6
Models Tested
50.0%
Success Rate
1m 42s
Avg Duration
17s - 5m 0s
Duration Range
| Score | Model | Duration | Session (KB) | test_1_file_exists.sh | test_2_valid_json.sh | test_3_json_structure.sh | test_4_expected_content.sh |
|---|---|---|---|---|---|---|---|
| 100.0% | openai/gpt-oss-20b | 1m 3s | 656.2 | ✅ | ✅ | ✅ | ✅ |
| 100.0% | openai/gpt-oss-120b | 2m 21s | 786.4 | ✅ | ✅ | ✅ | ✅ |
| 100.0% | qwen/qwen3-coder | 1m 12s | 65.6 | ✅ | ✅ | ✅ | ✅ |
| 0.0% | deepseek/deepseek-v3.1-terminus | 22s | 23.8 | ❌ | ❌ | ❌ | ❌ |
| 0.0% | litellm/GLM-4.5-Air-FP8-dev | 5m 0s | 0.0 | — | — | — | — |
| 0.0% | qwen/qwen3-14b | 17s | 23.7 | ❌ | ❌ | ❌ | ❌ |