Qwen 3.8 2.4T A95B (xHigh): benchmark results

Provider: Alibaba. Released 2026-08-12. Access: Open.

Aggregate Rating 1826 ± 20, rank #94 of 2163 rated models, from 72 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Nejumi 4 - JTruthfulQA77.62Score (%)99.3
Nejumi 4 - jaster (2-shot) - NIILC62.84Character F1 (x100)99.3
Nejumi 4 - jaster (0-shot) - JaMP83Exact match (%)98.6
Nejumi 4 - jaster (2-shot) - JCoLA (out-of-domain)90Exact match (%)98.2
Nejumi 4 - ARC-AGI-282Accuracy (%)96.5
Nejumi 4 - Toxicity - Prohibited Acts98.44Criteria met (%)96.5
Nejumi 4 - jaster (0-shot) - JCommonsenseQA100Exact match (%)96.1
Nejumi 4 - jaster (0-shot) - JCoLA (out-of-domain)90Exact match (%)94.7
Nejumi 4 - jaster (0-shot) - NIILC59.38Character F1 (x100)94.4
Nejumi 4 - HLE (Japanese) - Calibration Error44Calibration error (%)94
Nejumi 4 - ARC-AGI-198Accuracy (%)93.3
Nejumi 4 - jaster (0-shot) - AIO93.83Character F1 (x100)93

Interactive version: theaggregate.ai/model?slug=qwen-3-8-2-4t-a95b-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-19.