6
Models Tested
66.7%
Success Rate
1m 10s
Avg Duration
32s - 2m 4s
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% | openrouter/openai/gpt-oss-120b | 1m 9s | 195.5 | ✅ | ✅ | ✅ | ✅ |
| 100.0% | openrouter/qwen/qwen3-coder | 1m 8s | 62.1 | ✅ | ✅ | ✅ | ✅ |
| 100.0% | openrouter/deepseek/deepseek-v3.1-terminus | 1m 12s | 62.8 | ✅ | ✅ | ✅ | ✅ |
| 100.0% | litellm/GLM-4.5-Air-FP8-dev | 2m 4s | 83.1 | ✅ | ✅ | ✅ | ✅ |
| 0.0% | openrouter/openai/gpt-oss-20b | 55s | 138.6 | ❌ | ❌ | ❌ | ❌ |
| 0.0% | openrouter/qwen/qwen3-14b | 32s | 70.8 | ❌ | ❌ | ❌ | ❌ |