BenchMark·Hub

GPQA

A已审核Benchmark
推理通用推理GPQA 家族开放

发布方:Hugging Face

热度10.0±0

GPQA

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

排名模型子项分数Metric时间
#1Steelskull/L3.3-MS-Nevoria-70b
Steelskull
GPQA
hf-open-llm-leaderboard
29.4%score2025-01-17
#2Steelskull/L3.3-Nevoria-R1-70b
Steelskull
GPQA
hf-open-llm-leaderboard
29.2%score2025-02-05
#3Tarek07/Progenitor-V1.1-LLaMa-70B
Tarek07
GPQA
hf-open-llm-leaderboard
27.7%score2025-01-25
#4rootxhacker/Apollo-70B
rootxhacker
GPQA
hf-open-llm-leaderboard
27.6%score2025-03-02
#5Sao10K/70B-L3.3-Cirrus-x1
Sao10K
GPQA
hf-open-llm-leaderboard
26.6%score2025-01-12
#6Triangle104/Set-70b
Triangle104
GPQA
hf-open-llm-leaderboard
26.2%score2025-01-27
#7Daemontatox/Llama3.3-70B-CogniLink
Daemontatox
GPQA
hf-open-llm-leaderboard
26.1%score2025-03-02
#8Tarek07/Thalassic-Alpha-LLaMa-70B
Tarek07
GPQA
hf-open-llm-leaderboard
25.8%score2025-01-28
#9mistralai/Mistral-Large-Instruct-2411
mistralai
GPQA
hf-open-llm-leaderboard
24.9%score2024-11-19
#10OpenBuddy/openbuddy-llama3.3-70b-v24.1-131k
OpenBuddy
GPQA
hf-open-llm-leaderboard
24.6%score2024-12-08
#11pankajmathur/orca_mini_v8_1_70b
pankajmathur
GPQA
hf-open-llm-leaderboard
24.4%score2024-12-21
#12JungZoona/T3Q-Qwen2.5-14B-Instruct-1M-e3
JungZoona
GPQA
hf-open-llm-leaderboard
22.3%score2025-03-09
#13JungZoona/T3Q-qwen2.5-14b-v1.0-e3
JungZoona
GPQA
hf-open-llm-leaderboard
22.3%score2025-03-13
#14newsbang/Homer-v1.0-Qwen2.5-72B
newsbang
GPQA
hf-open-llm-leaderboard
22.1%score2024-12-16
#15Sakalti/ultiima-72B
Sakalti
GPQA
hf-open-llm-leaderboard
21.9%score2025-01-09
#16Sakalti/ultiima-72B-v1.5
Sakalti
GPQA
hf-open-llm-leaderboard
21.8%score2025-01-25
#17Qwen/Qwen2.5-32B
Qwen
GPQA
hf-open-llm-leaderboard
21.6%score2024-09-19
#18shuttleai/shuttle-3
shuttleai
GPQA
hf-open-llm-leaderboard
21.6%score2024-12-04
#19hotmailuser/Mistral-modelstock-24B
hotmailuser
GPQA
hf-open-llm-leaderboard
21.4%score2025-02-13
#20Daemontatox/PathFinderAi3.0
Daemontatox
GPQA
hf-open-llm-leaderboard
21.1%score2025-01-21
#21EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2
EVA-UNIT-01
GPQA
hf-open-llm-leaderboard
21.1%score2024-11-27
#22CultriX/Qwen2.5-14B-ReasoningMerge
CultriX
GPQA
hf-open-llm-leaderboard
21%score2025-02-18
#23MaziyarPanahi/calme-2.2-rys-78b
MaziyarPanahi
GPQA
hf-open-llm-leaderboard
20.9%score2024-08-08
#24zetasepic/Qwen2.5-72B-Instruct-abliterated
zetasepic
GPQA
hf-open-llm-leaderboard
20.9%score2024-11-08
#25NyxKrage/Microsoft_Phi-4
NyxKrage
GPQA
hf-open-llm-leaderboard
20.8%score2024-12-21
4,575 条结果 · 当前 1-25
1 / 183