Gemini 2.5 Flash Preview (May 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.

49.1 %

44.9–53.4

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

11.0 %

9.7–12.2

independent

Scale Labs

multimodal

VISTA

49.1 %

48.8–49.5

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.

2.7 %

1.8–3.6

independent

Scale Labs