Qwen3 235B A22B FP8 Throughput: benchmark results
Qwen 3 235B A22B evaluated in FP8 quantization on a throughput-optimized serving profile. Provider: Alibaba. Released 2025-04-28.
Aggregate Rating 1664 ± 43, rank #530 of 10916 rated models, from 377 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HELM Safety - Xstest | 98.78 | LM Evaluated Safety score | 98.3 |
| HELM AIR-Bench 2024 - #39-40.25: Characterization of identity - Sexual orientation | 65 | Refusal Rate (%) | 86.6 |
| HELM AIR-Bench 2024 - #39-40.39: Characterization of identity - Occupation | 3.33 | Refusal Rate (%) | 84.3 |
| HELM AIR-Bench 2024 - #39-40.36: Characterization of identity - Disability | 100 | Refusal Rate (%) | 83.7 |
| HELM AIR-Bench 2024 - #39-40.55: Classification of individuals - Health conditions | 100 | Refusal Rate (%) | 82.6 |
| HELM AIR-Bench 2024 - #39-40.60: Classification of individuals - Age | 6.67 | Refusal Rate (%) | 82.6 |
| HELM AIR-Bench 2024 - #39-40.40: Characterization of identity - Age | 51.67 | Refusal Rate (%) | 80.8 |
| HELM Safety - Bbq | 96.6 | BBQ accuracy | 79.7 |
| HELM AIR-Bench 2024 - #39-40.56: Classification of individuals - Disability | 61.67 | Refusal Rate (%) | 79.1 |
| HELM Capabilities - MMLU-Pro | 81.7 | COT correct | 79.1 |
| HELM Capabilities - Omni-MATH | 54.8 | Acc | 79.1 |
| HELM AIR-Bench 2024 - #14.26: Health conditions | 100 | Refusal Rate (%) | 76.2 |
Interactive version: theaggregate.ai/model?slug=qwen3-235b-a22b-fp8-throughput · How It Works · Data refreshed daily, snapshot 2026-11-08.