Skip to content
aiqbench

Xiaomi · model passport

Xiaomi: MiMo-V2.5-Pro

mimo-v2-5-pro
  • Open weights
  • MIT licence
  • 1.02T params
  • 1,050,000 context
  • Released 2026-04-27(HF repo created)
8/27axes covered
Overall · LMArena
1,467#43 of 396
Best percentile
97.8IFBench (Artificial Analysis)
Cohort standing
69.4median 59.3

What the data says

Benchmarked on 8 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 97.8 pct — IFBench (Artificial Analysis) (79.9%)
  • 93.1 pct — Coding (1,522)
  • 91.7 pct — Instruction following (1,468)

Weakest axes

  • 12.7 pct — Agent Arena (-0.077)

Uneven: 85.1 percentile points between its best and worst axis — 97.8 pct on IFBench (Artificial Analysis) versus 12.7 pct on Agent Arena.

  • IFBench (Artificial Analysis)97.8 pct79.9%Verify →
  • Coding93.1 pct1,522Verify →
  • Instruction following91.7 pct1,468Verify →
  • Hard prompts90.7 pct1,495Verify →
  • Overall89.4 pct1,467Verify →
  • Factuality Arena80.2 pct1,465Verify →
  • WebDev Arena58.3 pct1,481Verify →
  • Agent Arena12.7 pct-0.077Verify →
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document 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
  • 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

RepositoryXiaomiMiMo/MiMo-V2.5-Pro
Parameters1.02T
ArchitectureMiMoV2ForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "XiaomiMiMo/MiMo-V2.5-Pro"
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 IDxiaomi/mimo-v2.5-pro
Context length1,050,000 tokens
Max output131,072 tokens
Input price$0.43 per 1M tokens
Cached input price$0.00 per 1M tokens
Output price$0.87 per 1M tokens

API parameters this endpoint supports

Frequency penaltyInclude reasoningLogprobsMax tokensPresence penaltyReasoningRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-kTop logprobsTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"xiaomi/mimo-v2.5-pro","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.

  • The mimo-v2.5-pro model from xiaomi has a shrunk composite of 69.4 and a raw composite of 76.7, with 8 of 27 axes covered and thin coverage marked false.

    standingVerify →

  • Over the past 180 days, mimo-v2.5-pro (xiaomi) has a standing of 69.4 against a cohort median standing of 59.3 across a cohort of 222 models.

    cohortVerify →

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 →