JevBench Author Explains Separate Rankings After Microsoft Citation Dispute

The JevBench author responded to Microsoft's citation controversy, explaining that open models and API-provided decision models are ranked separately for fairness. Official results place Microsoft-Decision-1 sixth among API decision models.

2026-10-11 ~ 2026-10-11 · 2 related posts

• JevBench official results: Microsoft-Decision-1 ranks #6 among API decision models — airesearch12 · 2026-10-11
• JevBench creator explains why open and API models get separate leaderboards: fairness — airesearch12 · 2026-10-11