1792/6
Code generation50.4−14.9#13/201/1
Agentic coding56.6−10.3#26/1731/5
Professional52.3−10.1#66/1941/2
Medical55−11.5#42/1491/1
Legal53.6−12.3#59/1731/1
Finance50.6−11.8#94/1621/1
Knowledge52.6−9.9#77/1971/3
Academic knowledge56.2−7.7#47/1231/1
Human preference59.2−9.6#101/3541/1
Human preference59.2−9.6#101/3541/1
Reasoning46.4−19#127/1953/5
Reasoning48.4−20.6#73/1472/3
Science47−16.5#86/1221/1
Mathematics43.4−20.4#117/1521/2
§ 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 Opus 4, left for the other.
§ 3 · Sources
Where the numbers come from
10 publications, 25 figures. Every one links to the page it was read from.
LMArena Text 1426
ARC-AGI-2 8.6%
LiveCodeBench 56.6%
Aider polyglot 72%
Kagi LLM Benchmark 74.3%
SimpleBench 58.8%
Vals · LegalBench 83.07%Vals · TaxEval 71.91%Vals · MortgageTax 58.59%Vals · MedQA 92.87%Vals · GPQA Diamond 71.72%Vals · MMLU Pro 86.17%Vals · AIME 41.25%
HELM Safety · HarmBench 91.7%HELM Safety · SimpleSafetyTests 100%HELM Safety · Anthropic Red Team 98.9%HELM Safety · BBQ 97.1%HELM Safety · XSTest 97%
Enkrypt · Jailbreak risk 2%Enkrypt · Harmful content risk 1.1%Enkrypt · CBRN risk 25%Enkrypt · Toxicity risk 0.8%Enkrypt · Bias risk 56.6%Enkrypt · Insecure code risk 29.8%
Vectara · Factual consistency 88%
Badge
[](https://publicai.io/model-index/m/claude-opus-4)