PipelineScore
← Back to leaderboard
bigcode

StarCoder2 15B

Released 2024-02-28Context 16.384Kstarcoder2-15b
PipelineScore
69.3FEEDER
Ranked #46 of 52 models · 12th percentileAn even spread: no standout, no liability (67 to 72 across all five categories). Best-fit profile: Agentic.

Category breakdown

Score per category, normalized 0–100 against the v1 anchor.

Code
67.5
Reason
71.0
Tool Use
72.2
RAG
72.2
Speed
67.3

Strengths

Tool Use72.2
RAG72.2
Reason71.0

Same model, different rigs

Every submission of StarCoder2 15B on the 0–100 scale. The spread is the point: where it runs changes what you get.

0255075100

Best 72.7 on lab-macbook-pro-m3-pro-18gb · lowest 67.8 on rtx-3080-10gb · spread 4.9 pts across 4 runs. Hover a dot for its rig.

Sample tasks

A taste of what the test pack measures. Full prompts are private and rotated daily.

CodeDifficulty 1code-fib-1

Fibonacci function

Write a Python `fib(n)` returning the nth Fibonacci number, O(n).

ReasonDifficulty 1reason-math-1

Train meeting time

Two trains, opposite directions, given speeds and start times — when do they meet?

RAGDifficulty 2rag-extract-1

Extract metrics to JSON

From the context, extract net sales, operating margin, and free cash flow as a JSON object. Numbers only.

Tool UseDifficulty 2tool-schema-1

OpenAPI param selection

Given an OpenAPI schema with limit/offset/sort, fill JSON for 'next 50, recent first.'

RAGDifficulty 2rag-grounding-1

Refuses to fabricate

Context lacks the answer — does the model fabricate or correctly say it can't?

Compare with