← Back to user leaderboard
User profile
reason-first
3 runsFirst seen 2026-05-05Avg 78.4
Total tokens16.9KAcross every task this user has run
Avg latency792msPer task, across all submissions
Tasks run753 submissions x ~25 tasks
Rigs used1Distinct hardware tags
Category signature
Average score per category across all 3 runs.
Code
78.7
Reason
79.7
Write
75.9
Tool Use
76.5
RAG
81.6
Speed
77.9
Hardware mix
Rigs this user benchmarked on.
no hardware tag3 (100%)
Provider mix
Where they spend their tokens.
deepseek1 (33%)
mistral1 (33%)
cohere1 (33%)
Models tried
Best score per model. Click a model to see its full page.
| # | Model | Best Score | Tier |
|---|---|---|---|
| 1 | DeepSeek V4 | 83.4 | MAINLINE |
| 2 | Mistral Large 2 | 79.8 | MAINLINE |
| 3 | Command R+ | 72.0 | FEEDER |
All submissions
Every run, ordered by score.
| # | Model | Score | Tier |
|---|---|---|---|
| 1 | DeepSeek V4 | 83.4 | MAINLINE |
| 2 | Mistral Large 2 | 79.8 | MAINLINE |
| 3 | Command R+ | 72.0 | FEEDER |