GLM 4p5 Air

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

2 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.

60.8 %

59.0–62.6

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. Sampled at 32K Tokens, temp = null (default temp) · implementation=scale

8.1 %

7.0–9.2

independent

Scale Labs