読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニューストピック · Qoder Thinking Effortクイックテイク2 分で読めるDisconfirmAI 編集部

Alibaba Cloud's Qoder Lowers Default Thinking Effort for Several Models, Cutting Costs by Up to 40.5%

Alibaba Cloud's Qoder platform has adjusted the default 'thinking effort' for four AI models from 'Maximum' to 'High', balancing performance and cost based on internal benchmarks.

検証済み 2026-11-18 17:54 GMT+8

Alibaba Cloud's AI coding assistant Qoder recently announced adjustments to the default "Thinking Effort" settings for several large language models, based on evaluations conducted on its proprietary dataset, QoderBench. This parameter controls how much reasoning the model performs before taking action, directly influencing response time and token consumption.

Specifically, the default setting for GLM-5.3, Kimi-K3 (and its replacement Kimi-K3.1-Pro), Kimi-K2.8-Preview, and DeepSeek-Flash has been lowered from "Maximum" to "High". The defaults for GLM-5.3-Flash and DeepSeek-V4-Pro remain at "Maximum". Users can still manually select "Low", "High", or "Maximum" in the model manager.

According to the official Qoder blog, this change stems from testing nearly 200 real-world task cases. The data shows that reducing the thinking effort by one level from "Maximum" to "High" decreases output tokens by 19% to 48% and model call counts by 6.5% to 31.5%. In terms of cost, per-run expenses fell by 6.9% to 40.5%, while relative scores declined by only 5.7% to 16.1%. For instance, switching GLM-5.3 to "High" resulted in a 40.5% cost reduction with only a 6.3% relative drop in score.

Qoder notes that for most everyday development tasks, the marginal benefit of excessive reasoning diminishes, leading instead to increased wait times and Credits usage. These results are vendor-reported and do not specify changes in end-to-end task duration; actual impact may vary depending on the specific workload.

ソース

ログイン / 新規登録
読書リサーチレーダー投資フレームワーク
alibabacloud.comAlibaba Cloud Community↗
トピック

Qoder Thinking Effort

Alibaba Cloud's Qoder platform has adjusted the default "thinking effort" for four AI models—GLM-5.3, Kimi-K3 (now repla…

3 ステップ1 件更新日 2026-11-21 06:41

経緯

  1. 2026-11-18Alibaba Cloud's Qoder team evaluated six models on real tasks using QoderBench, comparing 'Maximum' vs 'High' thinking effort levels.alibabacloud.com ↗
  2. 2026-11-18Based on results showing diminishing returns for many tasks, Qoder changed the default thinking effort for GLM-5.3, Kimi-K3, Kimi-K2.8-Preview, and DeepSeek-Flash from 'Maximum' to 'High'.alibabacloud.com ↗
  3. 2026-11-18Kimi-K3 was subsequently replaced by Kimi-K3.1-Pro in the model list, which inherits the 'High' default setting pending further evaluation.alibabacloud.com ↗

未解決の問題

  • How will user satisfaction metrics evolve as they adapt to the new defaults?
  • Will other agentic coding platforms adopt similar dynamic default adjustments based on task complexity?
トピック全文を読む →
リサーチを続ける →