Leaderboards

RankModelScoreMetricEvaluatedSource
1zhengr/MixTAO-7Bx2-MoE-v8.1
20.52score11/8/2025link
2Qwen2.5-72B-Instruct-abliterated
54.13score11/8/2025link
3Qwen2.5-32B-Instruct-abliterated-v2
51.35score11/8/2025link
4recoilme-gemma-2-psy10k-mental_healt-9B-v0.1
35.34score11/8/2025link
5recoilme-gemma-2-Ifable-9B-v0.1
36.93score11/8/2025link
6recoilme-gemma-2-Gutenberg-Doppel-9B-v0.1
36.84score11/8/2025link
7recoilme-gemma-2-Ataraxy-9B-v0.2
36.92score11/8/2025link
8recoilme-gemma-2-Ataraxy-9B-v0.1-t0.75
34.90score11/8/2025link
9recoilme-gemma-2-Ataraxy-9B-v0.1-t0.25
37.78score11/8/2025link
10recoilme-gemma-2-Ataraxy-9B-v0.1
36.90score11/8/2025link
11gemma-2-S2MTM-9B
36.63score11/8/2025link
12Test01012025155054t0.5_gemma-2
1.00score11/8/2025link
13zelk12/Test01012025155054
1.00score11/8/2025link
14T31122024203920-gemma-2-9B
37.47score11/8/2025link
15Rv0.4MT4g2-gemma-2-9B
37.97score11/8/2025link
16Rv0.4DMv1t0.25Tt0.25-gemma-2-9B
37.19score11/8/2025link
17Rv0.4DMv1t0.25-gemma-2-9B
37.79score11/8/2025link
18MTMaMe-Merge_02012025163610-gemma-2-9B
37.57score11/8/2025link
19MTM-Merge-gemma-2-9B
37.65score11/8/2025link
20MT5-gemma-2-9B
37.41score11/8/2025link
21MT5-Max-Merge_02012025163610-gemma-2-9B
37.67score11/8/2025link
22MT5-Gen5-gemma-2-9B
36.99score11/8/2025link
23MT5-Gen4-gemma-2-9B
37.74score11/8/2025link
24MT5-Gen3-gemma-2-9B
37.50score11/8/2025link
25MT5-Gen2-gemma-2-9B
37.55score11/8/2025link
26MT5-Gen1-gemma-2-9B
37.43score11/8/2025link
27MT4-gemma-2-9B
37.40score11/8/2025link
28MT4-Max-Merge_02012025163610-gemma-2-9B
37.68score11/8/2025link
29MT4-Gen5-gemma-2-9B
37.60score11/8/2025link
30MT4-Gen4-gemma-2-9B
36.93score11/8/2025link
31MT4-Gen3-gemma-2-9B
37.56score11/8/2025link
32MT4-Gen2-gemma-2-9B
37.42score11/8/2025link
33MT4-Gen1-gemma-2-9B
37.66score11/8/2025link
34MT3-gemma-2-9B
36.96score11/8/2025link
35MT3-Max-Merge_02012025163610-gemma-2-9B
37.66score11/8/2025link
36MT3-Gen6-gemma-2-9B
34.47score11/8/2025link
37MT3-Gen5-gemma-2-9B_v1
37.32score11/8/2025link
38MT3-Gen5-gemma-2-9B
36.85score11/8/2025link
39MT3-Gen4-gemma-2-9B
37.64score11/8/2025link
40MT3-Gen3-gemma-2-9B
36.70score11/8/2025link
41MT3-Gen2-gemma-2-9B
37.03score11/8/2025link
42MT3-Gen1-gemma-2-9B
36.96score11/8/2025link
43MT2-gemma-2-9B
37.43score11/8/2025link
44MT2-Max-Merge_02012025163610-gemma-2-9B
37.68score11/8/2025link
45MT2-Gen7-gemma-2-9B
36.79score11/8/2025link
46MT2-Gen6-gemma-2-9B
35.66score11/8/2025link
47MT2-Gen5-gemma-2-9B
36.69score11/8/2025link
48MT2-Gen4-gemma-2-9B
36.90score11/8/2025link
49MT2-Gen3-gemma-2-9B
37.49score11/8/2025link
50MT2-Gen2-gemma-2-9B
37.65score11/8/2025link
51MT2-Gen1-gemma-2-9B
37.52score11/8/2025link
52MT1-gemma-2-9B
37.31score11/8/2025link
53MT1-Max-Merge_02012025163610-gemma-2-9B
37.57score11/8/2025link
54MT1-Gen7-gemma-2-9B
34.94score11/8/2025link
55MT1-Gen6-gemma-2-9B
34.81score11/8/2025link
56MT1-Gen5-gemma-2-9B
35.80score11/8/2025link
57MT1-Gen5-IF-gemma-2-S2DMv1-9B
35.75score11/8/2025link
58MT1-Gen4-gemma-2-9B
36.51score11/8/2025link
59MT1-Gen3-gemma-2-9B
37.21score11/8/2025link
60MT1-Gen2-gemma-2-9B
37.28score11/8/2025link
61MT1-Gen1-gemma-2-9B
37.51score11/8/2025link
62zelk12/MT-gemma-2-9B
35.82score11/8/2025link
63MT-Merge6-gemma-2-9B
34.61score11/8/2025link
64MT-Merge5-gemma-2-9B
37.64score11/8/2025link
65MT-Merge4-gemma-2-9B
37.67score11/8/2025link
66MT-Merge3-gemma-2-9B
37.48score11/8/2025link
67MT-Merge2-gemma-2-9B
37.57score11/8/2025link
68MT-Merge2-MU-gemma-2-MTg2MT1g2-9B
37.47score11/8/2025link
69MT-Merge1-gemma-2-9B
37.49score11/8/2025link
70MT-Merge-gemma-2-9B
37.35score11/8/2025link
71MT-Max-Merge_02012025163610-gemma-2-9B
37.73score11/8/2025link
72MT-Gen7-gemma-2-9B
34.69score11/8/2025link
73MT-Gen6fix-gemma-2-9B
34.66score11/8/2025link
74MT-Gen6-gemma-2-9B
35.17score11/8/2025link
75MT-Gen5-gemma-2-9B
37.80score11/8/2025link
76MT-Gen4-gemma-2-9B
37.64score11/8/2025link
77MT-Gen3-gemma-2-9B
37.29score11/8/2025link
78MT-Gen2-gemma-2-9B
37.64score11/8/2025link
79MT-Gen2-GI-gemma-2-9B
37.29score11/8/2025link
80MT-Gen1-gemma-2-9B
37.56score11/8/2025link
81Gemma-2-TM-9B
34.31score11/8/2025link
82gemma-2-9b-it-chinese-kyara
35.32score11/8/2025link
83gemma-2-2b-it-chinese-kyara-dpo
17.48score11/8/2025link
84Llama3-8B-abliterated-Spectrum-slerp
25.08score11/8/2025link
85Llama3-8B-SuperNova-Spectrum-dare_ties
28.60score11/8/2025link
86Llama3-8B-SuperNova-Spectrum-Hermes-DPO
18.16score11/8/2025link
87ArlowGPT-8B
30.96score11/8/2025link
88ArlowGPT-3B-Multilingual
20.19score11/8/2025link
89gemma-2-2b-jpn-it-abliterated-24
16.37score11/8/2025link
90gemma-2-2b-jpn-it-abliterated-18-ORPO
13.17score11/8/2025link
91gemma-2-2b-jpn-it-abliterated-18
16.72score11/8/2025link
92ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO-alpaca
13.88score11/8/2025link
93gemma-2-2b-jpn-it-abliterated-17-ORPO
13.23score11/8/2025link
94gemma-2-2b-jpn-it-abliterated-17-18-24
14.25score11/8/2025link
95gemma-2-2b-jpn-it-abliterated-17
16.17score11/8/2025link
96gemma-2-2b-ORPO-jpn-it-abliterated-18-merge
16.23score11/8/2025link
97gemma-2-2b-ORPO-jpn-it-abliterated-18
14.94score11/8/2025link
98Llama-3.1-8B-SFT-GRPO-Instruct
1.09score11/8/2025link
99Llama-3.1-8B-GRPO-Instruct
30.43score11/8/2025link
100ECE-PRYMMAL-YL-1B-SLERP-V8
15.37score11/8/2025link

Showing latest 100 models for “mmlu_pro”. Switch task or group to explore other leaderboards.