Skip to content
aiqbench

Mistral · model passport

Mistral: Devstral 2 2512

devstral-2512
  • Open weights
  • 125.0B params
  • 262,144 context
  • Released 2025-12-01(from model name)
1/27axes covered
Best percentile
34.7LiveBench
Cohort standing
46.2median 53.9

Thin coverage — read with caution

This model appears on only 1 of 27 benchmark axes considered. The overall standing has been shrunk toward the neutral 50 to reflect the small sample, and no weaknesses have been claimed — a low percentile on 2 axes is a coverage artifact, not a measured weakness.

What the data says

Benchmarked on 1 of 27 tracked axes. Every figure below is the model's own published result on that board.

On only 1 board(s), a ranked list of strengths would be false authority — the per-axis figures are shown below instead, without a verdict.

  • LiveBench34.7 pct46.0%Verify →
  • OverallNot benchmarked
  • 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
  • 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
  • CodingNot benchmarked
  • Instruction followingNot benchmarked
  • Hard promptsNot 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/Devstral-2-123B-Instruct-2512
Parameters125.0B
ArchitectureMinistral3ForCausalLM

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "mistralai/Devstral-2-123B-Instruct-2512"
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/devstral-2512
Context length262,144 tokens
Max output209,715 tokens
Acceptstext, file
Input price$0.40 per 1M tokens
Cached input price$0.04 per 1M tokens
Output price$2 per 1M tokens

API parameters this endpoint supports

Frequency penaltyMax tokensPresence penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-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/devstral-2512","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.

  • devstral-2512 stands at 46.2 (raw mean 34.7) — measured on only 1 of 27 axes, so the standing is shrunk toward the neutral 50.

    standingtemplateVerify →

  • devstral-2512 stands at 46.2 versus a cohort median of 53.9 across 125 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 →