Project AURIONAI Use-Cases Research & Innovation

IFBench

knowledge and reasoning.

knowledge and reasoning
4scores
4models
0independent
0maintainer-run
4vendor-reported

Definition

Version
not in the notes
Category
knowledge and reasoning
Maintainer
not in the notes
Status
not in the notes
Home page
not in the notes

Sources

  1. ibm-granite/granite-4.2-8b , Hugging Face huggingface.co https://huggingface.co/ibm-granite/granite-4.2-8b

Scores

4 of 4 scores shown ifbench-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
IBMGranite 4.2 8B79.33 %vendor-reported–––huggingface.co
Motif TechnologiesMotif-378.2 %vendor-reportedtemperature 1.0, top-p 0.95, max sequence 262,144Motif-3 model cardAug 2026huggingface.co
SK TelecomA.X K275.9 %vendor-reportedThinking modeA.X K2 model cardJul 2026huggingface.co
Arcee AITrinity-Large-Thinking52.3 %vendor-reported–Trinity-Large-Thinking model card1 Apr 2026huggingface.co
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "IFBench", https://aurion.semai.id/benchmarks/ifbench/, records of October 2026.