Xiaomi · Benchmarks

MiMo V2.6 Pro benchmarks

MiMo V2.6 Pro has 3 published scores in this dataset, from a Xiaomi release dated 2026-09-21. It does not yet have scores in enough categories to receive a composite index. Its best placing is on Terminal-Bench, where its 89.9 ranks 2nd of 13 models with a published score.

Deploy hereDeploy MiMo-V2.6-Pro-RL-UNCENSOREDOfficial page

OpenLLM Buddy runs MiMo-V2.6-Pro-RL-UNCENSORED, an uncensored fine-tune of MiMo V2.6 Pro, on 8× H200 (1128 GB VRAM). The scores below are the official base model's; a fine-tune can score slightly differently.

Category profile

Index 0–100: each score relative to the best published score on that test.

ReasoningCodingAgenticKnowledge
Reasoning
—no data
Coding
74.3#11 of 13 · 2 tests
Agentic
—no data
Knowledge
—no data

Model facts

Lab
Xiaomi
Type
OpenLLM Buddy catalog
Released
2026-09-21
Parameters
1.0T total, 42B active (MoE)
Context
1M
License
MIT
Runs on
8× H200

MiMo V2.6 Pro hardware requirements and cost

Even at 4-bit it needs about 704 GB (8× H200 (1,128 GB)), well beyond a home workstation, so most people run it on rented multi-GPU servers. Full BF16 precision needs about 2.3 TB (Multiple nodes (over 1.1 TB)).

Estimated GPU memory for MiMo V2.6 Pro
PrecisionWeightsWith headroomSmallest setup
BF16 (full precision)2.0 TB2.3 TBMultiple nodes (over 1.1 TB)
FP8 / 8-bit1.0 TB1.2 TBMultiple nodes (over 1.1 TB)
4-bit (GGUF Q4_K_M)612 GB704 GB8× H200 (1,128 GB)

Estimate: parameters × bytes per parameter, plus 15% for the KV cache and runtime at modest context lengths. Long contexts and large batches need more.

On OpenLLM Buddy: MiMo-V2.6-Pro-RL-UNCENSORED runs on 8× H200, with an OpenAI-compatible API and no per-token fees. Prices start at $559 USD for 11 hours.

  • 11 hours: $559 USD
  • 24 hours: $1220 USD
  • 1 week: $8537 USD
  • 1 month: $34145 USD
Deploy MiMo V2.6 Pro

Lighter or stronger open models

Open models ranked just above and below on the composite index, with their 4-bit memory needs.

MiMo V2.6 Pro speed and pricing

Measured figures link to their source; estimates are labelled.

API output speed
47 tok/sArtificial Analysis median · Artificial Analysis
Time to first token
3.80 sOpenRouter model page provider stats
API price per 1M tokens
$0.435 in · $0.870 outlab's own endpoint on OpenRouter · OpenRouter endpoints API
OpenLLM Buddy GPU rental
from $50.81 per hourflat rate, no per-token fees
Compare speed and price across all models

Score by test

Rank is among every model with a published score on that test.

Terminal-Bench89.9%Terminal Bench 2.1#2 of 13 · 0.7 behind DeepSeek V4.1 FlashTerminal-Bench 4.034.9%Terminal Bench 4.0#13 of 16 · 35.7 behind Claude Sonnet 5.5LMArena Text Elo1480LMArena text overall, 'MiMo-V2.6-Pro', ±9, as of 2026-10-27#8 of 21 · 40 behind Gemini 4 Argon

Nearby in the composite ranking

Models with the closest composite index.

  1. 1Claude Opus 5.598.4
  2. 2Kimi K3.1 Pro94.4
  3. 3Claude Sonnet 5.591.9
  4. 4GPT-6 Astra91.4
  5. 5Claude Fable 5.191.2
  6. 6DeepSeek V4 Pro91.0
  7. 7Kimi K390.6

Head-to-head comparisons

Side-by-side pages built from the tests both models report.

Sources

ModelTestScoreSettingSource
MiMo V2.6 ProTerminal-Bench89.9Terminal Bench 2.1MiMo-V2.6-Pro-RL model card (Hugging Face)
MiMo V2.6 ProTerminal-Bench 4.034.9Terminal Bench 4.0MiMo-V2.6-Pro-RL model card (Hugging Face)
MiMo V2.6 ProLMArena Text Elo1480LMArena text overall, 'MiMo-V2.6-Pro', ±9, as of 2026-10-27Arena (LMArena) text leaderboard

Scores are published results from model cards, lab reports, and public leaderboards, each linked to its source. Settings such as thinking mode or test version differ between sources and are shown next to each score. OpenLLM Buddy catalog models are uncensored fine-tunes; their scores are those of the official base model. Data collected 2026-10-30. How the index works