OpenAI's GPT-5.6 Luna Retests on ARC-AGI After 80% Price Cut
GregKamradt · x · 2026-08-08
Following an 80% price reduction for OpenAI's GPT-5.6 Luna model, the ARC Prize Foundation re-evaluated it on the ARC-AGI benchmark.
The results show the model maintained its original performance at a much lower cost: scoring 59.6% on ARC-AGI-2 ($0.18/task) and 90.7% on ARC-AGI-1 ($0.07/task).
Related event: OpenAI Luna Maintains High ARC-AGI Score After 80% Price Cut(3 posts)→
More from Models
- Deconstructing Kimi K3: How KDA and NoROPE Enable Continual Learning — bookwormengr · 2026-08-08
- Floatboat Harness Beats Flagship Models Using Low-Cost DeepSeek — 机器之心 · 2026-08-08
- Qwen3.8-Max Matches GPT-5.6 in Coding Game Test at Quarter the Cost — rohanpaul_ai · 2026-08-08
- Grok 4.6 Shows Major Leaps in Game Development, Demos Coming Soon — ChrisGPT · 2026-08-08
- Hitting a wall with local LLMs: How to break through 77% accuracy in logic judgments? — AZGhost · 2026-08-08
- Western Open Weights Lag as Chinese Labs Continue Sharing SoTA Models — teortaxesTex · 2026-08-08