mistral

Codestral 22B

Released 2024-05-29Context 32.768Kcodestral-22b

PipelineScore

75.7MAINLINE

Ranked #32 of 52 models · 38th percentileRAG is the headline (78.8); throughput is the soft spot (69.5). Best-fit profile: Coding.

Category breakdown

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

Code

78.0

Reason

76.5

Tool Use

75.5

RAG

78.8

Speed

69.5

RAG78.8

Code78.0

Reason76.5

Every submission of Codestral 22B on the 0–100 scale. The spread is the point: where it runs changes what you get.

0255075100

Best 77.9 on lab-rtx-3090-24gb · lowest 73.4 on ryzen-7950x-rtx-3090 · spread 4.5 pts across 4 runs. Hover a dot for its rig.

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

CodeDifficulty 1code-fib-1

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

ReasonDifficulty 1reason-math-1

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

RAGDifficulty 2rag-extract-1

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

Tool UseDifficulty 2tool-schema-1

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

RAGDifficulty 2rag-grounding-1

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