Anthropic’s ARC-AGI-3 lead is being called meaningless as the benchmark saturates
morqon · x · 2026-07-25
- The thread pushes back on Anthropic’s claim that Claude Opus 5 is three times better than the next-best model on ARC-AGI-3, arguing that the benchmark was effectively solved on day one and may be of limited value.
- The cited post highlights a broader criticism of evals that are already saturated: once a benchmark is too easy, large score gaps stop saying much about real-world capability.
- The takeaway is less about one score and more about how quickly some public benchmarks become obsolete as models improve.
Related event: Opus 5's High ARC-AGI-3 Score Sparks Cheating and Overfitting Controversy(11 posts)→
More from Models
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11