PipelineScore
← Back to leaderboard
alibaba

Qwen 2.5 Coder 7B

Released 2024-11-12Context 131.072Kqwen-2-5-coder-7b
PipelineScore
70.6FEEDER
Ranked #39 of 52 models · 25th percentileAn even spread: no standout, no liability (69 to 75 across all five categories). Best-fit profile: Agentic.

Category breakdown

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

Code
69.3
Reason
70.8
Tool Use
75.0
RAG
68.7
Speed
72.9

Strengths

Tool Use75.0
Speed72.9
Reason70.8

Same model, different rigs

Every submission of Qwen 2.5 Coder 7B on the 0–100 scale. The spread is the point: where it runs changes what you get.

0255075100

Best 75.5 on rtx-3080-10gb · lowest 68.7 on ryzen-7950x-cpu-only · spread 6.8 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