Updated daily at 05:00 UTC

Language

Qwen-14B-Chat

By Alibaba Group, in the Qwen family.

Released: 25 Sep 2023
Status: Legacy
Context: 8.2K
Max output: —
Input per 1M tokens: —
Output per 1M tokens: —
Open weights: Yes
License: tongyi-qianwen
Parameters: 14B
Knowledge cutoff: —
Reasoning: No
Modalities: text → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
Category	Score	Rank	Coverage
Human preference	18.2	Not ranked	1 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
Benchmark	Metric	Value	Provenance	Setting	Evaluated	Source
BIG-Bench Hard (BBH)	Average accuracy	55.0%	Third party	—	—	Yi: Open Foundation Models by 01.AI via Epoch AI
BIG-Bench Hard (BBH)	Average accuracy	49.7%	Third party	—	—	Yi: Open Foundation Models by 01.AI via Epoch AI
MMLU	Accuracy	65.0%	Third party	—	—	Yi: Open Foundation Models by 01.AI via Epoch AI
MMLU	Accuracy	64.0%	Third party	—	—	Yi: Open Foundation Models by 01.AI via Epoch AI

Mathematics

Mathematics results
Benchmark	Metric	Value	Provenance	Setting	Evaluated	Source
GSM8K	Exact match	61.2%	Third party	—	—	Yi: Open Foundation Models by 01.AI via Epoch AI
GSM8K	Exact match	59.5%	Third party	—	—	Yi: Open Foundation Models by 01.AI via Epoch AI

Human preference

Human preference results
Benchmark	Metric	Value	Provenance	Setting	Evaluated	Source
Text Arena (arena.ai)	Arena score (Elo scale)	1139	Independent	—	25 Sep 2026	Arena
Text Arena (arena.ai)	Votes	4964	Independent	—	25 Sep 2026	Arena

Other Qwen versions

Sources

https://huggingface.co/Qwen/Qwen-14B-Chat

Qwen-14B-Chat: benchmarks, price and specs · supermarket.dev