BenchMark·Hub

MMLU-Pro

S高可信Benchmark
知识问答通用问答MMLU 家族开放mit

发布方:TIGER-Lab

热度66.0▼ 0.1

MMLU-Pro

hf-open-llm-leaderboard / score · 4,575 行结果

排名模型子项分数Metric时间
#1MaziyarPanahi/calme-3.2-instruct-78b
MaziyarPanahi
MMLU-Pro
hf-open-llm-leaderboard
70%score2024-11-28
#2MaziyarPanahi/calme-3.1-instruct-78b
MaziyarPanahi
MMLU-Pro
hf-open-llm-leaderboard
68.7%score2024-11-27
#3dfurman/CalmeRys-78B-Orpo-v0.1
dfurman
MMLU-Pro
hf-open-llm-leaderboard
66.8%score2024-09-24
#4MaziyarPanahi/calme-2.4-rys-78b
MaziyarPanahi
MMLU-Pro
hf-open-llm-leaderboard
66.7%score2024-09-03
#5glaiveai/Reflection-Llama-3.1-70B
glaiveai
MMLU-Pro
hf-open-llm-leaderboard
59.3%score2024-10-07
#6arcee-ai/Arcee-Blitz
arcee-ai
MMLU-Pro
hf-open-llm-leaderboard
57.3%score2025-02-21
#7newsbang/Homer-v1.0-Qwen2.5-72B
newsbang
MMLU-Pro
hf-open-llm-leaderboard
57.2%score2024-12-16
#8Sakalti/ultiima-72B-v1.5
Sakalti
MMLU-Pro
hf-open-llm-leaderboard
56.2%score2025-01-25
#9Qwen/Qwen2.5-72B
Qwen
MMLU-Pro
hf-open-llm-leaderboard
55.2%score2024-09-19
#10Aryanne/QwentileSwap
Aryanne
MMLU-Pro
hf-open-llm-leaderboard
55%score2025-02-05
#11rombodawg/Rombos-LLM-V2.5-Qwen-72b
rombodawg
MMLU-Pro
hf-open-llm-leaderboard
54.8%score2024-12-19
#12rombodawg/Rombos-LLM-V2.5-Qwen-32b
rombodawg
MMLU-Pro
hf-open-llm-leaderboard
54.6%score2024-10-07
#13fblgit/TheBeagle-v2beta-32B-MGS
fblgit
MMLU-Pro
hf-open-llm-leaderboard
54.6%score2024-10-30
#14sakaltcommunity/novablast-preview
sakaltcommunity
MMLU-Pro
hf-open-llm-leaderboard
54.6%score2024-12-18
#15fblgit/TheBeagle-v2beta-32B-MGS
fblgit
MMLU-Pro
hf-open-llm-leaderboard
54.6%score2024-10-20
#16Sakalti/ultiima-32B
Sakalti
MMLU-Pro
hf-open-llm-leaderboard
54.6%score2024-12-23
#17Sakalti/Oxyge1-33B
Sakalti
MMLU-Pro
hf-open-llm-leaderboard
54.5%score2024-12-18
#18hotmailuser/RombosBeagle-v2beta-MGS-32B
hotmailuser
MMLU-Pro
hf-open-llm-leaderboard
54.5%score2024-12-23
#19Sakalti/ultiima-72B
Sakalti
MMLU-Pro
hf-open-llm-leaderboard
54.5%score2025-01-09
#20JungZoona/T3Q-Qwen2.5-14B-Instruct-1M-e3
JungZoona
MMLU-Pro
hf-open-llm-leaderboard
54.3%score2025-03-09
#21JungZoona/T3Q-qwen2.5-14b-v1.0-e3
JungZoona
MMLU-Pro
hf-open-llm-leaderboard
54.3%score2025-03-13
#22maldv/Qwentile2.5-32B-Instruct
maldv
MMLU-Pro
hf-open-llm-leaderboard
54.2%score2024-12-19
#23zetasepic/Qwen2.5-72B-Instruct-abliterated
zetasepic
MMLU-Pro
hf-open-llm-leaderboard
54.1%score2024-11-08
#24rootxhacker/Apollo_v2-32B
rootxhacker
MMLU-Pro
hf-open-llm-leaderboard
54.1%score2025-03-11
#25Baptiste-HUVELLE-10/LeTriomphant2.2_ECE_iLAB
Baptiste-HUVELLE-10
MMLU-Pro
hf-open-llm-leaderboard
53.9%score2025-02-28
4,575 条结果 · 当前 1-25
1 / 183