Epoch AI's Tier 4 Math Benchmark Saturated: 5% to 98% in 14 Months
Jsevillamol · x · 2026-09-11
- Citing official Epoch AI data: when the Tier 4 math benchmark launched on July 11, 2025, the top score was just 5%; less than 14 months later the top score is 98% and the benchmark is considered saturated.
- The retweeter notes AI's math progress felt sudden: LLM-based models couldn't even add three years ago, now they top hard math evals.
- Another sign that benchmark saturation is outpacing eval design.
Related event: Epoch AI's Tier 4 Math Benchmark Saturated in 14 Months(3 posts)→
More from Models
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27