Gemini 2.0 Flash (January 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

3 results

factuality

MASK

thinking

49.5 %

48.8–50.3

independent

Scale Labs

knowledge science

Humanity's Last Exam

contamination=Sampled at temperature 0.7 · implementation=scale

thinking

6.6 %

5.6–7.5

independent

Scale Labs

reasoning math

EnigmaEval

thinking

1.1 %

0.5–1.7

independent

Scale Labs