GSM8K#14 of 28
exact_match
View run →79.5%±1.1%
Evaluated across 13 benchmarks. Ranks in the top 3 on 0 of 13. Strongest showing on GSM8K (79.5% exact_match, #14 of 28). Weakest on MBPP(Instruct) (0.0% pass@1, #18 of 24).
| Benchmark | Metric | Score | Rank | Actions |
|---|---|---|---|---|
| GSM8K | exact_match | 79.5%±1.1% | #14 of 28 | View run → |
| EQ-Bench | eqbench | 79.0±1.9 | #10 of 28 | View run → |
| IFEval | prompt_level_strict_acc | 77.6%±1.8% | #18 of 28 | View run → |
| MGSM | exact_match | 74.4%±0.7% | #7 of 28 | View run → |
| MMLU-Pro | exact_match | 63.6%±0.4% | #12 of 28 | View run → |
| MBPP | pass@1 | 55.2%±2.2% | #12 of 28 | View run → |
| BBH | exact_match | 49.6%±0.5% | #8 of 28 | View run → |
| MMLU | acc | 37.9%±0.4% | #24 of 28 | View run → |
| LongBench | score | 31.9%±0.4% | #9 of 10 | View run → |
| GPQA Diamond | acc | 29.8%±3.3% | #12 of 28 | View run → |
| GPQA Main | acc | 28.3%±2.1% | #15 of 28 | View run → |
| GPQA Extended | acc | 27.7%±1.9% | #14 of 28 | View run → |
| MBPP(Instruct) | pass@1 | 0.0%±0.0% | #18 of 24 | View run → |
Citation
FrozeBench. "Qwen/Qwen3.5-35B-A3B." https://frozebench.com/models/qwen-qwen3-5-35b-a3b. Retrieved 2026-06-04.
BibTeX
@misc{frozebench_Qwen_Qwen3_5_35B_A3B,
title = {Qwen/Qwen3.5-35B-A3B},
howpublished = {\url{https://frozebench.com/models/qwen-qwen3-5-35b-a3b}},
year = {2026},
note = {FrozeBench. Retrieved 2026-06-04.}
}URL
https://frozebench.com/models/qwen-qwen3-5-35b-a3b