DeepSeek R1 Distill Qwen 14B

DeepSeek · Released Jan 20, 2025
DFO score #366 / 718
12.9 leaderboard score
Speed
– Not reported
Input Price
– Not priced
Output Price
– Not priced
Context
– Not reported

Analysis Summary

DeepSeek R1 Distill Qwen 14B has a low overall intelligence result despite stronger individual results on selected tasks, including a 0.484 GPQA result and 0.376 on a live coding benchmark. Its measured long-context result is particularly limited, and its instruction-following result offers little support for precise client-facing work. These mixed results point to a specialist profile rather than a dependable general model.

It could be tested for bounded reasoning or coding tasks where outputs are verified, but it is not a strong default for long-document analysis, customer-facing content, or agent workflows. The supplied data does not include pricing, speed, context capacity, or tool-use details, so it is difficult to establish a business advantage beyond its task-specific results.

Assessed September 23, 2026

Editorial notes

DeepSeek R1 Distill Qwen 14B shows some mathematical and coding-test ability, but its overall measured capability and long-context result are limited.

The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?

DFO Verdict

DeepSeek R1 Distill Qwen 14B shows some mathematical and coding-test ability, but its overall measured capability and long-context result are limited.

#366 of 718 overall Down 3 this week

Benchmarks

Intelligence Index 7.8 #287 of 443 · Artificial Analysis
Coding Index Not published yet Artificial Analysis
Agentic Index Not published yet Artificial Analysis
Creative Writing Not rated Arena rating
Instruction Following Not rated Arena rating
GPQA Diamond 48.4%
HLE 4.4%
MMLU Pro 74%
MATH 500 94.9%
AIME 66.7%
AIME 2025 55.7%
SciCode 23.9%
LiveCodeBench 37.6%
IFBench 22.1%
LCR 7%

Artificial Analysis data refreshed Oct 23, 2026. Arena ratings from the Oct 20, 2026 text leaderboard, with style control. Bars: magenta = reasoning, ink = coding and agents, cyan = instructions and long context.

Artificial Analysis has not published coding or agentic results for DeepSeek R1 Distill Qwen 14B yet. Until it does, the model sits below tested models on the Coding and AI Agents lists.

How DeepSeek R1 Distill Qwen 14B compares

DeepSeek R1 Distill Qwen 14B ranks #287 of 443 AI models we track for overall intelligence. DeepSeek R1 Distill Qwen 14B is currently free to use via OpenRouter.

Position in the field
DFO score: ahead of 49% of models #364
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
DeepSeek R1 Distill Qwen 14B $0.00 in $0.00 out
Anthropic: Claude Opus 5.5 $4.00 in $20.00 out
Google: Gemini 4 Argon $2.00 in $10.00 out
Anthropic: Claude Fable 5.1 $10.00 in $50.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Frequently asked questions about DeepSeek R1 Distill Qwen 14B

How much does DeepSeek R1 Distill Qwen 14B cost?

DeepSeek R1 Distill Qwen 14B is currently available for free via OpenRouter.

Who created DeepSeek R1 Distill Qwen 14B?

DeepSeek R1 Distill Qwen 14B is developed by DeepSeek and was released on January 20, 2025.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.