← challenges

bcb-0026

lib-knowledge · deterministic-tests · seed tier 2 · published

Best result per model

#ModelScoreTestsRun
1qwen3-coder
1.000
6/6UD-Q4_K_XL · 24 GB · runner verified
2qwen3-coder-next
1.000
6/6UD-Q4_K_XL · 24 GB · runner verified
3qwen3.5-9b
1.000
6/6UD-Q6_K_XL · 24 GB · runner verified
4qwen3.6-27b-fable-fusion
1.000
6/6IQ4_XS · 24 GB · runner verified
5glm-4.7-flash
0.333
2/6UD-Q4_K_XL · 24 GB · runner verified
6devstral
0.333
2/6UD-Q4_K_XL · 24 GB · runner verified
7deepseek-r1-qwen-14b
0.333
2/6Q6_K · 24 GB · runner verified
8phi-4-mini
0.333
2/6Q6_K · 24 GB · runner verified
9qwen3.6-27b
0.333
2/6UD-Q4_K_XL · 24 GB · runner verified
10qwen3.6-35b-a3b
0.333
2/6UD-Q4_K_XL · 24 GB · runner verified

10 models attempted.