Qwen2-Audio-7B: benchmark results
Provider: Alibaba. Access: Open.
Aggregate Rating 1135 ± 37, rank #2173 of 2257 rated models, from 16 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FinBen (Financial LLM) | 16.01 | Average Score | 73.7 |
| HalluAudio - Environmental Sound | 67.36 | Average classification accuracy (%) over the seven environme | 50 |
| Kimi-ASR Internal Testset - Subset 1 | 2.31 | WER (%), lower is better, Moonshot's internal ASR test set s | 50 |
| Kimi-ASR Internal Testset - Subset 2 | 3.24 | WER (%), lower is better, Moonshot's internal ASR test set s | 50 |
| TraceAV-Bench (Audio Only) | 30.74 | Accuracy (%), macro-average of the 12 general sub-tasks, fou | 50 |
| FinBen - FinNum | 0 | Normalized Score | 30 |
| HalluAudio - Speech | 28.72 | Average classification accuracy (%) over the ten speech task | 30 |
| MERA Multi - ruSLUn | 0.1 | Score (%) | 22.7 |
| FinBen - MultiFin | 0 | Normalized Score | 15.8 |
| FinBen - QA | 0 | Normalized Score | 15.8 |
| FinBen - FNS | 0 | Normalized Score | 15 |
| MERA Multi - ruEnvAQA | 14.3 | Score (%) | 9.1 |
Interactive version: theaggregate.ai/model?slug=qwen2-audio-7b · How It Works · Data refreshed daily, snapshot 2026-11-17.