py-05-calc
algorithms · deterministic-tests · seed tier 5 · published
Best result per model
| # | Model | Score | Tests | Run |
|---|---|---|---|---|
| 1 | glm-4.7-flash | 1.000 | 10/10 | UD-Q4_K_XL · 24 GB · runner verified |
| 2 | qwen3-coder-next | 1.000 | 10/10 | UD-Q4_K_XL · 24 GB · runner verified |
| 3 | qwen3.5-9b | 1.000 | 10/10 | UD-Q6_K_XL · 24 GB · runner verified |
| 4 | qwen3-coder | 0.900 | 9/10 | UD-Q4_K_XL · 24 GB · runner verified |
| 5 | devstral | 0.800 | 8/10 | UD-Q4_K_XL · 24 GB · runner verified |
| 6 | phi-4-mini | 0.100 | 1/10 | Q6_K · 24 GB · runner verified |
| 7 | deepseek-r1-qwen-14b | 0.000 | 0/1 | Q6_K · 24 GB · runner verified |
| 8 | qwen3.5-4b | 0.000 | 0/1 | Q4_K_M · 24 GB · runner verified |
| 9 | qwen3.6-27b | 0.000 | 0/1 | UD-Q4_K_XL · 24 GB · runner verified |
| 10 | qwen3.6-35b-a3b | 0.000 | 0/1 | UD-Q4_K_XL · 24 GB · runner verified |
| 11 | qwen3.6-27b-fable-fusion | 0.000 | 0/1 | IQ4_XS · 24 GB · runner verified |
11 models attempted.