← challenges

tool-03-multi-step

tool-calling · deterministic-tests · seed tier 4 · published

Best result per model

#ModelScoreTestsRun
1glm-4.7-flash
1.000
3/3UD-Q4_K_XL · 24 GB · runner verified
2qwen3-coder
1.000
3/3UD-Q4_K_XL · 24 GB · runner verified
3qwen3-coder-next
1.000
3/3UD-Q4_K_XL · 24 GB · runner verified
4qwen3.5-9b
1.000
3/3UD-Q6_K_XL · 24 GB · runner verified
5devstral
1.000
3/3UD-Q4_K_XL · 24 GB · runner verified
6qwen3.6-27b-fable-fusion
1.000
3/3IQ4_XS · 24 GB · runner verified
7qwen3.6-27b
1.000
3/3UD-Q4_K_XL · 24 GB · runner verified
8qwen3.6-35b-a3b
1.000
3/3UD-Q4_K_XL · 24 GB · runner verified
9phi-4-mini
0.000
0/3Q2_K · 24 GB · runner verified

9 models attempted.