Tag
A community member benchmarked three Qwen 3 quantized models (Flash, Swift, 27B) at four thinking effort levels on 14 recent AtCoder problems, finding that higher thinking effort rarely improves results and mainly increases token-capped failures, with Flash IQ3_S emerging as the best speed-accuracy compromise.
Scores update from the ongoing AtCoder heuristics finals, which will continue until July 8, 19:00 JST.