PipelineScore
User Leaderboard

Every run. Every user.

140 submissions from 50 users. Sort, filter, find someone who ran your model.

Want on the board? Run the CLI.
Filter
Allalibabacoherecommunitydatabricksdeepseekgooglemetamicrosoftmistralmoonshotnousyizhipu|TRUNKMAINLINEFEEDERTAPDRIP|Lab-verified onlyClear filters
#User ↕Model ↕Score ↑Tier ↕
1rocm-riderLlama 3.1 70B Instruct75.2MAINLINE
2local-llama-fanQwen 2.5 14B Instruct75.2MAINLINE
3labLabDeepSeek R1 Distill Llama 8B75.3MAINLINE
4mac-stackMagnum V4 72B75.3MAINLINE
5tps-counterQwen 2.5 Coder 7B75.5MAINLINE
6tensor-tomasGLM 4 Plus75.6MAINLINE
7gguf-pilgrimDevstral Small 24B75.6MAINLINE
8local-llama-fanGemma 3 12B IT75.7MAINLINE
9labLabYi 1.5 34B Chat75.8MAINLINE
10sram-hoarderGemma 3 27B IT75.9MAINLINE
11local-llama-fanQwen 2.5 32B Instruct76.0MAINLINE
12quant-or-dieLlama 3.1 70B Instruct76.0MAINLINE
13mac-stackQwen 3 32B Instruct76.3MAINLINE
14labLabQwen 2.5 32B Instruct76.3MAINLINE
15rocm-riderKimi K2 Instruct76.4MAINLINE
16cuda-cultCommand A76.5MAINLINE
17sram-hoarderGLM 4 Plus76.5MAINLINE
18rig-testerDeepSeek V2.576.6MAINLINE
19labLabDevstral Small 24B76.7MAINLINE
20labLabLlama 3.1 70B Instruct76.8MAINLINE
21vram-monkMagnum V4 72B76.8MAINLINE
22mlx-mikeCodestral 22B76.9MAINLINE
23mac-stackLlama 3.3 70B Instruct76.9MAINLINE
24gguf-pilgrimGemma 3 27B IT76.9MAINLINE
25rocm-riderDeepSeek Coder V2 16B76.9MAINLINE
26quant-or-dieQwen 2.5 VL 72B76.9MAINLINE
27labLabQwen 2.5 14B Instruct76.9MAINLINE
28rig-testerKimi K2 Instruct77.0MAINLINE
29bench-ratQwen 3 32B Instruct77.0MAINLINE
30inference-monkHermes 3 Llama 3.1 70B77.2MAINLINE
31localmodelsMistral Large 277.3MAINLINE
32agentic_dadMistral Large 277.3MAINLINE
33cuda-cultCommand A77.4MAINLINE
34mlx-mikeMixtral 8x22B Instruct77.4MAINLINE
35cpu-only-prophetDeepSeek V2.577.4MAINLINE
36rocm-riderDeepSeek V2.577.5MAINLINE
37haiku_or_dieMistral Large 277.5MAINLINE
38bench-ratQwen 2.5 VL 72B77.7MAINLINE
39flash-attn-fanGemma 3 27B IT77.7MAINLINE
40frontiermodelMistral Large 277.8MAINLINE
41mlx-mikeWizardLM 2 8x22B77.8MAINLINE
42labLabCodestral 22B77.9MAINLINE
43labLabGLM 4 Plus77.9MAINLINE
44labLabHermes 3 Llama 3.1 70B78.0MAINLINE
45gguf-pilgrimHermes 3 Llama 3.1 70B78.1MAINLINE
46sram-hoarderLlama 4 70B Instruct78.3MAINLINE
47flash-attn-fanMixtral 8x22B Instruct78.3MAINLINE
48tensor-tomasDeepSeek R1 Distill Qwen 32B78.5MAINLINE
49labLabMistral Large 278.5MAINLINE
50labLabQwen 2.5 Coder 32B78.5MAINLINE
51sram-hoarderQwen 2.5 Coder 32B78.5MAINLINE
52localmodelsMistral Large 278.6MAINLINE
53labLabDeepSeek V2.578.6MAINLINE
54labLabLlama 3.3 70B Instruct78.7MAINLINE
55temp-zeroMistral Large 278.7MAINLINE
56apple-siliconLlama 3.3 70B Instruct78.8MAINLINE
57labLabQwen 2.5 VL 72B78.8MAINLINE
58tensor-tomasDBRX Instruct 132B-MoE78.8MAINLINE
59gemini-fanMistral Large 279.0MAINLINE
60quant-or-dieQwen 3 14B Instruct79.0MAINLINE
61silicon-djinnQwen 3.6 72B79.1MAINLINE
62bench-ratLlama 3.1 70B Instruct79.1MAINLINE
63one-shot-onlyQwen 3.6 72B79.1MAINLINE
64flash-attn-fanDevstral Small 24B79.3MAINLINE
65tool-callerQwen 3.6 72B79.3MAINLINE
66labLabQwen 3.6 72B79.4MAINLINE
67gpu-shopperWizardLM 2 8x22B79.5MAINLINE
68benchmark-ratQwen 3.6 72B79.5MAINLINE
69gguf-pilgrimDeepSeek V3 671B-A37B79.6MAINLINE
70mistral-maxiQwen 3.6 72B79.6MAINLINE
71rig-testerHermes 3 Llama 3.1 70B79.7MAINLINE
72labLabKimi K2 Instruct79.8MAINLINE
73reason-firstMistral Large 279.8MAINLINE
74quant-or-dieQwen 3 14B Instruct79.9MAINLINE
75labLabQwen 2.5 72B Instruct79.9MAINLINE
76silicon-djinnMistral Large 279.9MAINLINE
77gpt-cynicMistral Large 280.0MAINLINE
78labLabWizardLM 2 8x22B80.0MAINLINE
79gguf-pilgrimQwen 2.5 Coder 32B80.0MAINLINE
80cli-nativeMistral Large 280.0MAINLINE
81midnight-bencherQwen 2.5 VL 72B80.0MAINLINE
82tensor-tomasCommand A80.3MAINLINE
83judgementalQwen 3.6 72B80.5MAINLINE
84vram-monkDBRX Instruct 132B-MoE80.5MAINLINE
85sram-hoarderQwen 2.5 72B Instruct80.6MAINLINE
86tps-counterQwen 3 72B Instruct80.8MAINLINE
87labLabDeepSeek V3 671B-A37B80.8MAINLINE
88cli-nativeQwen 3.6 72B80.8MAINLINE
89midnight-bencherLlama 4 70B Instruct81.0MAINLINE
90mac-stackQwen 2.5 32B Instruct81.0MAINLINE
91cli-nativeQwen 3.6 72B81.1MAINLINE
92labLabDeepSeek R1 Distill Qwen 32B81.2MAINLINE
93labLabMixtral 8x22B Instruct81.2MAINLINE
94labLabLlama 4 70B Instruct81.2MAINLINE
95tokenwranglerQwen 3.6 72B81.2MAINLINE
96gpt-cynicQwen 3.6 72B81.3MAINLINE
97rocm-riderQwen 3 72B Instruct81.5MAINLINE
98open-weightsDeepSeek V481.5MAINLINE
99flash-attn-fanHermes 3 Llama 3.1 405B81.5MAINLINE
100qwen-stanQwen 3.6 72B81.6MAINLINE
1–100 of 140
Next →

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