NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Yi 6B

Yi 6B

by Unknown · Released Jan 2024

Open Source
40.4
avg score
Rank #195
Compare
Better than 38% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text
License
Open Source
Benchmarks
14 tested
Data as of
About

Tested on 14 benchmarks · BenchGecko score 40.4. Top scores: HellaSwag (65.9%), MMLU (52.0%), GSM8K (44.9%).

Capabilities
reasoning
19.6
#143 globally
math
18.4
#233 globally
knowledge
35.4
#225 globally
language
30.5
#144 globally
general
35.5
#98 globally
Benchmark Scores
Compare All
Tested on 14 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
BBH

BIG-Bench Hard. 23 challenging tasks from BIG-Bench where prior language models fell below average human performance.

29.6·
MUSR

HuggingFace MuSR (Multi-Step Reasoning). Tests multi-hop reasoning requiring chaining multiple facts together.

9.7·
mathCompare math →
GSM8K

Grade school math word problems. 8,500 problems testing multi-step arithmetic reasoning. A foundational math benchmark.

44.9·
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

5.2·
MATH Level 5

HuggingFace evaluation of MATH Level 5 problems. Competition math requiring advanced reasoning and proof construction.

5.1·
knowledgeCompare knowledge →
HellaSwag

Sentence completion requiring commonsense reasoning about physical and social situations. Tests real-world understanding.

65.9·
MMLU

Massive Multitask Language Understanding. 57 subjects from STEM, humanities, and social sciences. The most widely-cited knowledge benchmark.

52.0·
Winogrande

Commonsense coreference resolution. Tests understanding of pronoun references in ambiguous sentences.

42.6·
Quick compare:Alibaba Qwen logovs Qwen3 30B A3B Instruct 2507Alibaba Qwen logovs Qwen3.5-9BOpenAI logovs GPT-4 Turbo
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Alibaba Qwen logo
Qwen3 30B A3B Instruct 2507
Alibaba Qwen
40.1$0.05/1M
Alibaba Qwen logo
Qwen3.5-9B
Alibaba Qwen
40.0$0.10/1M
OpenAI logo
GPT-4 Turbo
OpenAI
40.9$10.00/1M
Links
Info
UnknownPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Unknown
Source Code
GitHubHugging Face
BenchGecko API
yi-6b
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
Unknownn/a
Categories
reasoningmathknowledgelanguagegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Alibaba Qwen logoQwen3 30B A3B Instruct 2507
40.1
Alibaba Qwen logoQwen3.5-9B
40.0
OpenAI logoGPT-4 Turbo
40.9
Anthropic logoClaude 3.5 Sonnet
39.8
Yi 6B is an open-source text AI model by Unknown, released in January 2024. It has an average benchmark score of 40.4.

Related Models

Qwen3 30B A3B Instruct 2507 · Alibaba QwenQwen3.5-9B · Alibaba QwenGPT-4 Turbo · OpenAIClaude 3.5 Sonnet · AnthropicERNIE 4.5 21B A3B Thinking · baidu

Benchmarks

HellaSwagMMLUGSM8KWinograndeMMLU-PRO

Related Pages

Unknown · ProviderUnknown · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • Yi 6B by Unknown. BenchGecko score 40.4, rank 195 of 312 scored models (normalized average of public benchmark scores).
  • List price n/a input · n/a output per 1M tokens (as of 2026-04-09).

How to cite · data as of 2026-04-09

Yi 6B · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/yi-6b

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP