← Back to user leaderboard
User profile
tool-caller
2 runsFirst seen 2026-05-07Avg 76.2
Total tokens11.5KAcross every task this user has run
Avg latency823msPer task, across all submissions
Tasks run502 submissions x ~25 tasks
Rigs used2Distinct hardware tags
Category signature
Average score per category across all 2 runs.
Code
79.4
Reason
74.3
Write
75.8
Tool Use
75.7
RAG
74.7
Speed
75.8
Hardware mix
Rigs this user benchmarked on.
cloud-api1 (50%)
m3-max-128gb1 (50%)
Provider mix
Where they spend their tokens.
alibaba1 (50%)
meta1 (50%)
Models tried
Best score per model. Click a model to see its full page.
| # | Model | Best Score | Tier |
|---|---|---|---|
| 1 | Qwen 3.6 72B | 79.3 | MAINLINE |
| 2 | Llama 4 405B | 73.1 | FEEDER |
All submissions
Every run, ordered by score.
| # | Model | Score | Tier |
|---|---|---|---|
| 1 | Qwen 3.6 72B | 79.3 | MAINLINE |
| 2 | Llama 4 405B | 73.1 | FEEDER |