IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External Directives

The benchmark measures conditional task and output-contract success. It comes from a paper posted to arXiv on 12 October 2026. An external record may contain a procedure to apply or text to read, depending on the user's request. IBBench-Light tests both uses against the same record. Twelve semantic bases yield 144 matched pairs per model; four quantized instruction models produced 1,152 archived greedy responses. Paired exact-contract accuracy (PECA) requires both members to satisfy their output contracts. Qwen succeeds on 132 execute and 109 process prompts, but only 97 complete pairs, showing what marginal averages omit. We audit literal-target exposure and case normalization, then add 1,722 logged CPU generations to test directive-absent controls, twelve additional semantic bases, within-base wording changes, and generation stopping. In the pinned Phi rerun, changing the end-of-sequence (EOS) set changes exact paired success from 0/144 to 62/144. A bounded IHEval comparison uses the same SmolLM2 checkpoint and output budget while preserving its published instruction roles and scorer. Its task margins and paired count need to be read together with the stopping policy.

Why it counts

The benchmark measures conditional task and output-contract success.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.