GLM 5.2
Cite
Notes
Only stored in your browser.
Context
1.0M
Weights
Open
downloadable
Input
$1.40
/1M tok
Output
$4.40
/1M tok
Cache read
$0.16
0.12x input
Price & speed via Artificial Analysis · ranked across tracked models · caching via OpenRouter
| Reasoning effort | Index | Speed |
|---|---|---|
| max | 33.7 | 0 t/s |
| Non-reasoning | 22.4 | 0 t/s |
Intelligence Index per reasoning-effort setting, via Artificial Analysis · pricing identical across tiers
Reported on 26 evals across 11 domains - best 99.1% on τ²-bench (Tau²-bench) · #1 of 321
Reported eval scores
26IFBench73.3
LiveBench - Math89.8
LiveBench76.7
Vals Index53.1
GPQA Diamond89.5
SciCode51.2
CorpFin v266.1
TaxEval v273.3