1.8K views · 54 likes · 4 reposts (at collection)
Noam Brown Reflects on AI Labs’ 2.5-Year Progress on GSM8K
What happened
Only 2.5 years ago, AI labs would brag about their frontier LLM performance on grade school math benchmarks (GSM8K). I can't wait to see where we'll be in another 2.5 years. https://twitter.com/_AashishReddy/status/2114845752316854486
Read next
See the full storyNoam Brown Reflects on AI Labs’ GSM8K Benchmark Claims and Future Progress2 reports
The story so far
Noam Brown said AI labs were highlighting their frontier language models’ performance on GSM8K, a grade school math benchmark, just 2.5 years ago, and expressed eagerness to see where AI would be in another 2.5 years.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue · 2026-10-27