New Claude model beats Pokemon in 50 hours, 5x faster than Opus 4.7 five months ago
ben_j_todd · x · 2026-09-22
benjtodd's ongoing Pokemon benchmark shows steep Claude capability gains: Opus 4.0 needed 1,000 hours to get halfway, Opus 4.5 nearly finished in 1,000 hours, Opus 4.6 was another 10x faster. Fifteen months later, Fable beat the game in 50 hours — roughly the speed of a human child and 5x faster than Opus 4.7 just five months ago.
Related event: Claude Beats Pokémon in 50 Hours, 20x Faster Than 15 Months Ago(2 posts)→
More from Models
- Evolvent AI cofounder: China leads in pretraining architecture innovation, lags ~6 months on post-training data — vista8 · 2026-09-22
- GPT-6 Astra Cracks an Enigma Message Unsolved Since 2005 — jedisct1 · 2026-09-22
- Dev: Opus 5 is 'dumb as bricks' for coding, I'm switching to ChatGPT — rickasaurus · 2026-09-22
- Rumored GPT-6 Sol pricing: $2.50 input, $15 output per million tokens — iannuttall · 2026-09-22
- Real-world test: AI builds a self-contained bash-only agenda tool in 45 minutes — elonmusk · 2026-09-22
- Transformer Explainer shows GPT-2 tokenization: 'empowers' splits into two tokens — petrusenko_max · 2026-09-22