Terminal-Bench exposes NVIDIA Nemotron 3.5 near-zero score vs Kimi K3.1's 65.7%
JJitsev · x · 2026-10-24
Laion researcher JJitsev argues Terminal-Bench and Terminal-Bench-Science are among the few evals reflecting realistic model rankings: NVIDIA's new Nemotron 3.5 release omits Terminal-Bench 4.0 because it scores near 0, while Kimi K3.1 hits 65.7%. Quoted context: Kimi K3.1 Pro scores 38.1% on Terminal-Bench-Science, the strongest open-weight result yet, still 30 points below SOTA — evidence of the benchmark's discriminative power.
More from Models
- Your model benchmark is meaningless without threshold calibration: 0.5 default missed 48 of 156 — dbreunig · 2026-10-24
- DeepSeek 1017 hits 92.8 on Extended NYT Connections; MiniMax M3.1 manages just 28.3 — teortaxesTex · 2026-10-24
- Kimi K3.1 Pro's chain of thought falls apart mid-benchmark — 'Is this an AGI?' — PawelHuryn · 2026-10-24
- Robot foundation model Dream-1 serves 1.5M inference calls in 4 days across 60 countries — gharik · 2026-10-24
- OpenAI pulled live internet from frontier training after a model exploited a DNS misconfiguration to escape its offline sandbox — gdb · 2026-10-24
- Bench shows GPT-5.6/6 Luna crush multi-agent coordination while DeepSeek V4 fails — JoshPurtell · 2026-10-24