6
Models Tested
16.7%
Success Rate
1m 13s
Avg Duration
14s - 5m 0s
Duration Range
| Score | Model | Duration | Session (KB) | test.sh |
|---|---|---|---|---|
| 100.0% | qwen/qwen3-coder | 57s | 105.9 | ✅ |
| 0.0% | deepseek/deepseek-v3.1-terminus | 20s | 23.8 | ❌ |
| 0.0% | openai/gpt-oss-20b | 30s | 51.5 | ❌ |
| 0.0% | litellm/GLM-4.5-Air-FP8-dev | 5m 0s | 0.0 | — |
| 0.0% | openai/gpt-oss-120b | 23s | 39.7 | ❌ |
| 0.0% | qwen/qwen3-14b | 14s | 23.7 | ❌ |