.. |
groups
|
[Feature] Support OlympiadBench Benchmark (#1841)
|
2025-01-24 10:00:01 +08:00 |
agent_bench.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
charm_reason.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
chat_OC15_multi_faceted.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
chat_OC15.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
cibench.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
code_passk.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
compassbench_v1_1_objective_public.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
compassbench_v1_1_objective.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
compassbench_v1_3_objective.py
|
[Update] Compassbench v1.3 (#1396)
|
2024-08-12 19:09:19 +08:00 |
compassbench_v1_objective.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
contamination.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
example.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
infinitebench.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
internlm2_keyset.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
lawbench.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
leaderboard.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
leval.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
longbench.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
longeval_v2.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
lveval.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
math_agent.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
math_baseline.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
mathbench_v1.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
mathbench.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
medium.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
mmlu_cf.py
|
[Feature] Support MMLU-CF Benchmark (#1775)
|
2025-01-09 14:11:20 +08:00 |
mmlu_pro.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
mmmlu_lite.py
|
[Feature] Support MMMLU & MMMLU-lite Benchmark (#1565)
|
2024-10-17 19:09:34 +08:00 |
mmmlu.py
|
[Feature] Support MMMLU & MMMLU-lite Benchmark (#1565)
|
2024-10-17 19:09:34 +08:00 |
needlebench.py
|
[Feature] Add long context evaluation for base models (#1666)
|
2024-11-08 10:53:29 +08:00 |
OlympiadBench.py
|
[Feature] Support OlympiadBench Benchmark (#1841)
|
2025-01-24 10:00:01 +08:00 |
plugineval.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
PMMEval.py
|
[Feature] Add P-MMEval (#1714)
|
2024-11-27 21:26:18 +08:00 |
ruler.py
|
[Update] Add RULER 64k config (#1709)
|
2024-11-25 19:35:27 +08:00 |
scicode.py
|
[Feature] Add SciCode summarizer config (#1514)
|
2024-09-10 16:06:02 +08:00 |
simpleqa.py
|
[Feature] Add Openai Simpleqa dataset (#1720)
|
2024-11-28 19:16:07 +08:00 |
small.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
subjective.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
teval.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |
tiny.py
|
[Feature] Support import configs/models/summarizers from whl (#1376)
|
2024-08-01 00:42:48 +08:00 |