Qwen3 14B

ModelOpen sourceActive

by Alibaba (Qwen) · family “qwen3b”

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for... (description from the OpenRouter listing)

in: textout: textReasoningTool useStructured output

Epoch Capabilities Index

138.2 #122 of 268

90% CI 133.4 – 140.1

Listing ↗

Released

29 Apr 2025

Context window

131K tokens

Max output

16K tokens

Input $ / 1M tokens

$0.12

Output $ / 1M tokens

$0.24

Cached input $ / 1M

Unknown

Each benchmark shown separately with its own source

Benchmark results (6)

All benchmarks

Benchmark	Domain	Score	vs best recorded	Setting	Run	Source
LMCA	agents	18.2%	28%	—	—	External ↗
DTBench	reasoning	64.0%	65%	—	—	External ↗
Chess Puzzles	games	4.0% ±2.0	6%	—	30 Aug 2026	Eval log ↗
Fiction.LiveBench	long-context	62.5%	64%	—	—	External ↗
OTIS Mock AIME 2024-2025	math	66.4% ±6.2	66%	—	28 Aug 2026	Eval log ↗
GPQA diamond	science	63.8% ±2.9	67%	—	28 Aug 2026	Eval log ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

13 observations (OpenRouter listing + Internet Archive snapshots). History accumulates with every ingest run; a single point means no change has been observed yet.