Qwen2.5-14B-Instruct Q8.0 local: benchmark results
Provider: Alibaba.
Aggregate Rating 1510 ± 35, rank #2201 of 10916 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PyraMathBench - Equation Solving | 98.6 | Score (0-100) on the equation solving subtask (1,571 items, | 80 |
| PyraMathBench - Formula Application | 79.4 | Score (0-100) on the formula application subtask (246 items) | 80 |
| PyraMathBench - Math Knowledge | 83.5 | Score (0-100) on the math knowledge subtask (58 items: const | 80 |
| PyraMathBench - Number Conversion | 80.9 | Score (0-100) on the number conversion subtask (3,444 items: | 80 |
| PyraMathBench - Sorting | 96 | Score (0-100) on the sorting subtask (582 items: order numbe | 80 |
| PyraMathBench - Math Word Problems | 91.1 | Score (0-100) on the math word problem subtask (5,476 word p | 70 |
| PyraMathBench - Question Abstraction | 64.5 | Score (0-100) on the question abstraction subtask (8,883 ite | 60 |
| BenchTable - Tech | 57.5 | Weighted Score (%) | 53.6 |
| PyraMathBench - Arithmetic | 90.4 | Score (0-100) on the arithmetic subtask (3,532 items), score | 50 |
| PyraMathBench - Task Decomposition | 62.7 | Score (0-100) on the task decomposition subtask (4,812 items | 40 |
| PyraMathBench - Unit Conversion | 36.6 | Score (0-100) on the unit conversion subtask (1,093 items), | 40 |
| BenchTable - Reasoning | 25.9 | Weighted Score (%) | 33.4 |
Interactive version: theaggregate.ai/model?slug=qwen2-5-14b-instruct-q8-0-local · How It Works · Data refreshed daily, snapshot 2026-11-08.