NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/StarCoder 2 15B

StarCoder 2 15B

by Unknown · Released Jan 2024

Open Source
30.5
avg score
Rank #245
Compare
Better than 21% of all models
Context
N/A
Input $/1M
n/a
Output $/1M
n/a
Type
text
License
Open Source
Benchmarks
10 tested
Data as of
About

Tested on 10 benchmarks · BenchGecko score 30.5. Top scores: GSM8K (57.7%), MMLU (52.1%), ARC AI2 (29.6%).

Capabilities
reasoning
2.9
#218 globally
math
31.8
#179 globally
knowledge
25.7
#251 globally
general
20.4
#161 globally
language
27.8
#148 globally
Benchmark Scores
Compare All
Tested on 10 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.

2.9·
mathCompare math →
GSM8K

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

57.7·
MATH Level 5

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

6.0·
knowledgeCompare knowledge →
MMLU

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

52.1·
ARC AI2

AI2 Reasoning Challenge. Grade-school science questions requiring multi-step reasoning. Easy and Challenge sets test different difficulty levels.

29.6·
Winogrande

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

28.6·
Quick compare:Meta logovs Llama 3 70B InstructAnthropic logovs Claude 3 SonnetMeta logovs Meta Llama 3 8B Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Similar Models
Meta logo
Llama 3 70B Instruct
Meta
30.6$0.51/1M
Anthropic logo
Claude 3 Sonnet
Anthropic
30.3n/a
Meta logo
Meta Llama 3 8B Instruct
Meta
30.7n/a
Links
Info
UnknownPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Unknown
Source Code
GitHubHugging Face
BenchGecko API
starcoder-2-15b
Specifications
  • Typetext
  • ContextN/A
  • ReleasedJan 2024
  • LicenseOpen Source
  • Statusbenchmark-only
Available On
Unknownn/a
Categories
reasoningmathknowledgegenerallanguage
Learn More
transformeropen weightstokens
Share & Export
Tweet
Related Models
Meta logoLlama 3 70B Instruct
30.6
Anthropic logoClaude 3 Sonnet
30.3
Meta logoMeta Llama 3 8B Instruct
30.7
Meta logoLlama 3.1 8B Instruct
30.7
StarCoder 2 15B is an open-source text AI model by Unknown, released in January 2024. It has an average benchmark score of 30.5.

Related Models

Llama 3 70B Instruct · MetaClaude 3 Sonnet · AnthropicMeta Llama 3 8B Instruct · MetaLlama 3.1 8B Instruct · Metavicuna-13b-v1.1 · Unknown

Benchmarks

GSM8KMMLUARC AI2WinograndeIFEval

Related Pages

Unknown · ProviderUnknown · EconomyAll ModelsCompare ModelsPricingDevelopers · API

Key facts · as of 2026-04-09

  • StarCoder 2 15B by Unknown. BenchGecko score 30.5, rank 245 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

StarCoder 2 15B · benchmarks, pricing and providers. BenchGecko, data as of 2026-04-09. https://benchgecko.ai/model/starcoder-2-15b

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