6
Models Tested
33.3%
Success Rate
1m 35s
Avg Duration
34s - 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% | openrouter/openai/gpt-oss-20b | 1m 2s | 192.3 | ✅ | ✅ | ✅ | ✅ |
| 100.0% | openrouter/deepseek/deepseek-v3.1-terminus | 1m 4s | 87.2 | ✅ | ✅ | ✅ | ✅ |
| 0.0% | openrouter/openai/gpt-oss-120b | 52s | 60.5 | ❌ | ❌ | ❌ | ❌ |
| 0.0% | openrouter/qwen/qwen3-coder | 60s | 29.0 | ❌ | ❌ | ❌ | ❌ |
| 0.0% | litellm/GLM-4.5-Air-FP8-dev | 5m 0s | 0.0 | — | — | — | — |
| 0.0% | openrouter/qwen/qwen3-14b | 34s | 70.6 | ❌ | ❌ | ❌ | ❌ |