# Agent Arena 分析 29 模型 20840 条编码反馈

- 来源：Arena.ai (@arena)
- 发布时间：2026-09-21 23:38
- AIHOT 分数：44
- AIHOT 链接：https://aihot.news/items/cmubfa0v00xseroln356lj2ka
- 原文链接：https://x.com/arena/status/2102060023316898302

## AI 摘要

Arena 分析 Agent Arena: Code 中 29 个模型的 20840 条 trace 后发现，前沿模型获得的正向反馈明显更多，新模型整体反馈更偏正面。

## 正文

What can user praise and complaints tell us about coding agents themselves?

We analyzed 20,840 traces from Agent Arena: Code across 29 models, and found that direct feedback unlocks novel opportunities in tracking the frontier.

Some topline findings:
• Today’s frontier models receive markedly more positive feedback. Overall, newer models across labs tend to show a more positive feedback balance.
• Broken code is still the biggest driver of complaints, sloppy behavior comes second. 69.1% of complaints point to code not working. The next themes are incomplete output (27.1%), weak finish and usability (27.1%), and ignored instructions (20.3%).
• Models share common weaknesses, but differ in how they disappoint. Fable 5.1 attracts fewer “slop” and design complaints than Astra (3.9% versus 5.7% of sampled traces), and fewer complaints about being “flaky” (3.1% versus 5.0%).

Read more by diving into the full article from @DawidGalarowicz below.

### 引用推文

> Arena.ai：https://x.com/i/article/2101066086867492864