← Back to user leaderboard
User profile
apple-silicon
9 runsFirst seen 2026-04-10Avg 67.5
Total tokens47.5KAcross every task this user has run
Avg latency1172msPer task, across all submissions
Tasks run2259 submissions x ~25 tasks
Rigs used9Distinct hardware tags
Category signature
Average score per category across all 9 runs.
Code
67.5
Reason
70.7
Write
65.1
Tool Use
67.7
RAG
67.2
Speed
65.4
Hardware mix
Rigs this user benchmarked on.
m3-ultra-256gb1 (11%)
b200-192gb1 (11%)
2x-rtx-40901 (11%)
m2-pro-16gb1 (11%)
rtx-3060-12gb1 (11%)
rtx-4080-16gb1 (11%)
m3-pro-36gb1 (11%)
macbook-pro-m3-pro-18gb1 (11%)
snapdragon-x-elite-32gb1 (11%)
Provider mix
Where they spend their tokens.
alibaba2 (22%)
yi2 (22%)
meta1 (11%)
moonshot1 (11%)
mistral1 (11%)
microsoft1 (11%)
google1 (11%)
Models tried
Best score per model. Click a model to see its full page.
| # | Model | Best Score | Tier |
|---|---|---|---|
| 1 | Qwen 3 235B-A22B MoE | 82.3 | MAINLINE |
| 2 | Llama 3.3 70B Instruct | 78.8 | MAINLINE |
| 3 | Kimi K2 Instruct | 73.9 | FEEDER |
| 4 | Yi Coder 9B | 70.4 | FEEDER |
| 5 | Mistral Nemo 12B Instruct | 66.6 | FEEDER |
| 6 | Phi 3 Small 7B | 60.9 | FEEDER |
| 7 | Gemma 3 4B IT | 58.2 | TAP |
| 8 | Qwen 2.5 Coder 1.5B | 48.4 | TAP |
All submissions
Every run, ordered by score.
| # | Model | Score | Tier |
|---|---|---|---|
| 1 | Qwen 3 235B-A22B MoE | 82.3 | MAINLINE |
| 2 | Llama 3.3 70B Instruct | 78.8 | MAINLINE |
| 3 | Kimi K2 Instruct | 73.9 | FEEDER |
| 4 | Yi Coder 9B | 70.4 | FEEDER |
| 5 | Yi Coder 9B | 68.1 | FEEDER |
| 6 | Mistral Nemo 12B Instruct | 66.6 | FEEDER |
| 7 | Phi 3 Small 7B | 60.9 | FEEDER |
| 8 | Gemma 3 4B IT | 58.2 | TAP |
| 9 | Qwen 2.5 Coder 1.5B | 48.4 | TAP |