6
Models Tested
33.3%
Success Rate
1m 22s
Avg Duration
51s - 2m 16s
Duration Range
| Score | Model | Duration | Session (KB) | test.sh |
|---|---|---|---|---|
| 100.0% | openrouter/deepseek/deepseek-v3.1-terminus | 2m 12s | 123.1 | ✅ |
| 100.0% | litellm/GLM-4.5-Air-FP8-dev | 2m 16s | 95.8 | ✅ |
| 0.0% | openrouter/openai/gpt-oss-120b | 1m 1s | 32.8 | ❌ |
| 0.0% | openrouter/qwen/qwen3-coder | 54s | 33.3 | ❌ |
| 0.0% | openrouter/openai/gpt-oss-20b | 1m 1s | 31.8 | ❌ |
| 0.0% | openrouter/qwen/qwen3-14b | 51s | 70.1 | ❌ |