Cursor’s Composer 2.5 beats Kimi on coding but loses badly on math and science
gleech · x · 2026-07-21
A new write-up tests whether post-training can specialize a general model without preserving broad reasoning.
The reported result is stark: Cursor’s Composer 2.5, a coding finetune of Kimi, improves strongly on visual reasoning, RPG-style games, and agentic coding, but loses heavily on math and scientific reasoning benchmarks. The thread argues this is evidence against the old assumption that coding training automatically improves general reasoning.
More from coding & agent
- Shopify design lead on AI-era workflow: designers are becoming full-stack editors — KlausCodes · 2026-10-26
- Drex for Search hits Nace API console, saving 397k tokens and 56.8% latency per query — testingcatalog · 2026-10-26
- Nace AI launches Drex for Search, cutting agent steps 62% and tokens 56% — testingcatalog · 2026-10-26
- Ultrametric open-sources Open Startup Repo to let AI agents run startup operations — garrytan · 2026-10-26
- MCP fault injection study: agent task scores drop 60% under realistic tool failures, scale doesn't help — dair_ai · 2026-10-26
- General agents burn ~140M tokens/month on LinkedIn outreach; scripts do it 60x cheaper — ChrisHarpon2 · 2026-10-26