Spaces:
Running
Running
pasha
commited on
Commit
·
f62a6af
1
Parent(s):
048f168
Board updated
Browse files- test_all.csv +118 -62
test_all.csv
CHANGED
@@ -1,103 +1,159 @@
|
|
1 |
model,model_name,model_size,model_quant,dataset_name,dataset_split,total_tests,valid_responses,correct_responses,accuracy,avg_response_time,avg_token_count
|
2 |
-
|
3 |
-
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,122,0.9385,0.619,54.5
|
4 |
-
llama3.1:8b-instruct-fp16,llama3.1,8b,fp16,evilfreelancer/rrr-benchmark,generic,130,130,126,0.9692,1.039,55.7
|
5 |
-
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,38,12,0.0923,0.451,32.9
|
6 |
-
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,generic,130,20,14,0.1077,0.441,30.4
|
7 |
-
llama3.2:1b-instruct-fp16,llama3.2,1b,fp16,evilfreelancer/rrr-benchmark,generic,130,24,10,0.0769,0.492,28.4
|
8 |
-
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,121,0.9308,0.275,58.5
|
9 |
-
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,122,0.9385,0.376,58.8
|
10 |
-
llama3.2:3b-instruct-fp16,llama3.2,3b,fp16,evilfreelancer/rrr-benchmark,generic,130,130,127,0.9769,0.566,60.1
|
11 |
-
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,126,0.9692,0.547,62.6
|
12 |
-
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,generic,130,128,126,0.9692,0.818,67.8
|
13 |
-
qwen3:8b-fp16,qwen3,8b,fp16,evilfreelancer/rrr-benchmark,generic,130,130,129,0.9923,2.279,64.8
|
14 |
deepseek-r1:7b-qwen-distill-q4_K_M,deepseek-r1,7b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,0,0,0.0,0,0
|
15 |
deepseek-r1:7b-qwen-distill-q8_0,deepseek-r1,7b,q8_0,evilfreelancer/rrr-benchmark,generic,130,0,0,0.0,0,0
|
16 |
-
deepseek-r1:
|
|
|
|
|
|
|
|
|
17 |
deepseek-r1:8b-llama-distill-q4_K_M,deepseek-r1,8b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,120,0.9231,0.539,67.6
|
|
|
|
|
|
|
|
|
18 |
deepseek-r1:8b-llama-distill-q8_0,deepseek-r1,8b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,124,0.9538,0.73,62.9
|
19 |
-
deepseek-r1:8b-llama-distill-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,111,0.8538,1.24,108.8
|
|
|
|
|
|
|
|
|
21 |
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,113,0.8692,2.284,124.3
|
22 |
-
deepseek-v2:16b-lite-chat-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
hf.co/t-tech/T-pro-it-1.0-Q4_K_M-GGUF,T-pro-it-1.0,32b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,128,0.9846,1.418,47.7
|
24 |
hf.co/t-tech/T-pro-it-1.0-Q8_0-GGUF,T-pro-it-1.0,32b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,128,0.9846,19.59,48.4
|
25 |
-
|
26 |
-
|
27 |
-
|
|
|
|
|
|
|
28 |
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,999,929,0.929,0.399,51.2
|
29 |
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,999,916,0.916,0.412,52.0
|
30 |
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,890,0.89,0.433,54.1
|
31 |
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,1000,905,0.905,0.451,55.7
|
|
|
32 |
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,999,937,0.937,0.613,52.7
|
33 |
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,918,0.918,0.62,53.9
|
34 |
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,904,0.904,0.653,56.6
|
35 |
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,911,0.911,0.664,57.3
|
36 |
-
llama3.
|
37 |
-
llama3.
|
38 |
-
llama3.
|
39 |
-
llama3.
|
|
|
|
|
40 |
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,277,184,0.184,0.423,32.6
|
41 |
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,262,135,0.135,0.438,30.1
|
42 |
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,331,150,0.15,0.507,34.4
|
43 |
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,418,169,0.169,0.514,31.9
|
|
|
44 |
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,105,67,0.067,0.398,28.0
|
45 |
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,134,92,0.092,0.448,30.8
|
46 |
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,163,83,0.083,0.482,30.5
|
47 |
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,206,97,0.097,0.528,33.0
|
48 |
-
llama3.2:
|
49 |
-
llama3.2:
|
50 |
-
llama3.2:
|
51 |
-
llama3.2:
|
|
|
|
|
52 |
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,997,899,0.899,0.294,61.1
|
53 |
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,998,897,0.897,0.277,57.6
|
54 |
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,996,847,0.847,0.284,58.7
|
55 |
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,997,850,0.85,0.285,58.5
|
|
|
56 |
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,998,924,0.924,0.378,59.7
|
57 |
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,912,0.912,0.372,59.1
|
58 |
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,999,884,0.884,0.365,57.7
|
59 |
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,881,0.881,0.386,61.1
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,996,943,0.943,0.547,64.3
|
65 |
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,996,927,0.927,0.532,62.7
|
66 |
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,996,921,0.921,0.566,66.9
|
67 |
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,999,912,0.912,0.591,70.0
|
|
|
68 |
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,999,945,0.945,0.784,65.4
|
69 |
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,999,937,0.937,0.77,64.7
|
70 |
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,939,0.939,0.813,68.5
|
71 |
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,999,931,0.931,0.853,72.0
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,1000,848,0.848,0.546,96.4
|
89 |
-
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,1000,755,0.755,0.61,110.6
|
90 |
-
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,750,0.75,0.647,117.0
|
91 |
-
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,1000,738,0.738,0.647,115.1
|
92 |
-
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,1000,891,0.891,0.75,112.5
|
93 |
-
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,842,0.842,0.796,121.9
|
94 |
-
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,798,0.798,0.825,125.8
|
95 |
-
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,778,0.778,0.875,132.1
|
96 |
-
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,1000,891,0.891,8.471,109.9
|
97 |
-
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,1000,835,0.835,9.409,123.5
|
98 |
-
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,1000,787,0.787,9.71,127.0
|
99 |
-
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,999,774,0.774,10.034,129.7
|
100 |
-
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,routes_3,1000,1000,947,0.947,0.986,51.7
|
101 |
-
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,routes_5,1000,1000,932,0.932,0.981,50.9
|
102 |
-
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,routes_7,1000,1000,931,0.931,1.018,52.3
|
103 |
-
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,routes_9,1000,1000,928,0.928,1.055,53.6
|
|
|
1 |
model,model_name,model_size,model_quant,dataset_name,dataset_split,total_tests,valid_responses,correct_responses,accuracy,avg_response_time,avg_token_count
|
2 |
+
deepseek-r1:7b-qwen-distill-fp16,deepseek-r1,7b,fp16,evilfreelancer/rrr-benchmark,generic,130,0,0,0.0,0,0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
deepseek-r1:7b-qwen-distill-q4_K_M,deepseek-r1,7b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,0,0,0.0,0,0
|
4 |
deepseek-r1:7b-qwen-distill-q8_0,deepseek-r1,7b,q8_0,evilfreelancer/rrr-benchmark,generic,130,0,0,0.0,0,0
|
5 |
+
deepseek-r1:8b-llama-distill-fp16,deepseek-r1,8b,fp16,evilfreelancer/rrr-benchmark,generic,130,130,123,0.9462,1.239,63.9
|
6 |
+
deepseek-r1:8b-llama-distill-fp16,deepseek-r1,8b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,1000,933,0.933,1.23,65.4
|
7 |
+
deepseek-r1:8b-llama-distill-fp16,deepseek-r1,8b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,1000,915,0.915,1.204,64.5
|
8 |
+
deepseek-r1:8b-llama-distill-fp16,deepseek-r1,8b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,1000,897,0.897,1.31,70.3
|
9 |
+
deepseek-r1:8b-llama-distill-fp16,deepseek-r1,8b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,1000,875,0.875,1.328,71.3
|
10 |
deepseek-r1:8b-llama-distill-q4_K_M,deepseek-r1,8b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,120,0.9231,0.539,67.6
|
11 |
+
deepseek-r1:8b-llama-distill-q4_K_M,deepseek-r1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,1000,929,0.929,0.541,67.6
|
12 |
+
deepseek-r1:8b-llama-distill-q4_K_M,deepseek-r1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,1000,924,0.924,0.531,66.4
|
13 |
+
deepseek-r1:8b-llama-distill-q4_K_M,deepseek-r1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,901,0.901,0.555,69.6
|
14 |
+
deepseek-r1:8b-llama-distill-q4_K_M,deepseek-r1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,1000,895,0.895,0.599,75.4
|
15 |
deepseek-r1:8b-llama-distill-q8_0,deepseek-r1,8b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,124,0.9538,0.73,62.9
|
16 |
+
deepseek-r1:8b-llama-distill-q8_0,deepseek-r1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,1000,928,0.928,0.783,68.2
|
17 |
+
deepseek-r1:8b-llama-distill-q8_0,deepseek-r1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,914,0.914,0.758,66.1
|
18 |
+
deepseek-r1:8b-llama-distill-q8_0,deepseek-r1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,897,0.897,0.802,69.9
|
19 |
+
deepseek-r1:8b-llama-distill-q8_0,deepseek-r1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,887,0.887,0.844,73.7
|
20 |
+
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,generic,130,130,111,0.8538,9.833,129.5
|
21 |
+
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,1000,891,0.891,8.471,109.9
|
22 |
+
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,1000,835,0.835,9.409,123.5
|
23 |
+
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,1000,787,0.787,9.71,127.0
|
24 |
+
deepseek-v2:16b-lite-chat-fp16,deepseek-v2,16b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,999,774,0.774,10.034,129.7
|
25 |
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,111,0.8538,1.24,108.8
|
26 |
+
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,1000,848,0.848,0.546,96.4
|
27 |
+
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,1000,755,0.755,0.61,110.6
|
28 |
+
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,750,0.75,0.647,117.0
|
29 |
+
deepseek-v2:16b-lite-chat-q4_K_M,deepseek-v2,16b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,1000,738,0.738,0.647,115.1
|
30 |
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,113,0.8692,2.284,124.3
|
31 |
+
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,1000,891,0.891,0.75,112.5
|
32 |
+
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,842,0.842,0.796,121.9
|
33 |
+
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,798,0.798,0.825,125.8
|
34 |
+
deepseek-v2:16b-lite-chat-q8_0,deepseek-v2,16b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,778,0.778,0.875,132.1
|
35 |
+
hf.co/ai-sage/GigaChat-20B-A3B-instruct-v1.5-GGUF:Q4_K_M,GigaChat-v1.5,20b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,0,0,0.0,0,0
|
36 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,1000,910,0.91,0.622,68.3
|
37 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,1000,903,0.903,0.591,64.7
|
38 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,1000,869,0.869,0.586,63.7
|
39 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,1000,859,0.859,0.613,67.2
|
40 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,1000,901,0.901,0.31,66.4
|
41 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,1000,891,0.891,0.277,58.0
|
42 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,859,0.859,0.278,58.1
|
43 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,1000,838,0.838,0.278,57.5
|
44 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,1000,913,0.913,0.42,68.2
|
45 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,918,0.918,0.403,65.4
|
46 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,889,0.889,0.403,65.2
|
47 |
+
hf.co/DevQuasar/Menlo.ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF,ReZero-v0.1,3b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,870,0.87,0.41,66.1
|
48 |
+
hf.co/mradermacher/T-lite-it-1.0-GGUF:Q4_K_M,T-lite-it-1.0,7b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,0,0,0.0,0,0
|
49 |
+
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,generic,130,130,128,0.9846,1.157,56.1
|
50 |
+
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,routes_3,1000,1000,947,0.947,0.986,51.7
|
51 |
+
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,routes_5,1000,1000,932,0.932,0.981,50.9
|
52 |
+
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,routes_7,1000,1000,931,0.931,1.018,52.3
|
53 |
+
hf.co/NikolayKozloff/T-pro-it-1.0-Q2_K-GGUF,T-pro-it-1.0,32b,q2_k,evilfreelancer/rrr-benchmark,routes_9,1000,1000,928,0.928,1.055,53.6
|
54 |
+
hf.co/t-tech/T-pro-it-1.0-Q4_K_M-GGUF,T-pro-it-1.0,32b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,1000,947,0.947,1.269,48.7
|
55 |
+
hf.co/t-tech/T-pro-it-1.0-Q4_K_M-GGUF,T-pro-it-1.0,32b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,1000,944,0.944,1.28,48.6
|
56 |
+
hf.co/t-tech/T-pro-it-1.0-Q4_K_M-GGUF,T-pro-it-1.0,32b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,937,0.937,1.312,49.5
|
57 |
+
hf.co/t-tech/T-pro-it-1.0-Q4_K_M-GGUF,T-pro-it-1.0,32b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,1000,938,0.938,1.35,50.7
|
58 |
hf.co/t-tech/T-pro-it-1.0-Q4_K_M-GGUF,T-pro-it-1.0,32b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,128,0.9846,1.418,47.7
|
59 |
hf.co/t-tech/T-pro-it-1.0-Q8_0-GGUF,T-pro-it-1.0,32b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,128,0.9846,19.59,48.4
|
60 |
+
llama3.1:8b-instruct-fp16,llama3.1,8b,fp16,evilfreelancer/rrr-benchmark,generic,130,130,126,0.9692,1.039,55.7
|
61 |
+
llama3.1:8b-instruct-fp16,llama3.1,8b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,1000,939,0.939,1.001,52.9
|
62 |
+
llama3.1:8b-instruct-fp16,llama3.1,8b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,1000,927,0.927,1.019,54.6
|
63 |
+
llama3.1:8b-instruct-fp16,llama3.1,8b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,999,902,0.902,1.085,58.1
|
64 |
+
llama3.1:8b-instruct-fp16,llama3.1,8b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,999,902,0.902,1.09,58.9
|
65 |
+
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,123,0.9462,0.421,53.3
|
66 |
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,999,929,0.929,0.399,51.2
|
67 |
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,999,916,0.916,0.412,52.0
|
68 |
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,890,0.89,0.433,54.1
|
69 |
llama3.1:8b-instruct-q4_K_M,llama3.1,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,1000,905,0.905,0.451,55.7
|
70 |
+
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,122,0.9385,0.619,54.5
|
71 |
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,999,937,0.937,0.613,52.7
|
72 |
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,918,0.918,0.62,53.9
|
73 |
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,904,0.904,0.653,56.6
|
74 |
llama3.1:8b-instruct-q8_0,llama3.1,8b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,911,0.911,0.664,57.3
|
75 |
+
llama3.2:1b-instruct-fp16,llama3.2,1b,fp16,evilfreelancer/rrr-benchmark,generic,130,24,10,0.0769,0.492,28.4
|
76 |
+
llama3.2:1b-instruct-fp16,llama3.2,1b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,143,104,0.104,0.452,30.3
|
77 |
+
llama3.2:1b-instruct-fp16,llama3.2,1b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,131,91,0.091,0.504,32.7
|
78 |
+
llama3.2:1b-instruct-fp16,llama3.2,1b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,161,73,0.073,0.532,32.1
|
79 |
+
llama3.2:1b-instruct-fp16,llama3.2,1b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,218,106,0.106,0.552,31.8
|
80 |
+
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,38,12,0.0923,0.451,32.9
|
81 |
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,277,184,0.184,0.423,32.6
|
82 |
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,262,135,0.135,0.438,30.1
|
83 |
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,331,150,0.15,0.507,34.4
|
84 |
llama3.2:1b-instruct-q4_K_M,llama3.2,1b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,418,169,0.169,0.514,31.9
|
85 |
+
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,generic,130,20,14,0.1077,0.441,30.4
|
86 |
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,105,67,0.067,0.398,28.0
|
87 |
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,134,92,0.092,0.448,30.8
|
88 |
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,163,83,0.083,0.482,30.5
|
89 |
llama3.2:1b-instruct-q8_0,llama3.2,1b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,206,97,0.097,0.528,33.0
|
90 |
+
llama3.2:3b-instruct-fp16,llama3.2,3b,fp16,evilfreelancer/rrr-benchmark,generic,130,130,127,0.9769,0.566,60.1
|
91 |
+
llama3.2:3b-instruct-fp16,llama3.2,3b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,997,914,0.914,0.574,61.8
|
92 |
+
llama3.2:3b-instruct-fp16,llama3.2,3b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,1000,919,0.919,0.573,62.2
|
93 |
+
llama3.2:3b-instruct-fp16,llama3.2,3b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,998,886,0.886,0.551,59.3
|
94 |
+
llama3.2:3b-instruct-fp16,llama3.2,3b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,1000,879,0.879,0.58,62.7
|
95 |
+
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,121,0.9308,0.275,58.5
|
96 |
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,997,899,0.899,0.294,61.1
|
97 |
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,998,897,0.897,0.277,57.6
|
98 |
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,996,847,0.847,0.284,58.7
|
99 |
llama3.2:3b-instruct-q4_K_M,llama3.2,3b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,997,850,0.85,0.285,58.5
|
100 |
+
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,generic,130,130,122,0.9385,0.376,58.8
|
101 |
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,998,924,0.924,0.378,59.7
|
102 |
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,912,0.912,0.372,59.1
|
103 |
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,999,884,0.884,0.365,57.7
|
104 |
llama3.2:3b-instruct-q8_0,llama3.2,3b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,881,0.881,0.386,61.1
|
105 |
+
qwen3:1.7b-q4_k_m,qwen3,1.7b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,531,157,0.157,0.275,54.2
|
106 |
+
qwen3:1.7b-q4_k_m,qwen3,1.7b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,562,122,0.122,0.275,51.4
|
107 |
+
qwen3:1.7b-q4_k_m,qwen3,1.7b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,439,66,0.066,0.254,48.9
|
108 |
+
qwen3:1.7b-q4_k_m,qwen3,1.7b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,436,68,0.068,0.279,58.8
|
109 |
+
qwen3:1.7b-q8_0,qwen3,1.7b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,188,62,0.062,0.316,55.3
|
110 |
+
qwen3:1.7b-q8_0,qwen3,1.7b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,260,52,0.052,0.321,54.3
|
111 |
+
qwen3:1.7b-q8_0,qwen3,1.7b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,340,52,0.052,0.388,63.2
|
112 |
+
qwen3:1.7b-q8_0,qwen3,1.7b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,399,77,0.077,0.349,56.7
|
113 |
+
qwen3:1.7b-fp16,qwen3,1.7b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,136,53,0.053,1.582,43.2
|
114 |
+
qwen3:1.7b-fp16,qwen3,1.7b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,287,48,0.048,0.441,56.2
|
115 |
+
qwen3:1.7b-fp16,qwen3,1.7b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,295,56,0.056,0.428,56.0
|
116 |
+
qwen3:1.7b-fp16,qwen3,1.7b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,248,50,0.05,0.454,58.5
|
117 |
+
qwen3:4b-fp16,qwen3,4b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,1000,916,0.916,0.726,63.4
|
118 |
+
qwen3:4b-fp16,qwen3,4b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,1000,878,0.878,0.705,61.5
|
119 |
+
qwen3:4b-fp16,qwen3,4b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,1000,884,0.884,0.731,63.8
|
120 |
+
qwen3:4b-fp16,qwen3,4b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,1000,896,0.896,0.754,65.9
|
121 |
+
qwen3:4b-q4_k_m,qwen3,4b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,1000,922,0.922,0.349,57.5
|
122 |
+
qwen3:4b-q4_k_m,qwen3,4b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,1000,886,0.886,0.348,57.1
|
123 |
+
qwen3:4b-q4_k_m,qwen3,4b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,903,0.903,0.368,61.1
|
124 |
+
qwen3:4b-q4_k_m,qwen3,4b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,1000,908,0.908,0.382,63.4
|
125 |
+
qwen3:4b-q8_0,qwen3,4b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,1000,921,0.921,0.486,62.4
|
126 |
+
qwen3:4b-q8_0,qwen3,4b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,878,0.878,0.491,62.9
|
127 |
+
qwen3:4b-q8_0,qwen3,4b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,898,0.898,0.501,63.9
|
128 |
+
qwen3:4b-q8_0,qwen3,4b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,1000,885,0.885,0.522,66.5
|
129 |
+
qwen3:8b-fp16,qwen3,8b,fp16,evilfreelancer/rrr-benchmark,generic,130,130,129,0.9923,2.279,64.8
|
130 |
+
qwen3:8b-fp16,qwen3,8b,fp16,evilfreelancer/rrr-benchmark,routes_3,1000,1000,946,0.946,1.317,69.2
|
131 |
+
qwen3:8b-fp16,qwen3,8b,fp16,evilfreelancer/rrr-benchmark,routes_5,1000,1000,934,0.934,1.276,67.5
|
132 |
+
qwen3:8b-fp16,qwen3,8b,fp16,evilfreelancer/rrr-benchmark,routes_7,1000,1000,935,0.935,1.324,70.2
|
133 |
+
qwen3:8b-fp16,qwen3,8b,fp16,evilfreelancer/rrr-benchmark,routes_9,1000,1000,927,0.927,1.572,74.5
|
134 |
+
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,generic,130,130,126,0.9692,0.547,62.6
|
135 |
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,996,943,0.943,0.547,64.3
|
136 |
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,996,927,0.927,0.532,62.7
|
137 |
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,996,921,0.921,0.566,66.9
|
138 |
qwen3:8b-q4_K_M,qwen3,8b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,999,912,0.912,0.591,70.0
|
139 |
+
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,generic,130,128,126,0.9692,0.818,67.8
|
140 |
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,999,945,0.945,0.784,65.4
|
141 |
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,999,937,0.937,0.77,64.7
|
142 |
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,939,0.939,0.813,68.5
|
143 |
qwen3:8b-q8_0,qwen3,8b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,999,931,0.931,0.853,72.0
|
144 |
+
gemma3n:e4b-it-q4_K_M,gemma3n,4b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,1000,939,0.939,2.943,53.2
|
145 |
+
gemma3n:e4b-it-q4_K_M,gemma3n,4b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,999,929,0.929,2.975,51.1
|
146 |
+
gemma3n:e4b-it-q4_K_M,gemma3n,4b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,927,0.927,3.101,51.3
|
147 |
+
gemma3n:e4b-it-q4_K_M,gemma3n,4b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,999,919,0.919,3.217,52.6
|
148 |
+
gemma3n:e4b-it-q8_0,gemma3n,4b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,1000,936,0.936,2.89,49.8
|
149 |
+
gemma3n:e4b-it-q8_0,gemma3n,4b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,1000,921,0.921,2.947,48.7
|
150 |
+
gemma3n:e4b-it-q8_0,gemma3n,4b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,923,0.923,3.102,50.3
|
151 |
+
gemma3n:e4b-it-q8_0,gemma3n,4b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,999,918,0.918,3.274,52.7
|
152 |
+
gemma3n:e2b-it-q4_K_M,gemma3n,2b,q4_k_m,evilfreelancer/rrr-benchmark,routes_3,1000,998,936,0.936,2.914,70.7
|
153 |
+
gemma3n:e2b-it-q4_K_M,gemma3n,2b,q4_k_m,evilfreelancer/rrr-benchmark,routes_5,1000,1000,916,0.916,2.953,69.1
|
154 |
+
gemma3n:e2b-it-q4_K_M,gemma3n,2b,q4_k_m,evilfreelancer/rrr-benchmark,routes_7,1000,1000,921,0.921,2.945,64.8
|
155 |
+
gemma3n:e2b-it-q4_K_M,gemma3n,2b,q4_k_m,evilfreelancer/rrr-benchmark,routes_9,1000,998,913,0.913,3.12,68.3
|
156 |
+
gemma3n:e2b-it-q8_0,gemma3n,2b,q8_0,evilfreelancer/rrr-benchmark,routes_3,1000,999,940,0.94,2.759,58.4
|
157 |
+
gemma3n:e2b-it-q8_0,gemma3n,2b,q8_0,evilfreelancer/rrr-benchmark,routes_5,1000,990,919,0.919,2.743,55.3
|
158 |
+
gemma3n:e2b-it-q8_0,gemma3n,2b,q8_0,evilfreelancer/rrr-benchmark,routes_7,1000,1000,925,0.925,2.812,54.0
|
159 |
+
gemma3n:e2b-it-q8_0,gemma3n,2b,q8_0,evilfreelancer/rrr-benchmark,routes_9,1000,998,921,0.921,2.99,56.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|