Leaderboards

RankModelScoreMetricEvaluatedSource
1nvidia/Hymba-1.5B-Base
10.25score1/24/2026link
2nvidia/AceMath-7B-RM
1.54score1/24/2026link
3nvidia/AceMath-7B-Instruct
26.48score1/24/2026link
4nvidia/AceMath-72B-RM
1.98score1/24/2026link
5nvidia/AceMath-72B-Instruct
37.90score1/24/2026link
6nvidia/AceMath-1.5B-Instruct
11.82score1/24/2026link
7nvidia/AceInstruct-7B
35.30score1/24/2026link
8nvidia/AceInstruct-72B
43.04score1/24/2026link
9nvidia/AceInstruct-1.5B
17.49score1/24/2026link
10nothingiisreal/MN-12B-Starcannon-v3
25.16score1/24/2026link
11nothingiisreal/MN-12B-Starcannon-v2
23.65score1/24/2026link
12nothingiisreal/L3.1-8B-Celeste-V1.5
30.05score1/24/2026link
13notbdq/Qwen2.5-14B-Instruct-1M-GRPO-Reasoning
42.77score1/24/2026link
14noname0202/llama-math-1b-r8-512tokens-test
8.36score1/24/2026link
15noname0202/llama-math-1b-r32-test
8.68score1/24/2026link
16noname0202/llama-math-1b-r32-0to512tokens-test
8.45score1/24/2026link
17noname0202/llama-math-1b-r16-0to512tokens-test
8.09score1/24/2026link
18noname0202/gemma-2-9b-sft-jp-en-zh-v2
29.72score1/24/2026link
19noname0202/gemma-2-9b-sft-jp-en-zh-v1
23.61score1/24/2026link
20noname0202/gemma-2-2b-it-ties
17.34score1/24/2026link
21noname0202/Llama-3.2-4x3B-Instruct
25.39score1/24/2026link
22nlpguy/StarFusion-alpha1
24.34score1/24/2026link
23nlpguy/StableProse
27.43score1/24/2026link
24nlpguy/Mistral-NeMo-Minitron-Upscale-v3
1.90score1/24/2026link
25nlpguy/Mistral-NeMo-Minitron-Upscale-v2
10.29score1/24/2026link
26nlpguy/Mistral-NeMo-Minitron-Upscale-v1
17.08score1/24/2026link
27nlpguy/Miisce-one
49.02score1/24/2026link
28nlpguy/Lion-Lamarck-v.1.1.0
40.34score1/24/2026link
29nlpguy/Lion-Lamarck-v.1.0.9
41.16score1/24/2026link
30nlpguy/Lion-Lamarck-v.1.0.8
40.48score1/24/2026link
31nisten/tqwendo-36b
37.56score1/24/2026link
32nisten/franqwenstein-35b
51.23score1/24/2026link
33nidum/Nidum-Limitless-Gemma-2B
1.93score1/24/2026link
34nhyha/merge_Qwen2.5-7B-Instruct_20241023_0314
39.36score1/24/2026link
35nhyha/N3N_gemma-2-9b-it_20241110_2026
33.56score1/24/2026link
36nhyha/N3N_gemma-2-9b-it_20241029_1532
34.69score1/24/2026link
37nhyha/N3N_Llama-3.1-8B-Instruct_1028_0216
29.31score1/24/2026link
38nhyha/N3N_Delirium-v1_1030_0227
35.00score1/24/2026link
39ngxson/MiniThinky-v2-1B-Llama-3.2
1.29score1/24/2026link
40ngxson/MiniThinky-1B-Llama-3.2
1.63score1/24/2026link
41nguyentd/FinancialAdvice-Qwen2.5-7B
30.58score1/24/2026link
42newsbang/Homer-v1.0-Qwen2.5-7B
39.27score1/24/2026link
43newsbang/Homer-v1.0-Qwen2.5-72B
57.17score1/24/2026link
44newsbang/Homer-v0.5-Qwen2.5-7B
37.44score1/24/2026link
45newsbang/Homer-v0.4-Qwen2.5-7B
37.36score1/24/2026link
46newsbang/Homer-v0.3-Qwen2.5-7B
38.40score1/24/2026link
47newsbang/Homer-7B-v0.2
37.89score1/24/2026link
48newsbang/Homer-7B-v0.1
38.61score1/24/2026link
49netease-youdao/Confucius-o1-14B
47.39score1/24/2026link
50netcat420/qwen2.5-MFANN-7b-v1.1
24.98score1/24/2026link
51netcat420/qwen2.5-MFANN-7b-SLERPv1.1
27.20score1/24/2026link
52netcat420/qwen2.5-MFANN-7b-SLERP-V1.2
27.09score1/24/2026link
53netcat420/Qwen2.5-MFANN-7b
24.81score1/24/2026link
54netcat420/Qwen2.5-DeepSeek-R1-MFANN-Slerp-7b
7.52score1/24/2026link
55netcat420/Qwen2.5-Coder-Scholar-7B-Abliterated-MFANN-Slerp-Unretrained
27.02score1/24/2026link
56netcat420/Qwen2.5-Coder-Scholar-7B-Abliterated-MFANN
23.96score1/24/2026link
57netcat420/Qwen2.5-7b-nerd-uncensored-MFANN-slerp
1.12score1/24/2026link
58netcat420/Qwen2.5-7b-MFANN-slerp
26.85score1/24/2026link
59netcat420/Qwen2.5-7B-nerd-uncensored-v0.9-MFANN
32.26score1/24/2026link
60netcat420/MFANNv0.25
26.03score1/24/2026link
61netcat420/MFANNv0.24
26.09score1/24/2026link
62netcat420/MFANNv0.23
26.53score1/24/2026link
63netcat420/MFANNv0.22.1
26.03score1/24/2026link
64netcat420/MFANNv0.21
22.57score1/24/2026link
65netcat420/MFANNv0.20
24.47score1/24/2026link
66netcat420/MFANNv0.19
16.36score1/24/2026link
67netcat420/MFANN3bv1.4
18.95score1/24/2026link
68netcat420/MFANN3bv1.3
14.17score1/24/2026link
69netcat420/MFANN3bv1.2
5.00score1/24/2026link
70netcat420/MFANN3bv1.1
1.76score1/24/2026link
71netcat420/MFANN3bv0.24
15.02score1/24/2026link
72netcat420/MFANN3bv0.23
15.75score1/24/2026link
73netcat420/MFANN3bv0.22
16.86score1/24/2026link
74netcat420/MFANN3bv0.21
15.48score1/24/2026link
75netcat420/MFANN3bv0.20
16.67score1/24/2026link
76netcat420/MFANN3bv0.19
16.89score1/24/2026link
77netcat420/MFANN3bv0.18
16.67score1/24/2026link
78netcat420/MFANN3bv0.15
16.32score1/24/2026link
79netcat420/MFANN3b
14.51score1/24/2026link
80netcat420/MFANN-phigments-slerp-V3.3
20.03score1/24/2026link
81netcat420/MFANN-phigments-slerp-V3.2
18.95score1/24/2026link
82netcat420/MFANN-phigments-slerp-V2
19.08score1/24/2026link
83netcat420/MFANN-llama3.1-abliterated-v2
27.67score1/24/2026link
84netcat420/MFANN-llama3.1-abliterated-SLERP-v3.1
28.26score1/24/2026link
85netcat420/MFANN-llama3.1-abliterated-SLERP-v3
28.12score1/24/2026link
86netcat420/MFANN-llama3.1-Abliterated-SLERP
21.42score1/24/2026link
87netcat420/MFANN-abliterated-phi2-merge-unretrained
5.31score1/24/2026link
88netcat420/MFANN-SFT
25.96score1/24/2026link
89netcat420/MFANN-Llama3.1-Abliterated-Slerp-V3.2
28.08score1/24/2026link
90netcat420/MFANN-Llama3.1-Abliterated-Slerp-TIES
28.13score1/24/2026link
91netcat420/MFANN-Llama3.1-Abliterated-SLERP-V5
27.17score1/24/2026link
92netcat420/MFANN-Llama3.1-Abliterated-SLERP-V4
27.96score1/24/2026link
93netcat420/MFANN-Llama3.1-Abliterated-SLERP-TIES-V3
27.67score1/24/2026link
94netcat420/MFANN-Llama3.1-Abliterated-SLERP-TIES-V2
28.03score1/24/2026link
95netcat420/Llama3.1-MFANN-8b
19.17score1/24/2026link
96netcat420/DeepSeek-R1-MFANN-TIES-unretrained-7b
1.61score1/24/2026link
97netcat420/DeepSeek-R1-Distill-Qwen-MFANN-Slerp-7b
1.00score1/24/2026link
98neopolita/loki-v0.1-virtuoso
45.88score1/24/2026link
99neopolita/jessi-v0.6-falcon3-7b-instruct
32.85score1/24/2026link
100neopolita/jessi-v0.5-falcon3-7b-instruct
32.96score1/24/2026link

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