6
Models Tested
50.0%
Success Rate
48s
Avg Duration
13s - 1m 12s
Duration Range
| Score | Model | Duration | Session (KB) | test_calculator_functions.sh | test_file_exists.sh | test_main_output.sh |
|---|---|---|---|---|---|---|
| 100.0% | openrouter/openai/gpt-oss-20b | 1m 12s | 313.9 | ✅ | ✅ | ✅ |
| 100.0% | openrouter/deepseek/deepseek-v3.1-terminus | 1m 7s | 68.4 | ✅ | ✅ | ✅ |
| 100.0% | litellm/GLM-4.5-Air-FP8-dev | 39s | 75.8 | ✅ | ✅ | ✅ |
| 0.0% | openrouter/openai/gpt-oss-120b | 47s | 37.4 | ❌ | ❌ | ❌ |
| 0.0% | openrouter/qwen/qwen3-coder | 13s | 1.3 | ❌ | ❌ | ❌ |
| 0.0% | openrouter/qwen/qwen3-14b | 50s | 71.0 | ❌ | ❌ | ❌ |