o1 (December 2024)

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

59.3 %

58.0–60.5

independent

Scale Labs

knowledge science

Humanity's Last Exam

contamination=This model was used as an initial filter for the dataset. · implementation=scale

8.0 %

6.9–9.0

independent

Scale Labs

multimodal

VISTA

45.3 %

44.9–45.6

independent

Scale Labs

reasoning math

EnigmaEval

5.7 %

4.3–7.0

independent

Scale Labs