mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
![]() * [Update] Add dataset configurations of no max_out_len * update test torch version * update test torch version * update test torch version * update test torch version |
||
---|---|---|
.. | ||
cmo_fib_0shot_notcot_gen_4c6c29.py | ||
cmo_fib_gen_2783e5.py | ||
cmo_fib_gen_ace24b.py | ||
cmo_fib_gen.py | ||
README.md |
Description
Math dataset composed of problems from CMO (Chinese Mathematical Olympiad) 2009-2022 .
Performance
Qwen2.5-Math-72B-Instruct | Qwen2.5-Math-7B-Instruct | Qwen2-Math-7B-Instruct | Qwen2-Math-1.5B-Instruct | internlm2-math-7b |
---|---|---|---|---|
46.15 | 42.79 | 31.73 | 23.56 | 3.37 |
Qwen2.5-72B-Instruct | Qwen2.5-7B-Instruct | internlm2_5-7b-chat |
---|---|---|
20.00 | 16.67 | 6.67 |