6
Models Tested
50.0%
Success Rate
1m 31s
Avg Duration
55s - 3m 46s
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 7s | 174.0 | ✅ | ✅ | ✅ | ✅ |
| 100.0% | openrouter/deepseek/deepseek-v3.1-terminus | 1m 15s | 51.1 | ✅ | ✅ | ✅ | ✅ |
| 100.0% | litellm/GLM-4.5-Air-FP8-dev | 1m 2s | 97.6 | ✅ | ✅ | ✅ | ✅ |
| 0.0% | openrouter/qwen/qwen3-coder | 55s | 42.9 | ❌ | ❌ | ❌ | ❌ |
| 0.0% | openrouter/openai/gpt-oss-20b | 3m 46s | 3389.8 | ❌ | ❌ | ❌ | ❌ |
| 0.0% | openrouter/qwen/qwen3-14b | 1m 2s | 70.4 | ❌ | ❌ | ❌ | ❌ |