WFGY/archive/benchmarks_archive/all_suites.yaml

17 lines
206 B
YAML

# benchmarks/all_suites.yaml
all:
- MMLU
- GSM8K
- BBH
- MathBench
- TruthfulQA
- XNLI
- MLQA
- LongBench
- VQAv2
- OK-VQA
efficiency:
- latency
- flops
- energy