GLM-5.1
#56 of 274 scored.
Z.aiApr 7, 2026Open weights
Capabilities Index
Range 147.9–151.4
149.8
Context
Takes text
205K
Input
Per 1M tokens
$0.97
Output
Per 1M tokens
$3.04
Benchmarks
How it scores.
- GPQA Diamond86.5%
41st of 186
- SWE-bench Verified74.2%
16th of 32
- FrontierMath36.8%
54th of 81
- SimpleQA Verified34.0%
53rd of 77
- Mock AIME93.3%
41st of 176
Everything else Epoch has for it
- WeirdML57.1%
- SimpleBench46.1%
- APEX-Agents40.9%
- ProofBench22.2%
- FrontierMath-Tier-4-2025-07-01-Private20.8%
- ExploitBench18.1%
- Chess Puzzles14.8%
On the index
Around it.
Sources