Blind tests: DeepSeek matches Opus on 95% of agentic loops at 40x lower cost
bindureddy · x · 2026-11-11
Bindu Reddy reports that in blind tests DeepSeek matches frontier models (Carbon / Opus) on 95% of agentic loops while being roughly 40x cheaper. The one weakness: on very long agentic loops it degrades faster than frontier models — he argues fixing context compaction should bring it on par.
More from Models
- Commit leak reveals unreleased Gemini 4 variants: Argon, Hydrogen and Helix (unconfirmed) — BlackHC · 2026-11-11
- Rewiring just 89 of 442,368 neurons in Qwen3-8B matches full SFT for a persona — maxsloef · 2026-11-11
- Unsloth ships Qwen3.8-27B Dynamic V3.1 GGUFs with 5-10% accuracy gains — danielhanchen · 2026-11-11
- Zvi: being forced back to an older model is the best reminder of AI progress — TheZvi · 2026-11-11
- Screenshots Made a 4B Browser Agent Worse: A Postmortem With Real Numbers — Stunning-Sherbet1853 · 2026-11-11
- Codex safety filter flags developer's hobby git forge app as cybersecurity risk — brianmichel · 2026-11-11