ts-align-benchmarks / Benchmark_eval

Commit History

fix: normalize explicit TSQA choice labels
9dbdae6

fengxr93 commited on

Align caption and TSQA evaluation pipelines
592a672

fengxr93 commited on

Caption-scoring pipeline fixes + with-definitions GLM extractor
60d6a4e

fengxr93 Claude Opus 4.8 commited on

TS-Align benchmark reproduction bundles + canonical eval data + dataset sources
c3efe57

fengxr93 Claude Opus 4.8 commited on