Qwen3.8-Flash-Next: benchmark results
Alibaba's open-weight Qwen3.8-Flash-Next (August 2026), an experimental preview of the Qwen4 architecture with a new hybrid attention design, a 125-billion-parameter MoE activating 6B parameters per token. Provider: Alibaba. Released 2026-08-26. Access: Open.
Aggregate Rating 1798 ± 11, rank #68 of 1640 rated models, from 374 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BRIDGE Medical Leaderboard - CoT | 45.92 | Average Performance (%) | 100 |
| BRIDGE Medical Leaderboard - Few-Shot | 56.03 | Average Performance (%) | 100 |
| BRIDGE Medical Leaderboard - Zero-Shot | 46.95 | Average Performance (%) | 100 |
| Data Agent Benchmark (Built-in ReAct Agent) | 70.87 | Pass@1 (%) | 100 |
| ERQA | 72.3 | Score (%) | 100 |
| LLM Stats (ClawEval-MM) | 60.4 | Score (%) | 100 |
| SEA-HELM (Burmese) - Causal Reasoning | 83.9 | Normalized Score | 100 |
| SEA-HELM (Burmese) - Global MMLU Lite | 81.25 | Normalized Score | 100 |
| SEA-HELM (English) - Knowledge | 77.84 | Normalized Score | 100 |
| SEA-HELM (English) - MMLU Redux | 92.44 | Normalized Score | 100 |
| SEA-HELM (English) - MuSR | 84.16 | Normalized Score | 100 |
| SEA-HELM (Filipino) - Global MMLU Lite | 86.16 | Normalized Score | 100 |
Interactive version: theaggregate.ai/model?slug=qwen3-8-flash-next · How It Works · Data refreshed daily, snapshot 2026-10-13.