PipelineScore
← Back to leaderboard
mistral

Mistral Nemo 12B Instruct

Released 2024-07-18Context 131.072Kmistral-nemo-12b-instruct
PipelineScore
69.1FEEDER
An even spread: no standout, no liability (66 to 69 across all five categories). Best-fit profile: Agentic.

Category breakdown

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

Code
68.4
Reason
69.2
Tool Use
69.3
RAG
66.3
Speed
68.8

Strengths

Tool Use69.3
Reason69.2
Speed68.8

Same model, different rigs

Every submission of Mistral Nemo 12B Instruct on the 0–100 scale. The spread is the point: where it runs changes what you get.

0255075100

Best 71.0 on rtx-4070-12gb · lowest 66.6 on rtx-4080-16gb · spread 4.3 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

Mistral Nemo 12B Instruct vs openai/gpt-oss-20bMistral Nemo 12B Instruct vs DeepSeek R1 671B-A37BMistral Nemo 12B Instruct vs Qwen 3 235B-A22B MoEMistral Nemo 12B Instruct vs DeepSeek V3 671B-A37BMistral Nemo 12B Instruct vs DeepSeek Coder V2 236B
Mistral Nemo 12B Instruct · PipelineScore