APEX TESTING_
Find out which AI coding models actually deliver and which are just hype.
by HauhauCS
Models Tested
51
Tasks
70
Total Runs
0
Avg Score
0.0
Capital Spent
$0.00
Top Models
View full leaderboard →| # | Model | ELO |
|---|---|---|
| 1 | Claude Opus 4.6 | 1840 |
| 2 | Claude Sonnet 4.6 | 1839 |
| 3 | GPT 5.2 | 1828 |
| 4 | GPT 5.3 Codex | 1808 |
| 5 | Claude Opus 4.5 | 1783 |
Recent Activity
Qwen3.5 35b A3b [Q4_K_XL]→Write tests for untested legacy Flask service
0.08m 37s
Step 3.5 Flash→Add Google OAuth2 login to Express app
9m 27s
Step 3.5 Flash→Build codebase indexer for LLM context windows
0.09m 12s
Step 3.5 Flash→Add retry logic and dead letter queue to Python task queue
28.08m 12s
Step 3.5 Flash→Build real-time portfolio risk calculator
0.07m 23s