Skip to content
aiqbench

Mistral · model passport

Mistral: Mistral Small 3

mistral-small-24b-instruct-2501
  • Open weights
  • Apache 2.0 licence
  • 23.6B params
  • 32,768 context
  • Released 2025-01-01(from model name)
4/27axes covered
Overall · LMArena
1,274#288 of 396
Best percentile
29.8Hard prompts
Cohort standing
37.7median 42.2

What the data says

Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 2.3 percentile points between its best and worst axis — 29.8 pct on Hard prompts versus 27.5 pct on Instruction following.

  • Hard prompts29.8 pct1,285Verify →
  • Coding28.9 pct1,312Verify →
  • Overall27.5 pct1,274Verify →
  • Instruction following27.5 pct1,255Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

Repositorymistralai/Mistral-Small-24B-Instruct-2501
Parameters23.6B
ArchitectureMistralForCausalLM
LicenceApache 2.0

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Mistral-Small-24B-Instruct-2501"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Use it hosted

API model IDmistralai/mistral-small-24b-instruct-2501
Context length32,768 tokens
Max output16,384 tokens
Input price$0.05 per 1M tokens
Output price$0.08 per 1M tokens

API parameters this endpoint supports

Frequency penaltyLogit biasMax tokensMin-pPresence penaltyRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTop-kTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"mistralai/mistral-small-24b-instruct-2501","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • mistral-small-24b-instruct-2501 stands at 37.7 (raw mean 28.4) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • mistral-small-24b-instruct-2501 stands at 37.7 versus a cohort median of 42.2 across 135 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →