Skip to content
aiqbench

Xiaomi · model passport

Xiaomi: MiMo-V2.6-Pro

mimo-v2-6-pro
  • Open weights
  • MIT licence
  • 1.02T params
  • 1,050,000 context
  • Released 2026-09-21(HF repo created)
8/27axes covered
Overall · LMArena
1,479#24 of 396
Best percentile
97.4Coding
Cohort standing
77.8median 60.4

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

  • 97.4 pct — Coding (1,538)
  • 95.3 pct — Factuality Arena (1,483)
  • 94.9 pct — Hard prompts (1,504)

Uneven: 30.7 percentile points between its best and worst axis — 97.4 pct on Coding versus 66.7 pct on Vision Arena.

  • Coding97.4 pct1,538Verify →
  • Factuality Arena95.3 pct1,483Verify →
  • Hard prompts94.9 pct1,504Verify →
  • Overall94.2 pct1,479Verify →
  • Instruction following92.7 pct1,471Verify →
  • WebDev Arena87.8 pct1,625Verify →
  • Agent Arena76.4 pct0.040Verify →
  • Vision Arena66.7 pct1,246Verify →
  • 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
  • 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

RepositoryXiaomiMiMo/MiMo-V2.6-Pro-RL
Parameters1.02T
ArchitectureMiMoV2ForCausalLM
LicenceMIT

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "XiaomiMiMo/MiMo-V2.6-Pro-RL"
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-v2.6-pro
Context length1,050,000 tokens
Max output131,072 tokens
Acceptstext, image, video, audio
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 reasoningLogit biasMax tokensMin-pPresence penaltyReasoningRepetition penaltyResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-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":"xiaomi/mimo-v2.6-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.

  • mimo-v2.6-pro stands at 77.8 (raw mean 88.2) — measured on 8 of 27 axes.

    standingtemplateVerify →

  • mimo-v2.6-pro stands at 77.8 versus a cohort median of 60.4 across 175 models released within 180 days — above 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 →