IFEval#3 of 28
prompt_level_strict_acc
View run →89.6%±1.3%
Evaluated across 13 benchmarks. Ranks in the top 3 on 2 of 13. Strongest showing on IFEval (89.6% prompt_level_strict_acc, #3 of 28). Weakest on MBPP(Instruct) (0.0% pass@1, #11 of 24).
| Benchmark | Metric | Score | Rank | Actions |
|---|---|---|---|---|
| IFEval | prompt_level_strict_acc | 89.6%±1.3% | #3 of 28 | View run → |
| EQ-Bench | eqbench | 84.6±1.3 | #3 of 28 | View run → |
| MGSM | exact_match | 67.1%±0.8% | #12 of 28 | View run → |
| MMLU | acc | 37.9%±0.4% | #23 of 28 | View run → |
| LongBench | score | 31.5%±0.4% | #10 of 10 | View run → |
| GPQA Main | acc | 29.9%±2.2% | #10 of 28 | View run → |
| GPQA Extended | acc | 27.8%±1.9% | #13 of 28 | View run → |
| GPQA Diamond | acc | 26.3%±3.1% | #24 of 28 | View run → |
| BBH | exact_match | 24.1%±0.4% | #15 of 28 | View run → |
| MMLU-Pro | exact_match | 7.2%±0.2% | #27 of 28 | View run → |
| MBPP | pass@1 | 3.4%±0.8% | #20 of 28 | View run → |
| GSM8K | exact_match | 1.1%±0.3% | #28 of 28 | View run → |
| MBPP(Instruct) | pass@1 | 0.0%±0.0% | #11 of 24 | View run → |
Citation
FrozeBench. "Qwen/Qwen3.6-35B-A3B." https://frozebench.com/models/qwen-qwen3-6-35b-a3b. Retrieved 2026-06-04.
BibTeX
@misc{frozebench_Qwen_Qwen3_6_35B_A3B,
title = {Qwen/Qwen3.6-35B-A3B},
howpublished = {\url{https://frozebench.com/models/qwen-qwen3-6-35b-a3b}},
year = {2026},
note = {FrozeBench. Retrieved 2026-06-04.}
}URL
https://frozebench.com/models/qwen-qwen3-6-35b-a3b