GLM-5
#81 of 274 scored.
Z.aiFeb 11, 2026Open weights
Capabilities Index
Range 143.8–147.7
145.8
Context
Takes text
205K
Input
Per 1M tokens
$0.60
Output
Per 1M tokens
$1.92
Benchmarks
How it scores.
- GPQA Diamond83.8%
51st of 186
- SWE-bench Verified72.1%
22nd of 32
- ARC-AGI-24.9%
52nd of 79
- Mock AIME80.0%
80th of 176
- Terminal-Bench52.4%
13th of 35
Everything else Epoch has for it
- WeirdML48.2%
- ARC-AGI44.7%
- SimpleBench43.8%
- FrontierMath-2025-02-28-Private28.8%
- CL-bench18.7%
- Chess Puzzles5.3%
- FrontierMath-Tier-4-2025-07-01-Private3.5%
On the index
Around it.
Sources