‹ PublicAI Index
The LLM benchmark aggregator.
Claude Opus 4.1
Anthropic
Strongest in Academic knowledge (#23 of 123), weakest in Safety (#221 of 329). Above par in 12 of 14 scopes. Among the models it meets almost everywhere, it finishes behind GPT-5.5 and Claude Opus 5 and ahead of Qwen3.5 Flash and Grok 3 Mini.
§ 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.
Knowledge53.5−9#53/1971/3
Academic knowledge58.4−5.5#23/1231/1
Human preference61.5−7.3#65/3541/1
Human preference61.5−7.3#65/3541/1
Professional52.1−10.3#71/1941/2
Legal53.9−12#56/1731/1
Medical53−13.5#64/1491/1
Finance50.5−11.9#97/1621/1
Reasoning52.4−13#75/1952/5
Reasoning53.2−15.8#52/1471/3
Mathematics53.2−10.6#69/1521/2
Science50.1−13.4#76/1221/1
Safety48.5−12.9#221/3291/3
Factual grounding45.3−25.4#75/1041/1
§ 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 4.1, left for the other.
§ 3 · Sources
Where the numbers come from
4 publications, 12 figures. Every one links to the page it was read from.
LMArena Text 1450
SimpleBench 60%
Vals · LegalBench 83.46%Vals · TaxEval 73.67%Vals · MortgageTax 56.12%Vals · MedQA 93.59%Vals · MedCode 47.23%Vals · MedScribe 73.9%Vals · GPQA Diamond 76.26%Vals · MMLU Pro 87.92%Vals · AIME 78.18%
Vectara · Factual consistency 88.2%
Badge
[](https://publicai.io/model-index/m/claude-opus-4-1)