chatglm2-6b
#252 of 274 scored.
Z.aiJun 24, 2023
Capabilities Index
Range 81.0–105.5
98.9
Context
Tokens
—
Input
Per 1M tokens
—
Output
Per 1M tokens
—
Benchmarks
No independent scores yet.
Epoch AI hasn't run chatglm2-6b yet. Its scores show up here the morning after they do.
Everything else Epoch has for it
- LAMBADA54.3%
- ARC AI248.0%
- HellaSwag42.7%
- PIQA39.2%
- GSM8K32.4%
- MMLU30.5%
- BBH11.6%
On the index
Around it.
Sources