o3 (high) (April 2025)

release date unknown

BenchAtlas Index

as of 2026-07-14

Not enough benchmark coverage for a composite score (needs ≥4 families across ≥3 categories). The per-benchmark evidence below stands on its own — sparse coverage is an evidence gap, not a low score.

Benchmark evidence

4 results

factuality

MASK

contamination=Potential contamination warning: This model was evaluated after the public release of MASK, allowing model builder access to the prompts and solutions.

84.5 %

82.1–86.8

independent

Scale Labs

knowledge science

Humanity's Last Exam

contamination=Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. · implementation=scale

20.3 %

18.7–21.9

independent

Scale Labs

multimodal

VISTA

50.1 %

48.9–51.2

independent

Scale Labs

reasoning math

EnigmaEval

contamination=Potential contamination warning: This model was evaluated after the public release of EnigmaEval, allowing model builder access to the prompts and solutions.

11.9 %

10.1–13.8

independent

Scale Labs