6
Models Tested
50.0%
Success Rate
2m 11s
Avg Duration
29s - 5m 0s
Duration Range
| Score | Model | Duration | Session (KB) | test.sh |
|---|---|---|---|---|
| 100.0% | openrouter/qwen/qwen3-coder | 1m 42s | 97.5 | ✅ |
| 100.0% | openrouter/deepseek/deepseek-v3.1-terminus | 42s | 75.2 | ✅ |
| 100.0% | litellm/GLM-4.5-Air-FP8-dev | 4m 34s | 158.4 | ✅ |
| 0.0% | openrouter/openai/gpt-oss-120b | 43s | 40.3 | ❌ |
| 0.0% | openrouter/openai/gpt-oss-20b | 5m 0s | 0.0 | — |
| 0.0% | openrouter/qwen/qwen3-14b | 29s | 70.5 | ❌ |