How much does Hunyuan A13B Instruct cost?

Hunyuan A13B Instruct costs $0.14 per million input tokens and $0.57 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.001 per message.

What benchmarks has Hunyuan A13B Instruct been tested on?

Hunyuan A13B Instruct has been evaluated on 6 benchmarks. Top scores: OpenCompass — MMLU-Pro: 73.8, OpenCompass — AIME2025: 65.7, OpenCompass — GPQA-Diamond: 64.1.

Is Hunyuan A13B Instruct open source?

Yes, Hunyuan A13B Instruct is open source.

How does Hunyuan A13B Instruct compare to Baichuan 2-7B?

Hunyuan A13B Instruct has an average score of 29.3 while Baichuan 2-7B scores 29.0. Hunyuan A13B Instruct outperforms Baichuan 2-7B overall. See full comparison →

Home/Models/Hunyuan A13B Instruct

Hunyuan A13B Instruct

Name: Hunyuan A13B Instruct
Price: 0.14 USD
Author: tencent

by tencent · Released Jul 2025

Open Source

29.3

avg score

Rank #183

Compare

Better than 21% of all models

Context

131K tokens (~66 books)

Input $/1M

$0.14

Output $/1M

$0.57

Type

text

License

Open Source

Benchmarks

6 tested

Data updated today

About

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

Tested on 6 benchmarks with 52.3% average. Top scores: OpenCompass — MMLU-Pro (73.8%), OpenCompass — AIME2025 (65.7%), OpenCompass — GPQA-Diamond (64.1%).

Looking for similar performance at lower cost?
Llama 3.3 70B Instruct (free) scores 29.6 (101% as good) at $0.00/1M input · 100% cheaper

Capabilities

coding

43.9

#90 globally

math

65.7

#38 globally

knowledge

48.0

#110 globally

language

60.3

#86 globally

Benchmark Scores

Compare All

Tested on 6 benchmarks · Ranked across 4 categories

Score Distribution (all 233 models)

0255075100

▲ You are here

codingCompare coding →

OpenCompass — LiveCodeBenchV6

OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.

43.9—

mathCompare math →

OpenCompass — AIME2025

OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.

65.7—

knowledgeCompare knowledge →

OpenCompass — MMLU-Pro

OpenCompass MMLU-Pro evaluation. Harder knowledge test with more answer choices.

73.8—

OpenCompass — GPQA-Diamond

OpenCompass evaluation of GPQA Diamond. PhD-level science questions from the hardest subset.

64.1—

OpenCompass — HLE

OpenCompass evaluation of Humanitys Last Exam. Expert-level cross-discipline knowledge test.

6.0—

Quick compare:

vs Baichuan 2-7B

vs Llama 3.3 70B Instruct (free)

vs Mistral 7B Instruct V0.2

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Similar Models

Baichuan 2-7B

Unknown

29.0TBD

Llama 3.3 70B Instruct (free)

Frequently Asked Questions

Hunyuan A13B Instruct is an open-source text AI model by tencent, released in July 2025. It has an average benchmark score of 29.3. Context window: 131K tokens.

Benchmarks

OpenCompass — MMLU-Pro OpenCompass — AIME2025 OpenCompass — GPQA-Diamond OpenCompass — IFEval OpenCompass — LiveCodeBenchV6

tencent · Provider tencent · Economy All Models Compare Models Pricing Developers · API Context Window · Glossary

Hunyuan A13B Instruct

Frequently Asked Questions

Related Models

Benchmarks

Related Pages