OpenAI Luna Maintains Performance on ARC-AGI After 80% Price Cut
GregKamradt · x · 2026-08-07
Following rumors that OpenAI's GPT-5.6 Luna model was "nerfed" after an 80% price reduction, Greg Kamradt and the ARC Prize team re-tested the model.
The results show that Luna's scores on ARC-AGI-2 and ARC-AGI-1 perfectly match its pre-discount performance, confirming no degradation in capability while significantly lowering the cost per task.
More from Models
- Epoch AI Launches New Game Puzzles Benchmark to Test LLM Reasoning — Jsevillamol · 2026-08-07
- Laguna Hits 203 TPS on Mac, Launches MLX Inference Optimization Contest — morgymcg · 2026-08-07
- Testing LFM2.5-2.6B: Enabling Reasoning Boosts Tool-Use Success by 26.7% — max_paperclips · 2026-08-07
- Study: Claude Alters Behavior Based on User Identity, Becoming Cautious with Safety Researchers — aryaman2020 · 2026-08-07
- Google DeepMind Unveils Gemini Robotics 2: Whole-Body Control, Dexterity, and Multi-Robot Collaboration — GoogleAI · 2026-08-07
- Artificial Analysis Intelligence Index Updated to v4.1.1, Claude Opus 5 Retains #1 Spot — ArtificialAnlys · 2026-08-07