TerminalBench Deep Dive: GPT-5.6 Leads, Many Models Drop in Rank
abeirami · x · 2026-08-27
Top 20 models from TerminalBench 2.1 were re-evaluated on the stricter TB-fn benchmark. Results show a widening performance gap, with GPT-5.6 Sol and Opus 5 maintaining their lead, while others see significant drops. TB-fn adds steps and removes shortcuts, increasing task difficulty by 38% on average. Pareto frontier analysis also shows GPT-5.6 Luna and DeepSeek V4 Flash outperforming ox-alpha in cost-effectiveness.
More from Models
- DeepSeek outage compensation reportedly hands single accounts over $850K in API credits — teortaxesTex · 2026-10-15
- Nat Lambert: wave of AI releases rumored — thinky, muse spark, Fable 5.5, OpenAI — natolambert · 2026-10-15
- Musk amplifies dev's verdict: Grok Bot easier to use than Codex and Claude — elonmusk · 2026-10-15
- Rumor: New Anthropic model imminent, apparently behind a batch of high-severity Chrome CVEs — matthew_d_green · 2026-10-15
- StartLux-Decision debuts RL-trained calibrated decision models, 27B scores 72.8 — startlux-models · 2026-10-15
- Meta's Muse Code slammed for harsh quotas: 21% left after 5 hours — ThomasScialom · 2026-10-15