ABCDEFGHIJKL
1
Modelwithout templatewith templatewith template multiturnn-shotdiff without and withdiff without and with multiturn
2
generatemulti_choicegeneratemulti_choicegeneratemulti_choicegeneratemulti_choicegeneratemulti_choice
3
Remek/OpenChat3.5-0106-Spichlerz-Inst-00156,2150,9055,6249,4657,0252,115-0,59-1,440,811,21
4
berkeley-nest/Starling-LM-7B-alpha52,4749,4251,4446,5555,1851,165-1,03-2,872,711,74
5
mistralai/Mistral-7B-Instruct-v0.247,4042,8340,3139,9443,6041,505-7,09-2,88-3,80-1,33
6
HuggingFaceH4/zephyr-7b-alpha44,0031,5933,1915,7543,3137,445-10,80-15,84-0,695,85
7
openchat/openchat-3.5-010656,3550,8656,2850,5857,0750,975-0,06-0,280,730,11
8
Remek/OpenChat3.5-0106-Spichlerz-Bocian56,0848,1552,3947,535-3,69-0,62
9
Nexusflow/Starling-LM-7B-beta56,3848,4351,4247,905-4,96-0,53
10
Qwen/Qwen1.5-32B-Chat54,4854,6155,4651,8350,97-2,79
11
Qwen/Qwen1.5-72B-Chat54,3458,9260,6056,0656,26-2,86
12
Qwen/Qwen2-7B-Instruct54,7347,6153,3042,985-1,42-4,63
13
meta-llama/Meta-Llama-3-70B-Instruct66,4060,7563,0954,305-3,31-6,45
14
meta-llama/Meta-Llama-3-8B-Instruct53,5344,1913,2919,1654,2340,755-40,24-25,030,70-3,44
15
speakleash/Bielik-7B-Instruct-v0.147,9737,5647,9512,0443,3242,525-0,02-25,52-4,664,96
16
mistralai/Mistral-7B-Instruct-v0.349,5043,0243,8539,7549,4440,425-5,65-3,26-0,06-2,59
17
mistralai/Mixtral-8x22B-Instruct-v0.167,9160,7962,8357,425-5,09-3,37
18
mistralai/Mixtral-8x7B-Instruct-v0.157,9550,0043,1342,115-14,82-7,89
19
models/gwint265,5862,6565,4563,315-0,130,66
20
openchat/openchat-3.5-0106-gemma57,3653,3439,0241,3650,0941,255-18,34-11,99-7,27-12,09
21
openchat/openchat-3.6-8b-2024052256,7751,8557,7847,5751,01-4,28
22
23
Remek/OpenChat3.5-0106-Spichlerz-Inst-00135,9127,4336,3635,2436,3635,2400,457,820,457,82
24
berkeley-nest/Starling-LM-7B-alpha36,8325,3842,2246,4942,2246,4905,3921,115,3921,11
25
mistralai/Mistral-7B-Instruct-v0.233,7523,4830,4133,1730,4133,170-3,349,69-3,349,69
26
HuggingFaceH4/zephyr-7b-alpha27,2524,3627,5230,1127,5230,1100,275,750,275,75
27
openchat/openchat-3.5-010637,4828,1539,4843,2039,4843,2002,0015,052,0015,05
28
Remek/OpenChat3.5-0106-Spichlerz-Bocian36,3328,8030,9839,270-5,3410,47
29
Nexusflow/Starling-LM-7B-beta34,9329,1731,3638,250-3,579,07
30
Qwen/Qwen1.5-32B-Chat25,2042,3333,7640,2108,56-2,12
31
Qwen/Qwen1.5-72B-Chat1,1148,8146,4648,95045,350,14
32
Qwen/Qwen2-7B-Instruct41,7138,1235,8644,730-5,856,61
33
meta-llama/Meta-Llama-3-70B-Instruct44,8441,3348,0542,8803,221,55
34
meta-llama/Meta-Llama-3-8B-Instruct35,3823,2635,1436,1035,1436,120-0,2412,85-0,2412,87
35
speakleash/Bielik-7B-Instruct-v0.119,3819,9340,4818,3140,4818,31021,10-1,6221,10-1,62
36
mistralai/Mistral-7B-Instruct-v0.333,2721,6831,8429,9831,4128,890-1,438,30-1,867,22
37
mistralai/Mixtral-8x22B-Instruct-v0.155,3250,3046,9052,870-8,422,57
38
mistralai/Mixtral-8x7B-Instruct-v0.141,5030,0836,6938,250-4,818,17
39
models/gwint248,6353,5050,5959,3901,955,89
40
openchat/openchat-3.5-0106-gemma46,8241,9233,798,7633,638,360-13,03-33,16-13,19-33,57
41
openchat/openchat-3.6-8b-2024052239,1836,5441,1444,5401,968,00