IFBench
A benchmark for evaluating the instruction-following capability of large models, measuring how accurately a model executes instructions that carry multiple constraints.
Timeline (last 90 days)
Dory leads Qwen3.5-4B by more than 20 points on IFBench (79 vs 53.83, 4 loops).
Saluki scored 93.5 on the IFEval benchmark (versus the original model's 91.5), and scored 72.7 on IFBench, surpassing the original model's 71.0.
In benchmark tests, 2.0 shows notable improvements over the base model on IFBench (37.3→43.7), When2Call (48→58), and BFCL irrelevance (60→78).
All Facts (3)
Dory leads Qwen3.5-4B by more than 20 points on IFBench (79 vs 53.83, 4 loops).
50%UnverifiedSaluki scored 93.5 on the IFEval benchmark (versus the original model's 91.5), and scored 72.7 on IFBench, surpassing the original model's 71.0.
50%UnverifiedIn benchmark tests, 2.0 shows notable improvements over the base model on IFBench (37.3→43.7), When2Call (48→58), and BFCL irrelevance (60→78).
50%