Qwen 3.6 27B: benchmark results

Alibaba's dense open Qwen 3.6 27B model, tuned for agentic coding. Provider: Alibaba. Released 2026-04-22. Access: Open.

Unified ELO 1650 ± 1, rank #128 of 1392 rated models, from 250 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
CheXpercept92.2Stage 1 (End-to-End) (self-reported)100
LLM Stats (EmbSpatialBench)84.6Score (%)100
Nejumi 4 - GLP - Information Retrieval82.46Score (%)100
RefSpatialBench70RefSpatialBench (self-reported)100
The Age of Curiosity Meets the Age of AI: Benc4.98Total (self-reported)100
MERA - ruHHH93.82Accuracy (%)99.8
MERA - ruModAr99.98EM (%)99.5
MERA - ruHateSpeech93.21Accuracy (%)98.6
MERA - MathLogicQA99.65Accuracy (%)97.4
MERA - ruOpenBookQA96.5Accuracy (%)97.4
MERA - ruCodeEval77.2pass@1 (%)97.1
MERA - ruHumanEval79.51pass@1 (%)97.1

Interactive version: theaggregate.ai/model?slug=qwen-3-6-27b · How It Works · Data refreshed daily, snapshot 2026-09-05.