New TB-fn Benchmark Exposes Model Performance Gaps on Terminal Tasks
abeirami · x · 2026-08-26
Researchers released TB-fn, a stricter benchmark that reworks Terminal Bench 2.1 tasks by adding steps, tightening requirements, and requiring complex algorithms to eliminate shortcut solutions. When tested on TB-fn, models that clustered together on the original leaderboard spread across performance tiers, revealing a wider gap between open-weight families and frontier models.
More from Research
- Interpretability paper incoming: in-depth look at testing explanations on modern LLMs — burny_tech · 2026-10-16
- Better-learning models tend to be more interpretable, argues Nick Cammarata — burny_tech · 2026-10-16
- Cornell and Amazon revisit the 16x pretraining compute gap: diffusion LMs need only 3-8x — LucaAmb · 2026-10-16
- AI trained on the fraction of human intelligence that fit the page — r0ck3t23 · 2026-10-16
- Quotient Recurrent Reasoners hit 97.9% on Sudoku-Extreme with 78% fewer loops — burny_tech · 2026-10-16
- Mathematicians publish explainer for the Egyptian fraction proof in OpenAI's proofs collection — burny_tech · 2026-10-16