Qwen3.8-Flash-Next (xHigh): benchmark results
Provider: Alibaba. Released 2026-08-26. Access: Open.
Aggregate Rating 1774 ± 22, rank #205 of 2245 rated models, from 73 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Nejumi 4 - jaster (0-shot) - JCoLA (out-of-domain) | 92 | Exact match (%) | 96.8 |
| Nejumi 4 - HalluLens | 100 | Hallucination resistance (%) | 94.5 |
| Nejumi 4 - jaster (0-shot) - JBLiMP | 97 | Exact match (%) | 93.2 |
| Nejumi 4 - jaster (2-shot) - MGSM | 94 | Exact match (%) | 92.9 |
| Nejumi 4 - jaster (0-shot) - CommonsenseMoralJA | 97 | Exact match (%) | 91.6 |
| Nejumi 4 - jaster (0-shot) - JSICK | 84 | Exact match (%) | 91.6 |
| Nejumi 4 - jaster (2-shot) - JSeM | 82 | Exact match (%) | 90.3 |
| Nejumi 4 - jaster (2-shot) - JaMP | 80 | Exact match (%) | 89 |
| Nejumi 4 - jaster (0-shot) - MMLU-ProX (Japanese) | 90 | Exact match (%) | 88.3 |
| Nejumi 4 - jaster (2-shot) - JCoLA (out-of-domain) | 88 | Exact match (%) | 87.3 |
| Nejumi 4 - M-IFEval (Japanese) | 89.38 | Score (%) | 85.7 |
| Nejumi 4 - HLE (Japanese) - Accuracy | 40.21 | Accuracy (%) | 84.7 |
Interactive version: theaggregate.ai/model?slug=qwen3-8-flash-next-xhigh · How It Works · Data refreshed daily, snapshot 2026-11-16.