Sailing sim race shows Chinese models lag frontier: "cheap tokens ≠ cheap agents"
shekitup · x · 2026-11-05
To test claims that Chinese models have caught up, the author raced the big three against Astra in their own sailing simulator. Kimi struggled while costing 2x Astra; GLM and DeepSeek barely got out of the blocks. Takeaway: frontier models remain far better—cheap tokens don't make cheap agents.
More from Models
- Sam Altman resurfaces ahead of rumored big OpenAI drop on Thursday — iruletheworldmo · 2026-11-05
- Epoch AI rebuilds its ECI with Bayesian methodology for sharper model comparisons — scaling01 · 2026-11-05
- Bittensor subnet to release ChronoLLM-16B, claiming lead in point-in-time financial LLMs — const_reborn · 2026-11-05
- Epoch AI now gives probabilistic model matchups: Astra 72% likely above Opus 5.5 — teortaxesTex · 2026-11-05
- OpenAI quietly built a hidden ChatGPT shopping mall that mines Gmail for coupons — ryanmerket · 2026-11-05
- Ripple claims frontier-level open-weight model trained in 32 minutes at one-tenth cost — annadgoldie · 2026-11-05