Cerebras / Qwen 3 235B A22B Instruct on MMLU

Cerebras hosting Qwen 3 235B A22B Instruct on MMLU. Completed at 4/30/2026, 5:25:52 AM. 88.7%. 3872 ms p50 latency.

Run Summary

This run is partial. Benchscope recorded 100 samples with 97 completed samples. Prompt mode: canonical. Sample scope: random.

Benchmark and Endpoint

Model family: Qwen 3 235B A22B Instruct. Provider: Cerebras. Benchmark: MMLU. Compare this run with other public runs on the same benchmark and model pages.

Benchscope is a JavaScript app. If the interactive interface does not load, enable JavaScript or use the links above for the main public sections.