Leaderboards

RankModelScoreMetricEvaluatedSource
1zhengr/MixTAO-7Bx2-MoE-v8.1
20.52score1/25/2026link
2Qwen2.5-72B-Instruct-abliterated
54.13score1/25/2026link
3Qwen2.5-32B-Instruct-abliterated-v2
51.35score1/25/2026link
4recoilme-gemma-2-psy10k-mental_healt-9B-v0.1
35.34score1/25/2026link
5recoilme-gemma-2-Ifable-9B-v0.1
36.93score1/25/2026link
6recoilme-gemma-2-Gutenberg-Doppel-9B-v0.1
36.84score1/25/2026link
7recoilme-gemma-2-Ataraxy-9B-v0.2
36.92score1/25/2026link
8recoilme-gemma-2-Ataraxy-9B-v0.1-t0.75
34.90score1/25/2026link
9recoilme-gemma-2-Ataraxy-9B-v0.1-t0.25
37.78score1/25/2026link
10recoilme-gemma-2-Ataraxy-9B-v0.1
36.90score1/25/2026link
11gemma-2-S2MTM-9B
36.63score1/25/2026link
12Test01012025155054t0.5_gemma-2
1.00score1/25/2026link
13zelk12/Test01012025155054
1.00score1/25/2026link
14T31122024203920-gemma-2-9B
37.47score1/25/2026link
15Rv0.4MT4g2-gemma-2-9B
37.97score1/25/2026link
16Rv0.4DMv1t0.25Tt0.25-gemma-2-9B
37.19score1/25/2026link
17Rv0.4DMv1t0.25-gemma-2-9B
37.79score1/25/2026link
18MTMaMe-Merge_02012025163610-gemma-2-9B
37.57score1/25/2026link
19MTM-Merge-gemma-2-9B
37.65score1/25/2026link
20MT5-gemma-2-9B
37.41score1/25/2026link
21MT5-Max-Merge_02012025163610-gemma-2-9B
37.67score1/25/2026link
22MT5-Gen5-gemma-2-9B
36.99score1/25/2026link
23MT5-Gen4-gemma-2-9B
37.74score1/25/2026link
24MT5-Gen3-gemma-2-9B
37.50score1/25/2026link
25MT5-Gen2-gemma-2-9B
37.55score1/25/2026link
26MT5-Gen1-gemma-2-9B
37.43score1/25/2026link
27MT4-gemma-2-9B
37.40score1/25/2026link
28MT4-Max-Merge_02012025163610-gemma-2-9B
37.68score1/25/2026link
29MT4-Gen5-gemma-2-9B
37.60score1/25/2026link
30MT4-Gen4-gemma-2-9B
36.93score1/25/2026link
31MT4-Gen3-gemma-2-9B
37.56score1/25/2026link
32MT4-Gen2-gemma-2-9B
37.42score1/25/2026link
33MT4-Gen1-gemma-2-9B
37.66score1/25/2026link
34MT3-gemma-2-9B
36.96score1/25/2026link
35MT3-Max-Merge_02012025163610-gemma-2-9B
37.66score1/25/2026link
36MT3-Gen6-gemma-2-9B
34.47score1/25/2026link
37MT3-Gen5-gemma-2-9B_v1
37.32score1/25/2026link
38MT3-Gen5-gemma-2-9B
36.85score1/25/2026link
39MT3-Gen4-gemma-2-9B
37.64score1/25/2026link
40MT3-Gen3-gemma-2-9B
36.70score1/25/2026link
41MT3-Gen2-gemma-2-9B
37.03score1/25/2026link
42MT3-Gen1-gemma-2-9B
36.96score1/25/2026link
43MT2-gemma-2-9B
37.43score1/25/2026link
44MT2-Max-Merge_02012025163610-gemma-2-9B
37.68score1/25/2026link
45MT2-Gen7-gemma-2-9B
36.79score1/25/2026link
46MT2-Gen6-gemma-2-9B
35.66score1/25/2026link
47MT2-Gen5-gemma-2-9B
36.69score1/25/2026link
48MT2-Gen4-gemma-2-9B
36.90score1/25/2026link
49MT2-Gen3-gemma-2-9B
37.49score1/25/2026link
50MT2-Gen2-gemma-2-9B
37.65score1/25/2026link
51MT2-Gen1-gemma-2-9B
37.52score1/25/2026link
52MT1-gemma-2-9B
37.31score1/25/2026link
53MT1-Max-Merge_02012025163610-gemma-2-9B
37.57score1/25/2026link
54MT1-Gen7-gemma-2-9B
34.94score1/25/2026link
55MT1-Gen6-gemma-2-9B
34.81score1/25/2026link
56MT1-Gen5-gemma-2-9B
35.80score1/25/2026link
57MT1-Gen5-IF-gemma-2-S2DMv1-9B
35.75score1/25/2026link
58MT1-Gen4-gemma-2-9B
36.51score1/25/2026link
59MT1-Gen3-gemma-2-9B
37.21score1/25/2026link
60MT1-Gen2-gemma-2-9B
37.28score1/25/2026link
61MT1-Gen1-gemma-2-9B
37.51score1/25/2026link
62zelk12/MT-gemma-2-9B
35.82score1/25/2026link
63MT-Merge6-gemma-2-9B
34.61score1/25/2026link
64MT-Merge5-gemma-2-9B
37.64score1/25/2026link
65MT-Merge4-gemma-2-9B
37.67score1/25/2026link
66MT-Merge3-gemma-2-9B
37.48score1/25/2026link
67MT-Merge2-gemma-2-9B
37.57score1/25/2026link
68MT-Merge2-MU-gemma-2-MTg2MT1g2-9B
37.47score1/25/2026link
69MT-Merge1-gemma-2-9B
37.49score1/25/2026link
70MT-Merge-gemma-2-9B
37.35score1/25/2026link
71MT-Max-Merge_02012025163610-gemma-2-9B
37.73score1/25/2026link
72MT-Gen7-gemma-2-9B
34.69score1/25/2026link
73MT-Gen6fix-gemma-2-9B
34.66score1/25/2026link
74MT-Gen6-gemma-2-9B
35.17score1/25/2026link
75MT-Gen5-gemma-2-9B
37.80score1/25/2026link
76MT-Gen4-gemma-2-9B
37.64score1/25/2026link
77MT-Gen3-gemma-2-9B
37.29score1/25/2026link
78MT-Gen2-gemma-2-9B
37.64score1/25/2026link
79MT-Gen2-GI-gemma-2-9B
37.29score1/25/2026link
80MT-Gen1-gemma-2-9B
37.56score1/25/2026link
81Gemma-2-TM-9B
34.31score1/25/2026link
82gemma-2-9b-it-chinese-kyara
35.32score1/25/2026link
83gemma-2-2b-it-chinese-kyara-dpo
17.48score1/25/2026link
84Llama3-8B-abliterated-Spectrum-slerp
25.08score1/25/2026link
85Llama3-8B-SuperNova-Spectrum-dare_ties
28.60score1/25/2026link
86Llama3-8B-SuperNova-Spectrum-Hermes-DPO
18.16score1/25/2026link
87ArlowGPT-8B
30.96score1/25/2026link
88ArlowGPT-3B-Multilingual
20.19score1/25/2026link
89gemma-2-2b-jpn-it-abliterated-24
16.37score1/25/2026link
90gemma-2-2b-jpn-it-abliterated-18-ORPO
13.17score1/25/2026link
91gemma-2-2b-jpn-it-abliterated-18
16.72score1/25/2026link
92ymcki/gemma-2-2b-jpn-it-abliterated-17-ORPO-alpaca
13.88score1/25/2026link
93gemma-2-2b-jpn-it-abliterated-17-ORPO
13.23score1/25/2026link
94gemma-2-2b-jpn-it-abliterated-17-18-24
14.25score1/25/2026link
95gemma-2-2b-jpn-it-abliterated-17
16.17score1/25/2026link
96gemma-2-2b-ORPO-jpn-it-abliterated-18-merge
16.23score1/25/2026link
97gemma-2-2b-ORPO-jpn-it-abliterated-18
14.94score1/25/2026link
98Llama-3.1-8B-SFT-GRPO-Instruct
1.09score1/25/2026link
99Llama-3.1-8B-GRPO-Instruct
30.43score1/25/2026link
100ECE-PRYMMAL-YL-1B-SLERP-V8
15.37score1/25/2026link

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