Qwen·released 2023-09-241 source
Qwen-14B benchmark scores: 6 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 6 benchmarks·best result 79.2 on ARC AI2 (self-reported)·0 of 6 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| ARC AI2 | 79.2accuracy (%) | self-reported· optimizedT1 | 2023-09-24Qwen Technical Report |
| LAMBADA | 71.1accuracy (%) | self-reported· optimizedT1 | 2023-09-24Qwen Technical Report |
| GSM8K | 61.3accuracy (%) | self-reported· optimizedT1 | 2023-09-24Nemotron-4 15B Technical Report |
| PIQA | 59.8accuracy (%) | self-reported· optimizedT1 | 2023-09-24Qwen Technical Report |
| MMLU | 55.07accuracy (%) | self-reported· optimizedT1 | 2023-09-24Nemotron-4 15B Technical Report |
| BBH | 40accuracy (%) | self-reported· optimizedT1 | 2023-09-24Qwen Technical Report |
Claims drawn from cited facts, not live model generation.
Developed by Qwen, this model is a large 14-billion-parameter system released in 2023. That scale puts it on the more expensive side of the efficiency curve, buying extra headroom but demanding more compute than compact alternatives.
3 cited facts
This model is scored on 6 tracked benchmarks. It holds no current top score on any of those benchmarks. These results are self-reported and not yet independently confirmed, so they should be read as claims rather than verified results.
3 cited facts
On average this model trails the benchmark leader by 24.65 points, a wide gap that places it well behind the front-of-pack. It holds the top score on none of the tracked benchmarks, so there is no category leadership yet.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: curated_param_counts, epoch_benchmarks
Qwen-14B is an AI model developed by Qwen, released 2023-09-24. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Qwen-14B has recorded scores on 6 benchmarks, each shown with its evidence status.
Qwen-14B has recorded scores on 6 benchmarks — PIQA, MMLU, ARC AI2, BBH, GSM8K, LAMBADA. The full table above shows each score with its evidence status.
0 of 6 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Qwen-14B has 6 tracked claims: 6 self-reported.