Opus 5 tops an ARC-AGI-3 chart but at much higher evaluation cost
Angaisb_ · x · 2026-07-25
The attached chart compares Opus 5, Opus 4.8, and GPT-5.6 Sol on ARC-AGI-3 “novel problem-solving by cost.” Opus 5 sits far above the other points on the score axis, but at a much higher total evaluation cost than earlier runs. The image is essentially a benchmark snapshot arguing that Opus 5’s reasoning gains come with steep eval cost.
Related event: Anthropic Releases Claude Opus 5: SOTA Performance at Half the Price(128 posts)→
More from Models
- MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27