‹ PublicAI Index
The LLM benchmark aggregator.
O3 Pro
OpenAI
Strongest in Agentic coding (#14 of 173, on 1 of its 5 boards), weakest in Safety (#304 of 327). Above par in 4 of 8 scopes. Among the models it meets almost everywhere, it finishes behind GPT-6 Astra and Gemini 4 Argon and ahead of Grok 4.7 and Gemini 3.1 Flash-Lite.
§ 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.
Coding58.8−7.3#16/1791/6
Agentic coding59.7−7#14/1731/5
Core abilities56.6−9#33/2001/4
General intelligence59.5−9.5#30/1801/3
Reasoning46−19.4#128/1951/5
Reasoning42.9−26.1#99/1471/3
Safety42.5−18.9#304/3271/3
Factual grounding26−44.7#102/1041/1
§ 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 O3 Pro, left for the other.
§ 3 · Sources
Where the numbers come from
4 publications, 4 figures. Every one links to the page it was read from.
ARC-AGI-2 4.9%
Aider polyglot 84.9%
Kagi LLM Benchmark 72.1%
Vectara · Factual consistency 76.7%
Badge
[](https://publicai.io/model-index/m/o3-pro)