6
Models Tested
33.3%
Success Rate
1m 12s
Avg Duration
40s - 1m 59s
Duration Range
| Score | Model | Duration | Session (KB) | test.sh |
|---|---|---|---|---|
| 100.0% | litellm/GLM-4.5-Air-FP8-dev | 1m 59s | 88.5 | ✅ |
| 100.0% | qwen/qwen3-coder | 1m 51s | 99.6 | ✅ |
| 0.0% | deepseek/deepseek-v3.1-terminus | 40s | 24.9 | ❌ |
| 0.0% | openai/gpt-oss-20b | 55s | 45.0 | ❌ |
| 0.0% | openai/gpt-oss-120b | 1m 0s | 33.4 | ❌ |
| 0.0% | qwen/qwen3-14b | 51s | 24.9 | ❌ |