PipelineScore
User Leaderboard

Every run. Every user.

96 submissions from 50 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 ↕
1labLabTinyLlama 1.1B Chat28.9DRIP
2labLabQwen 2.5 0.5B Instruct32.5DRIP
3labLabSmolLM 1.7B32.7DRIP
4labLabLlama 3.2 1B Instruct36.5DRIP
5labLabSmolLM2 1.7B40.6TAP
6labLabQwen 2.5 1.5B Instruct43.4TAP
7labLabStarCoder2 3B46.1TAP
8labLabGranite 3.1 2B Instruct49.3TAP
9labLabGemma 2 2B IT49.5TAP
10labLabLlama 3.2 3B Instruct50.1TAP
11labLabQwen 2.5 Coder 1.5B53.8TAP
12labLabQwen 2.5 3B Instruct55.1TAP
13labLabPhi 3 Mini 3.8B55.1TAP
14labLabPhi 3.5 Mini56.0TAP
15labLabLLaVA 1.6 Mistral 7B56.7TAP
16labLabMistral 7B Instruct v0.357.1TAP
17labLabYi 1.5 6B Chat57.2TAP
18labLabAya 23 8B59.3TAP
19labLabGemma 3 4B IT59.8TAP
20labLabZamba 2 7B Instruct60.4FEEDER
21labLabFalcon Mamba 7B61.9FEEDER
22labLabCodeGemma 7B62.2FEEDER
23labLabStarCoder2 7B62.4FEEDER
24labLabPhi 3 Small 7B62.9FEEDER
25labLabLlama 3.1 8B Instruct64.0FEEDER
26labLabCode Llama 34B Instruct64.0FEEDER
27labLabGranite 3.1 8B Instruct64.3FEEDER
28labLabQwen 2.5 7B Instruct64.4FEEDER
29labLabQwen 3 4B Instruct64.6FEEDER
30labLabFalcon 3 10B Instruct64.8FEEDER
31labLabDolphin 2.9 Llama 3 8B65.0FEEDER
32labLabYi 1.5 9B Chat65.1FEEDER
33labLabDolphin 3.0 Llama 3.1 8B65.1FEEDER
34labLabQwen 2.5 VL 7B65.3FEEDER
35labLabSOLAR 10.7B Instruct65.6FEEDER
36labLabLLaVA OneVision 7B66.3FEEDER
37labLabMiniCPM-V 2.6 8B66.7FEEDER
38labLabGemma 2 9B IT66.8FEEDER
39labLabInternLM 2.5 7B Chat66.9FEEDER
40labLabOpenChat 3.6 8B67.7FEEDER
41labLabCommand R67.8FEEDER
42labLabGrok-1 314B68.0FEEDER
43labLabInternLM 2.5 20B Chat68.3FEEDER
44labLabLlama 4 8B Instruct68.3FEEDER
45labLabYi Coder 9B68.4FEEDER
46labLabPhi 3.5 MoE 42B68.4FEEDER
47labLabMixtral 8x7B Instruct68.7FEEDER
48labLabGLM 4 9B Chat69.0FEEDER
49labLabMistral Nemo 12B Instruct69.4FEEDER
50labLabAya 23 35B70.0FEEDER
51labLabHermes 3 Llama 3.1 8B70.0FEEDER
52labLabQwen 2.5 Coder 7B70.7FEEDER
53labLabMistral Small 24B Instruct70.7FEEDER
54labLabL3 70B Euryale71.0FEEDER
55labLabMagnum V4 72B71.6FEEDER
56labLabCommand R+71.8FEEDER
57labLabGemma 3 12B IT72.2FEEDER
58labLabPhi 4 14B72.3FEEDER
59labLabQwen 3 8B Instruct72.6FEEDER
60labLabStarCoder2 15B72.7FEEDER
61labLabDBRX Instruct 132B-MoE73.1FEEDER
62labLabGemma 2 27B IT73.3FEEDER
63labLabGemma 3 27B IT73.4FEEDER
64labLabDeepSeek Coder V2 16B73.4FEEDER
65labLabLlama 4 405B73.6FEEDER
66labLabQwen 3 14B Instruct74.2FEEDER
67labLabDeepSeek R1 Distill Llama 8B75.3MAINLINE
68labLabYi 1.5 34B Chat75.8MAINLINE
69labLabQwen 2.5 32B Instruct76.3MAINLINE
70labLabDevstral Small 24B76.7MAINLINE
71labLabLlama 3.1 70B Instruct76.8MAINLINE
72labLabQwen 2.5 14B Instruct76.9MAINLINE
73labLabCodestral 22B77.9MAINLINE
74labLabGLM 4 Plus77.9MAINLINE
75labLabHermes 3 Llama 3.1 70B78.0MAINLINE
76labLabMistral Large 278.5MAINLINE
77labLabQwen 2.5 Coder 32B78.5MAINLINE
78labLabDeepSeek V2.578.6MAINLINE
79labLabLlama 3.3 70B Instruct78.7MAINLINE
80labLabQwen 2.5 VL 72B78.8MAINLINE
81labLabQwen 3.6 72B79.4MAINLINE
82labLabKimi K2 Instruct79.8MAINLINE
83labLabQwen 2.5 72B Instruct79.9MAINLINE
84labLabWizardLM 2 8x22B80.0MAINLINE
85labLabDeepSeek V3 671B-A37B80.8MAINLINE
86labLabDeepSeek R1 Distill Qwen 32B81.2MAINLINE
87labLabMixtral 8x22B Instruct81.2MAINLINE
88labLabLlama 4 70B Instruct81.2MAINLINE
89labLabCommand A82.0MAINLINE
90labLabQwen 3 32B Instruct82.4MAINLINE
91labLabHermes 3 Llama 3.1 405B83.1MAINLINE
92labLabDeepSeek V483.7MAINLINE
93labLabQwen 3 235B-A22B MoE84.0MAINLINE
94labLabQwen 3 72B Instruct85.0MAINLINE
95labLabDeepSeek Coder V2 236B87.3MAINLINE
96labLabDeepSeek R1 671B-A37B89.5MAINLINE

Top reviewers

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

#1
lab
96 runs
89.5
#2
cpu-only-prophet
17 runs
88.8
#3
flash-attn-fan
17 runs
88.1
#4
rig-tester
15 runs
86.6
#5
mac-stack
21 runs
86.0
#6
quant-or-die
18 runs
85.3
#7
gpu-shopper
12 runs
85.1
#8
local-llama-fan
15 runs
84.8
#9
inference-monk
15 runs
84.7
#10
bench-rat
12 runs
84.5
#11
deepseek-wins
1 run
84.0
#12
sram-hoarder
11 runs
83.8
← Switch to model leaderboard