LetTokenBurn
Sign in
Auto57%Harbor: pendingMath

gsm hard

gsm hard — AI evaluation benchmark listed by opencompass.

PaperRepo

How to run

ltb · gsm-hard
$ npm i -g lettokenburn-cli
$ ltb bench pull gsm-hard

External harness. pip install opencompass && opencompass --models <model_cfg> --datasets gsmhard_gen (OpenCompass dataset config dir 'gsm_hard') https://github.com/open-compass/opencompass

Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs

Scores

0 sourced entries

No sourced scores recorded yet.

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

gsm hard — AI evaluation benchmark listed by opencompass.