NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/SmolLM2 135M Instruct

SmolLM2 135M Instruct

by Hugging Face TB · Released Oct 2024

Open Source
7.6
avg score
Rank #307
Compare
Better than 2% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text-generation
License
Open Source
Benchmarks
11 tested
Data as of
About

HuggingFaceTB text generation model. 927K downloads on HuggingFace.

Tested on 11 benchmarks · BenchGecko score 7.6. Top scores: JNLI (55.3%), IFEval (28.8%), JMMLU (24.2%).

Capabilities
reasoning
3.7
#211 globally
math
0.3
#287 globally
knowledge
0.6
#306 globally
language
25.8
#151 globally
general
4.7
#208 globally
Benchmark Scores
Compare All
Tested on 11 benchmarks · Ranked across 5 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
reasoningCompare reasoning →
MUSR

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

3.7·
mathCompare math →
MATH Level 5

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

0.3·
knowledgeCompare knowledge →
MMLU-PRO

HuggingFace MMLU-Pro. Harder version of MMLU with 10 answer choices instead of 4 and more challenging questions.

1.3·
GPQA

HuggingFace evaluation of GPQA (Graduate-Level Google-Proof Q&A). PhD-level science questions that cannot be easily searched.

0.0·
Quick compare:Alibaba logovs Qwen2 0.5B InstructOpenAI logovs Gpt2 Largevs Distilgpt2
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Alibaba logo
Qwen2 0.5B Instruct
Alibaba
7.8n/a
OpenAI logo
Gpt2 Large
OpenAI
7.9n/a
Distilgpt2
DistilBERT
8.3n/a
Links
Info
Hugging Face TBPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Hugging Face TB
Source Code
GitHubHugging Face
BenchGecko API
huggingfacetb-smollm2-135m-instruct
Specifications
  • Typetext-generation
  • ContextN/A
  • ReleasedOct 2024
  • LicenseOpen Source
  • StatusActive
Available On
Hugging Face TBn/a
Categories
reasoningmathknowledgelanguagegeneral
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Alibaba logoQwen2 0.5B Instruct
7.8
OpenAI logoGpt2 Large
7.9
Distilgpt2
8.3
OpenAI logoGpt2 Medium
8.8
SmolLM2 135M Instruct is an open-source text-generation AI model by Hugging Face TB, released in October 2024. It has an average benchmark score of 7.6.

Related Models

Qwen2 0.5B Instruct · AlibabaGpt2 Large · OpenAIDistilgpt2 · DistilBERTGpt2 Medium · OpenAISmolLM2 135M · Hugging Face TB

Benchmarks

JNLIIFEvalJMMLUJCommonsenseQALLM-JP — Overall

Related Pages

Hugging Face TB · ProviderHugging Face TB · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • SmolLM2 135M Instruct by Hugging Face TB. BenchGecko score 7.6, rank 307 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

SmolLM2 135M Instruct · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/huggingfacetb-smollm2-135m-instruct

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