Qwen 3 14B (Reasoning): benchmark results
Qwen 3 14B evaluated with reasoning enabled. Provider: Alibaba. Released 2025-04-29. Access: Open.
Aggregate Rating 1539 ± 7, rank #933 of 2170 rated models, from 405 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEA-HELM (Tamil) - Question Answering | 72.39 | Normalized Score | 98.2 |
| Nejumi 4 - jaster (2-shot) - JSICK | 86 | Exact match (%) | 97.2 |
| Medmarks - Med-HALT Reasoning NOTA | 73.78 | Score (%) | 96.6 |
| SEA-HELM (Tamil) - NLU | 82.79 | Normalized Score | 96.5 |
| SEA-HELM (Thai) - Safety | 58.64 | Normalized Score | 93 |
| SEA-HELM (Thai) - Toxicity Detection | 46.54 | Normalized Score | 93 |
| SEA-HELM (English) - LiveCodeBench v6 | 68.05 | Normalized Score | 91.2 |
| Werewolf Accusation Benchmark - Role Separation | 1.51 | Belief separation (wolves minus villagers, -3..+3 scale) | 89.7 |
| SEA-HELM (Filipino) - Sentiment Analysis | 64.6 | Normalized Score | 89.5 |
| Avalon-ToM-Bench - Strategic Signaling | 80.71 | Accuracy (%) | 88.5 |
| Nejumi 4 - BFCL - Non-Live AST | 80.74 | Accuracy (%) | 87.8 |
| SEA-HELM (Indonesian) - Sentiment Analysis | 79.52 | Normalized Score | 84.2 |
Interactive version: theaggregate.ai/model?slug=qwen-3-14b-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.