‹ PublicAI Index
The LLM benchmark aggregator.
O3
OpenAI
Strongest in Code generation (#2 of 20), weakest in Toxicity avoidance (#180 of 268). Above par in 25 of 27 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of GLM-5.1 and GLM-5.2.
§ 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.
Coding60−6.2#10/1792/6
Code generation62.5−2.8#2/201/1
Agentic coding58.8−8.1#16/1731/5
Safety57.7−3.7#20/3292/3
Jailbreak resistance62.9−2.1#12/2681/1
Safe-prompt compliance57.1−3.3#20/821/1
Harm refusal58.3−3.2#22/2922/2
Secure code62.8−3.4#33/2701/1
Fairness55.1−14.9#69/2922/2
Toxicity avoidance51.7−7.3#180/2681/1
Core abilities55.1−10.2#43/1991/4
General intelligence57.3−12.1#39/1781/3
Professional54−8.4#43/1941/2
Medical54.6−11.9#47/1491/1
Legal54.2−11.7#52/1731/1
Finance54.2−8.2#60/1621/1
Knowledge52.3−10.2#83/1971/3
Academic knowledge55.5−8.4#55/1231/1
Reasoning51.5−13.9#89/1953/5
Mathematics55.1−8.7#54/1521/2
Science55.6−7.9#54/1221/1
Reasoning46.4−22.6#83/1472/3
Human preference59.7−9.1#93/3541/1
Human preference59.7−9.1#93/3541/1
Agents51.8−14.6#99/2982/6
Tool use68.3−5.7#7/811/1
Computer use39.6−28.5#56/681/2
§ 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 O3, left for the other.
§ 3 · Sources
Where the numbers come from
11 publications, 29 figures. Every one links to the page it was read from.
LMArena Text 1432
ARC-AGI-2 6.5%
LiveCodeBench 75.8%
Aider polyglot 81.3%
BFCL v4 63.05%
OSWorld 23%
Kagi LLM Benchmark 67.6%
SimpleBench 53.1%
Vals · LegalBench 83.76%Vals · CorpFin 59.71%Vals · TaxEval 74.57%Vals · MortgageTax 65.7%Vals · MedQA 96.06%Vals · MedCode 47.29%Vals · MedScribe 76.65%Vals · GPQA Diamond 84.09%Vals · MMLU Pro 85.59%Vals · AIME 85.28%
HELM Safety · HarmBench 98.4%HELM Safety · SimpleSafetyTests 99%HELM Safety · Anthropic Red Team 98.3%HELM Safety · BBQ 97.9%HELM Safety · XSTest 97.3%
Enkrypt · Jailbreak risk 2%Enkrypt · Harmful content risk 6.1%Enkrypt · CBRN risk 9.7%Enkrypt · Toxicity risk 5%Enkrypt · Bias risk 77%Enkrypt · Insecure code risk 7.1%
Badge
[](https://publicai.io/model-index/m/o3)