Claude · Last 7 days
Claude Opus 4.6
0–100 · higher means more positive community experience, not benchmark performance.
Updated 2026-10-02 14:32 UTC · 2026-09-25 – 2026-10-02 UTCRECENT EXPERIENCE
How the Experience Index is changing
30 days of rolling 7-day scores at each daily snapshot. The vertical scale adapts to the data. Missing or insufficient samples leave gaps; today is still updating.
No trend available
Hacker News · Not enough opinions · 1 scored comments · Read platform reviews →
ONE MODEL, DIFFERENT COMMUNITIES
Across the communities
Scored separately for each platform, with different samples and audiences. Platform scores are not simply averaged; scored counts exclude quota-only comments.
Scores range from 0 to 100. Select a platform for its trend and reviews. Latest opinion time is not crawler health.
What people think
One user noted that Claude Opus 4.6 is notorious for token management issues and typically has very low usage caps when accessed through third-party platforms. One user is satisfied with Opus 4.6 for daily development, finding it still adequate.
About the sample and scores
As of 2026-10-02 14:32:03 UTC, Claude Opus 4.6 in the Claude family has 10 explicitly attributed community comments in the last 7 days; its community score is 56.5/100. Available category scores include General text 66.9/100 (n=6). Scoring method and sources
Community reviews
Selected comments from the last 7 days. The balance of excerpts does not represent the share of positive reviews.
1 selected excerpts
Community reports about limits cannot establish official allowances.
Show original
Claude Opus 4.6 在软件任务上的平均执行时间约为 14.5 小时（95%置信区间在 6 小时到 98 小时之间）
Show original
前一代模型（GLM-5.2和Opus 4.6）几乎无法完成
Comment context
In Chrome V8 vulnerability testing, GLM-5.3 successfully completed 50 end-to-end exploitations out of 410 attempts, while 3Claude Mythos Preview completed 56; the previous generation models (GLM-5.2 and Opus 4.6) were barely able to complete, and Kimi K3 and DeepSeek-V4.1-Flash also performed terribly.
Machine translatedShow original
在Chrome V8漏洞测试中，GLM-5.3在410次尝试里成功完成50次端到端利用，3Claude Mythos Preview则是56次；前一代模型（GLM-5.2和Opus 4.6）几乎无法完成，Kimi K3和DeepSeek-V4.1-Flash也是拉胯到不行。
No selected comments for this filter in the last 7 days.