PipelineScore
User Leaderboard

Every run. Every user.

96 submissions from 52 users. Sort, filter, find someone who ran your model.

Want on the board? Run the CLI.
Filter
Allalibababigcodecognitivecomputationscoherecommunitydatabricksdeepseekgooglehuggingfaceibminternlmmetamicrosoftmistralmoonshotnousopenbmbopenchattiiupstagexaiyizhipuzyphra|TRUNKMAINLINEFEEDERTAPDRIP|Lab-verified onlyClear filters
#User ↕Model ↕Score ↓Tier ↕
1labLabDeepSeek R1 671B-A37B
89.5
MAINLINE
2labLabDeepSeek Coder V2 236B
87.3
MAINLINE
3labLabQwen 3 72B Instruct
85.0
MAINLINE
4labLabQwen 3 235B-A22B MoE
84.0
MAINLINE
5labLabDeepSeek V4
83.7
MAINLINE
6labLabHermes 3 Llama 3.1 405B
83.1
MAINLINE
7labLabQwen 3 32B Instruct
82.4
MAINLINE
8labLabCommand A
82.0
MAINLINE
9labLabLlama 4 70B Instruct
81.2
MAINLINE
10labLabMixtral 8x22B Instruct
81.2
MAINLINE
11labLabDeepSeek R1 Distill Qwen 32B
81.2
MAINLINE
12labLabDeepSeek V3 671B-A37B
80.8
MAINLINE
13labLabWizardLM 2 8x22B
80.0
MAINLINE
14labLabQwen 2.5 72B Instruct
79.9
MAINLINE
15labLabKimi K2 Instruct
79.8
MAINLINE
16labLabQwen 3.6 72B
79.4
MAINLINE
17labLabQwen 2.5 VL 72B
78.8
MAINLINE
18labLabLlama 3.3 70B Instruct
78.7
MAINLINE
19labLabDeepSeek V2.5
78.6
MAINLINE
20labLabMistral Large 2
78.5
MAINLINE
21labLabQwen 2.5 Coder 32B
78.5
MAINLINE
22labLabHermes 3 Llama 3.1 70B
78.0
MAINLINE
23labLabGLM 4 Plus
77.9
MAINLINE
24labLabCodestral 22B
77.9
MAINLINE
25labLabQwen 2.5 14B Instruct
76.9
MAINLINE
26labLabLlama 3.1 70B Instruct
76.8
MAINLINE
27labLabDevstral Small 24B
76.7
MAINLINE
28labLabQwen 2.5 32B Instruct
76.3
MAINLINE
29labLabYi 1.5 34B Chat
75.8
MAINLINE
30labLabDeepSeek R1 Distill Llama 8B
75.3
MAINLINE
31labLabQwen 3 14B Instruct
74.2
FEEDER
32labLabLlama 4 405B
73.6
FEEDER
33labLabDeepSeek Coder V2 16B
73.4
FEEDER
34labLabGemma 3 27B IT
73.4
FEEDER
35labLabGemma 2 27B IT
73.3
FEEDER
36labLabDBRX Instruct 132B-MoE
73.1
FEEDER
37labLabStarCoder2 15B
72.7
FEEDER
38labLabQwen 3 8B Instruct
72.6
FEEDER
39labLabPhi 4 14B
72.3
FEEDER
40labLabGemma 3 12B IT
72.2
FEEDER
41labLabCommand R+
71.8
FEEDER
42labLabMagnum V4 72B
71.6
FEEDER
43labLabL3 70B Euryale
71.0
FEEDER
44labLabQwen 2.5 Coder 7B
70.7
FEEDER
45labLabMistral Small 24B Instruct
70.7
FEEDER
46labLabAya 23 35B
70.0
FEEDER
47labLabHermes 3 Llama 3.1 8B
70.0
FEEDER
48labLabMistral Nemo 12B Instruct
69.4
FEEDER
49labLabGLM 4 9B Chat
69.0
FEEDER
50labLabMixtral 8x7B Instruct
68.7
FEEDER
51labLabPhi 3.5 MoE 42B
68.4
FEEDER
52labLabYi Coder 9B
68.4
FEEDER
53labLabLlama 4 8B Instruct
68.3
FEEDER
54labLabInternLM 2.5 20B Chat
68.3
FEEDER
55labLabGrok-1 314B
68.0
FEEDER
56labLabCommand R
67.8
FEEDER
57labLabOpenChat 3.6 8B
67.7
FEEDER
58labLabInternLM 2.5 7B Chat
66.9
FEEDER
59labLabGemma 2 9B IT
66.8
FEEDER
60labLabMiniCPM-V 2.6 8B
66.7
FEEDER
61labLabLLaVA OneVision 7B
66.3
FEEDER
62labLabSOLAR 10.7B Instruct
65.6
FEEDER
63labLabQwen 2.5 VL 7B
65.3
FEEDER
64labLabYi 1.5 9B Chat
65.1
FEEDER
65labLabDolphin 3.0 Llama 3.1 8B
65.1
FEEDER
66labLabDolphin 2.9 Llama 3 8B
65.0
FEEDER
67labLabFalcon 3 10B Instruct
64.8
FEEDER
68labLabQwen 3 4B Instruct
64.6
FEEDER
69labLabQwen 2.5 7B Instruct
64.4
FEEDER
70labLabGranite 3.1 8B Instruct
64.3
FEEDER
71labLabCode Llama 34B Instruct
64.0
FEEDER
72labLabLlama 3.1 8B Instruct
64.0
FEEDER
73labLabPhi 3 Small 7B
62.9
FEEDER
74labLabStarCoder2 7B
62.4
FEEDER
75labLabCodeGemma 7B
62.2
FEEDER
76labLabFalcon Mamba 7B
61.9
FEEDER
77labLabZamba 2 7B Instruct
60.4
FEEDER
78labLabGemma 3 4B IT
59.8
TAP
79labLabAya 23 8B
59.3
TAP
80labLabYi 1.5 6B Chat
57.2
TAP
81labLabMistral 7B Instruct v0.3
57.1
TAP
82labLabLLaVA 1.6 Mistral 7B
56.7
TAP
83labLabPhi 3.5 Mini
56.0
TAP
84labLabQwen 2.5 3B Instruct
55.1
TAP
85labLabPhi 3 Mini 3.8B
55.1
TAP
86labLabQwen 2.5 Coder 1.5B
53.8
TAP
87labLabLlama 3.2 3B Instruct
50.1
TAP
88labLabGemma 2 2B IT
49.5
TAP
89labLabGranite 3.1 2B Instruct
49.3
TAP
90labLabStarCoder2 3B
46.1
TAP
91labLabQwen 2.5 1.5B Instruct
43.4
TAP
92labLabSmolLM2 1.7B
40.6
TAP
93labLabLlama 3.2 1B Instruct
36.5
DRIP
94labLabSmolLM 1.7B
32.7
DRIP
95labLabQwen 2.5 0.5B Instruct
32.5
DRIP
96labLabTinyLlama 1.1B Chat
28.9
DRIP

Top reviewers

By best PipelineScore submitted. Click a user to open their dashboard.

#1
drew
3 runs
93.2
#2
lab
96 runs
89.5
#3
cpu-only-prophet
17 runs
88.8
#4
flash-attn-fan
17 runs
88.1
#5
rig-tester
15 runs
86.6
#6
mac-stack
21 runs
86.0
#7
quant-or-die
18 runs
85.3
#8
gpu-shopper
12 runs
85.1
#9
local-llama-fan
15 runs
84.8
#10
inference-monk
15 runs
84.7
#11
bench-rat
12 runs
84.5
#12
deepseek-wins
1 run
84.0
← Switch to model leaderboard