Qwen3.8 2.4T A95B (xHigh): benchmark results

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

Aggregate Rating 1807 ± 22, rank #132 of 2245 rated models, from 76 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Nejumi 4 - JTruthfulQA77.62Score (%)99.4
Nejumi 4 - jaster (2-shot) - NIILC62.84Character F1 (x100)99.4
Nejumi 4 - jaster (0-shot) - JaMP83Exact match (%)98.7
Nejumi 4 - Toxicity - Prohibited Acts98.44Criteria met (%)96.8
Nejumi 4 - jaster (0-shot) - JCommonsenseQA100Exact match (%)96.1
Nejumi 4 - jaster (2-shot) - JCoLA (out-of-domain)90Exact match (%)95.5
Nejumi 4 - jaster (0-shot) - AIO93.83Character F1 (x100)93.5
Nejumi 4 - ARC-AGI-282Accuracy (%)93.2
Nejumi 4 - jaster (0-shot) - NIILC59.38Character F1 (x100)92.9
Nejumi 4 - ARC-AGI-198Accuracy (%)92.2
Nejumi 4 - jaster (0-shot) - JCoLA (out-of-domain)90Exact match (%)92.2
SecureBio BioTIER Permit99.9Benign prompts answered (%)90.8

Interactive version: theaggregate.ai/model?slug=qwen3-8-2-4t-a95b-xhigh · How It Works · Data refreshed daily, snapshot 2026-11-16.