Dev notes model fixed overthinking with fewer reasoning tokens, suspects benchmaxxing
cedric_chee · x · 2026-10-24
Developer Cedric Chee observes that a recent model update appears to have fixed the overthinking problem: fewer reasoning tokens, much better token efficiency, and far less time wasted on excessive deliberation. But he's cautious and now trying to verify whether these gains are real or just benchmaxxed — optimized for benchmarks rather than genuine tasks.
More from Models
- Kimi K3.1 Pro vs GPT-6 Astra vs Opus 5.5: Building Star Trek's Enterprise D in Minecraft — Angaisb_ · 2026-10-24
- Kimi 3.1 Pro priced like Argon but scores like DeepSeek V4.1 Flash on meme 'Runescape Bench' — scaling01 · 2026-10-24
- Jon Barron details his workflow: Gemini runs experiments, drafts the paper, then rewrites in his style — jon_barron · 2026-10-24
- Users praise Gem Argon for cultural fluency: a frontier model that roots for you — sebkrier · 2026-10-24
- User says Opus silently downgraded to 4.8 mid-task, then told him to talk to people — natesiggard · 2026-10-24
- Suspicious new GitHub accounts reference Qwen4 in Alibaba T-Head repo PRs — brainExploded99 · 2026-10-24