JevBench Switches to Capability Score and Adds Custom Cost Thresholds

JevBench v1.5.4 now scores models by Capability Score instead of Composite Score, and lets users customize speed and cost thresholds, which can change the leaderboard winner.

2026-10-02 ~ 2026-10-02 · 2 related posts

• JevBench v1.5.4 ditches cost-weighted scoring; Original Jev returns to top of leaderboard — airesearch12 · 2026-10-02
• JevBench adds configurable cost tolerance: different budgets, different winners — airesearch12 · 2026-10-02