PipelineScore
User Leaderboard

Every run. Every user.

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

Want on the board? Run the CLI.
Filter
Allalibabacoherecommunitydatabricksdeepseekgooglemetamicrosoftmistralmoonshotnouszhipu|TRUNKMAINLINEFEEDERTAPDRIP|Lab-verified only
#User ↕Model ↕Score ↑Tier ↕
301sram-hoarderGLM 4 Plus76.5MAINLINE
302rig-testerDeepSeek V2.576.6MAINLINE
303labLabDevstral Small 24B76.7MAINLINE
304labLabLlama 3.1 70B Instruct76.8MAINLINE
305vram-monkMagnum V4 72B76.8MAINLINE
306mlx-mikeCodestral 22B76.9MAINLINE
307mac-stackLlama 3.3 70B Instruct76.9MAINLINE
308gguf-pilgrimGemma 3 27B IT76.9MAINLINE
309rocm-riderDeepSeek Coder V2 16B76.9MAINLINE
310quant-or-dieQwen 2.5 VL 72B76.9MAINLINE
311labLabQwen 2.5 14B Instruct76.9MAINLINE
312rig-testerKimi K2 Instruct77.0MAINLINE
313bench-ratQwen 3 32B Instruct77.0MAINLINE
314inference-monkHermes 3 Llama 3.1 70B77.2MAINLINE
315localmodelsMistral Large 277.3MAINLINE
316agentic_dadMistral Large 277.3MAINLINE
317cuda-cultCommand A77.4MAINLINE
318mlx-mikeMixtral 8x22B Instruct77.4MAINLINE
319cpu-only-prophetDeepSeek V2.577.4MAINLINE
320rocm-riderDeepSeek V2.577.5MAINLINE
321haiku_or_dieMistral Large 277.5MAINLINE
322bench-ratQwen 2.5 VL 72B77.7MAINLINE
323flash-attn-fanGemma 3 27B IT77.7MAINLINE
324frontiermodelMistral Large 277.8MAINLINE
325mlx-mikeWizardLM 2 8x22B77.8MAINLINE
326labLabCodestral 22B77.9MAINLINE
327labLabGLM 4 Plus77.9MAINLINE
328labLabHermes 3 Llama 3.1 70B78.0MAINLINE
329gguf-pilgrimHermes 3 Llama 3.1 70B78.1MAINLINE
330sram-hoarderLlama 4 70B Instruct78.3MAINLINE
331flash-attn-fanMixtral 8x22B Instruct78.3MAINLINE
332tensor-tomasDeepSeek R1 Distill Qwen 32B78.5MAINLINE
333labLabMistral Large 278.5MAINLINE
334labLabQwen 2.5 Coder 32B78.5MAINLINE
335sram-hoarderQwen 2.5 Coder 32B78.5MAINLINE
336localmodelsMistral Large 278.6MAINLINE
337labLabDeepSeek V2.578.6MAINLINE
338labLabLlama 3.3 70B Instruct78.7MAINLINE
339temp-zeroMistral Large 278.7MAINLINE
340apple-siliconLlama 3.3 70B Instruct78.8MAINLINE
341labLabQwen 2.5 VL 72B78.8MAINLINE
342tensor-tomasDBRX Instruct 132B-MoE78.8MAINLINE
343gemini-fanMistral Large 279.0MAINLINE
344quant-or-dieQwen 3 14B Instruct79.0MAINLINE
345silicon-djinnQwen 3.6 72B79.1MAINLINE
346bench-ratLlama 3.1 70B Instruct79.1MAINLINE
347one-shot-onlyQwen 3.6 72B79.1MAINLINE
348flash-attn-fanDevstral Small 24B79.3MAINLINE
349tool-callerQwen 3.6 72B79.3MAINLINE
350labLabQwen 3.6 72B79.4MAINLINE
351gpu-shopperWizardLM 2 8x22B79.5MAINLINE
352benchmark-ratQwen 3.6 72B79.5MAINLINE
353gguf-pilgrimDeepSeek V3 671B-A37B79.6MAINLINE
354mistral-maxiQwen 3.6 72B79.6MAINLINE
355rig-testerHermes 3 Llama 3.1 70B79.7MAINLINE
356labLabKimi K2 Instruct79.8MAINLINE
357reason-firstMistral Large 279.8MAINLINE
358quant-or-dieQwen 3 14B Instruct79.9MAINLINE
359labLabQwen 2.5 72B Instruct79.9MAINLINE
360silicon-djinnMistral Large 279.9MAINLINE
361gpt-cynicMistral Large 280.0MAINLINE
362labLabWizardLM 2 8x22B80.0MAINLINE
363gguf-pilgrimQwen 2.5 Coder 32B80.0MAINLINE
364cli-nativeMistral Large 280.0MAINLINE
365midnight-bencherQwen 2.5 VL 72B80.0MAINLINE
366tensor-tomasCommand A80.3MAINLINE
367judgementalQwen 3.6 72B80.5MAINLINE
368vram-monkDBRX Instruct 132B-MoE80.5MAINLINE
369sram-hoarderQwen 2.5 72B Instruct80.6MAINLINE
370tps-counterQwen 3 72B Instruct80.8MAINLINE
371labLabDeepSeek V3 671B-A37B80.8MAINLINE
372cli-nativeQwen 3.6 72B80.8MAINLINE
373midnight-bencherLlama 4 70B Instruct81.0MAINLINE
374mac-stackQwen 2.5 32B Instruct81.0MAINLINE
375cli-nativeQwen 3.6 72B81.1MAINLINE
376labLabDeepSeek R1 Distill Qwen 32B81.2MAINLINE
377labLabMixtral 8x22B Instruct81.2MAINLINE
378labLabLlama 4 70B Instruct81.2MAINLINE
379tokenwranglerQwen 3.6 72B81.2MAINLINE
380gpt-cynicQwen 3.6 72B81.3MAINLINE
381rocm-riderQwen 3 72B Instruct81.5MAINLINE
382open-weightsDeepSeek V481.5MAINLINE
383flash-attn-fanHermes 3 Llama 3.1 405B81.5MAINLINE
384qwen-stanQwen 3.6 72B81.6MAINLINE
385gpt-cynicDeepSeek V481.7MAINLINE
386mac-stackQwen 2.5 Coder 32B81.8MAINLINE
387open-weightsDeepSeek V481.9MAINLINE
388judgementalDeepSeek V481.9MAINLINE
389quant-or-dieLlama 4 70B Instruct81.9MAINLINE
390labLabCommand A82.0MAINLINE
391edge_runnerDeepSeek V482.2MAINLINE
392flash-attn-fanQwen 3 32B Instruct82.3MAINLINE
393rig-testerDeepSeek R1 Distill Qwen 32B82.3MAINLINE
394apple-siliconQwen 3 235B-A22B MoE82.3MAINLINE
395labLabQwen 3 32B Instruct82.4MAINLINE
396cohere-cultDeepSeek V482.5MAINLINE
397qwen-stanDeepSeek V482.7MAINLINE
398inference-monkQwen 3 235B-A22B MoE83.0MAINLINE
399local-llama-fanDeepSeek R1 671B-A37B83.0MAINLINE
400judgementalDeepSeek V483.1MAINLINE
301–400 of 424
← PreviousNext →

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