User profile

judgemental

3 runsFirst seen 2026-04-28Avg 81.8

Best PipelineScore

83.1MAINLINE

Total tokens15.5KAcross every task this user has run

Avg latency790msPer task, across all submissions

Tasks run753 submissions x ~25 tasks

Rigs used3Distinct hardware tags

Category signature

Average score per category across all 3 runs.

Code

81.4

Reason

81.1

Write

79.2

Tool Use

81.2

RAG

84.8

Speed

84.7

Rigs this user benchmarked on.

m4-pro-48gb1 (33%)

no hardware tag1 (33%)

ryzen-7950x-cpu-only1 (33%)

Where they spend their tokens.

deepseek2 (67%)

alibaba1 (33%)

Best score per model. Click a model to see its full page.

#	Model	Provider	Best Score	Tier	Achieved
1	DeepSeek V4	deepseek	83.1	MAINLINE	2026-05-05
2	Qwen 3.6 72B	alibaba	80.5	MAINLINE	2026-05-20

Every run, ordered by score.

#	Model	Hardware	Score	Tier	Code	Reason	Write	Tool Use	RAG	Speed	Tokens	Avg ms	Date
1	DeepSeek V4	m4-pro-48gb	83.1	MAINLINE	84.5	79.6	82.2	79.6	89.9	84.5	5.2K	775	2026-05-05
2	DeepSeek V4	—	81.9	MAINLINE	81.4	83.2	74.5	85.5	85.8	81.7	5.3K	750	2026-04-28
3	Qwen 3.6 72B	ryzen-7950x-cpu-only	80.5	MAINLINE	78.3	80.5	81.0	78.6	78.6	87.9	4.9K	844	2026-05-20