IFEval#5 of 28
prompt_level_strict_acc
View run →88.9%±1.4%
Evaluated across 13 benchmarks. Ranks in the top 3 on 1 of 13. Strongest showing on IFEval (88.9% prompt_level_strict_acc, #5 of 28). Weakest on MBPP(Instruct) (0.0% pass@1, #10 of 24).
| Benchmark | Metric | Score | Rank | Actions |
|---|---|---|---|---|
| IFEval | prompt_level_strict_acc | 88.9%±1.4% | #5 of 28 | View run → |
| MMLU | acc | 84.5%±0.3% | #2 of 28 | View run → |
| EQ-Bench | eqbench | 82.0±1.6 | #5 of 28 | View run → |
| MGSM | exact_match | 69.4%±0.7% | #9 of 28 | View run → |
| GSM8K | exact_match | 69.1%±1.3% | #19 of 28 | View run → |
| LongBench | score | 36.6%±0.4% | #5 of 10 | View run → |
| BBH | exact_match | 31.2%±0.5% | #13 of 28 | View run → |
| GPQA Main | acc | 28.8%±2.1% | #14 of 28 | View run → |
| GPQA Diamond | acc | 28.8%±3.2% | #16 of 28 | View run → |
| MBPP | pass@1 | 26.8%±2.0% | #16 of 28 | View run → |
| MMLU-Pro | exact_match | 26.2%±0.3% | #25 of 28 | View run → |
| GPQA Extended | acc | 25.5%±1.9% | #22 of 28 | View run → |
| MBPP(Instruct) | pass@1 | 0.0%±0.0% | #10 of 24 | View run → |
Citation
FrozeBench. "Qwen/Qwen3.6-27B." https://frozebench.com/models/qwen-qwen3-6-27b. Retrieved 2026-06-04.
BibTeX
@misc{frozebench_Qwen_Qwen3_6_27B,
title = {Qwen/Qwen3.6-27B},
howpublished = {\url{https://frozebench.com/models/qwen-qwen3-6-27b}},
year = {2026},
note = {FrozeBench. Retrieved 2026-06-04.}
}URL
https://frozebench.com/models/qwen-qwen3-6-27b