Skip to content
Model Pareto

MiMo-V2.6-Pro

Xiaomi MiMoOpen weightshuggingface.co ↗
Compare with nearest rivalsCompare with…
Input
$0.435/M tok
Output
$0.87/M tok
Blended
$0.544/M tok · 3:1
Speed
49tok/s
Context
1Mtokens

Open weights (MIT). Writing: no LMArena/EQ-Bench entry or lab-reported writing benchmark as of 2026-09-24, so its Writing entry is fully estimated from its other categories (flagged “Estimated from other categories”).

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
16× B200 180GB
FP8 weights
Throughput
~43,957 tok/s
many requests batched
Price
$0.28–2.49 /M tok
busy → light use
On your own machine
Too large
needs data-center GPUs
Assumptions (5)
  • FP8 weights (1020B params, 42B active per token) + 40% KV-cache headroom ≈ 1428 GB
  • 16× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~43,957 output tok/s aggregate at batch 1480 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~344,250 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#2 of 14 (estimated)~89.6%
  1. #1Claude Opus 596.0%
  2. ~#2MiMo-V2.6-ProEstimated89.6%
  3. #2Claude Sonnet 585.2%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#5 of 19 (estimated)~71.8%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #4Claude Opus 579.2%
  4. ~#5MiMo-V2.6-ProEstimated71.8%
  5. #5Intern-S2-397B68.5%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#2 of 20 (estimated)~92.1%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. ~#2MiMo-V2.6-ProEstimated92.1%
  3. #2Qwen3.8 Flash-Next91.9%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#7 of 15 (estimated)~55.0
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #6Grok 4.756.3
  4. ~#7MiMo-V2.6-ProEstimated55.0
  5. #7Muse Spark 1.354.3
No published score — estimated from related benchmarks

Writing & chat

IFBenchEstimated
~#4 of 126 (estimated)~81.5%
  1. #1MiniMax-M382.9%
  2. #2Qwen3.8 2.4T A95B82.8%
  3. #3Qwen3.8-Omni-Flash81.5%
  4. ~#4MiMo-V2.6-ProEstimated81.5%
  5. #4Nemotron 3 Ultra81.4%
No published score — estimated from related benchmarks
MMMLUEstimated
~#2 of 5 (estimated)~90.9%
  1. #1Gemini 3.1 Pro92.6%
  2. ~#2MiMo-V2.6-ProEstimated90.9%
  3. #2Gemma 4 31B88.4%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#13 of 531461 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #12DeepSeek V4.1 Flash1462
  4. #13MiMo-V2.6-Pro1461
  5. #14GPT-6 AstraFew votes1460
lmarena.ai · 2026-09-25
LMArena Text (Elo)Verified
#10 of 531480 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #10GPT-6 AstraFew votes1480
  4. #10MiMo-V2.6-Pro1480
  5. #13DeepSeek V4.1 Flash1477
lmarena.ai · 2026-09-25
EQ-Bench Creative Writing v3 (Elo)Estimated
~#9 of 26 (estimated)~1966 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #8Grok 4.72007
  4. ~#9MiMo-V2.6-ProEstimated1966
  5. #9Muse Spark 1.31906
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2MiMo-V2.6-ProEstimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
MMMU-ProEstimated
~#4 of 77 (estimated)~85.3%
  1. #1Claude Opus 5.587.7%
  2. #2GPT-6 Astra86.9%
  3. #3Gemini 3.8 Flash85.6%
  4. ~#4MiMo-V2.6-ProEstimated85.3%
  5. #4Claude Opus 584.7%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#4 of 9 (estimated)~84.1%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #3Qwen3.8 Flash-Next84.6%
  4. ~#4MiMo-V2.6-ProEstimated84.1%
  5. #4Qwen3.8-Omni-Flash83.5%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~90.1%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4MiMo-V2.6-ProEstimated90.1%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
ChartographyEstimated
~#7 of 23 (estimated)~32.0%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #6GPT-5.6 Terra34.0%
  4. ~#7MiMo-V2.6-ProEstimated32.0%
  5. #7GPT-5.531.0%
No published score — estimated from related benchmarks

Hard reasoning

GPQA DiamondEstimated
~#2 of 173 (estimated)~95.5%
  1. #1GPT-6 Astra96.1%
  2. ~#2MiMo-V2.6-ProEstimated95.5%
  3. #2Gemini 3.8 Flash95.3%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 25 (estimated)~96.5%
  1. #1Inkling97.1%
  2. ~#2MiMo-V2.6-ProEstimated96.5%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#2 of 116 (estimated)~98.1%
  1. #1Step 3.7 Flash98.5%
  2. ~#2MiMo-V2.6-ProEstimated98.1%
  3. #2Gemini 3.1 Pro95.6%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~56.9%
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. ~#3MiMo-V2.6-ProEstimated56.9%
  4. #3GPT-5.6 Terra50.2%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#5 of 18 (estimated)~90.7%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #4Claude Opus 590.8%
  4. ~#5MiMo-V2.6-ProEstimated90.7%
  5. #5Nex-N2.5-Pro89.7%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#11 of 89 (estimated)~44.5%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #10Gemini 3.8 Flash44.9%
  4. ~#11MiMo-V2.6-ProEstimated44.5%
  5. #11Grok 4.643.3%
No published score — estimated from related benchmarks