Qwen Plus (2025-12-01): benchmark results

Provider: Alibaba. Released 2025-12-01. Access: API.

Aggregate Rating 1662 ± 52, rank #546 of 10916 rated models, from 4 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Wolfram LLM Benchmarking Project53.5Correct Functionality (%)69.4
REDAgentBench (Codex)71.81Attack success rate (%; share of valid rollouts judged harmf40
REDAgentBench (Hermes Agent)81.74Attack success rate (%; share of valid rollouts judged harmf0
REDAgentBench (OpenClaw)78.74Attack success rate (%; share of valid rollouts judged harmf0

Interactive version: theaggregate.ai/model?slug=qwen-plus-2025-12-01 · How It Works · Data refreshed daily, snapshot 2026-11-08.