Skip to content
Model Pareto

MiMo-V2.5

Xiaomi MiMoOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.14/M tok
Output
$0.28/M tok
Blended
$0.175/M tok · 3:1
Speed
40tok/s
Context
1Mtokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: MiMo-V2.5. Price = AA median host price.

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
4× B200 180GB
FP8 weights
Throughput
~18,598 tok/s
many requests batched
Price
$0.14–1.27 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~110 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (310B params, 15B active per token) + 40% KV-cache headroom ≈ 434 GB
  • 4× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~18,598 output tok/s aggregate at batch 532 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~283,500 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
~#10 of 14 (estimated)~74.9%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #9Xing4.0-29B-A4B75.0%
  4. ~#10MiMo-V2.5Estimated74.9%
  5. #10Claude Haiku 4.573.3%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#17 of 19 (estimated)~54.1%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #15Gemini 3.5 Flash-Lite54.2%
  4. ~#17MiMo-V2.5Estimated54.1%
  5. #17Muse Glimmer51.2%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#27 of 31 (estimated)~51.2%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #26Nex-N2.5-Pro55.8%
  4. ~#27MiMo-V2.5Estimated51.2%
  5. #27Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#8 of 20 (estimated)~73.7%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #7gpt-oss-20b77.7%
  4. ~#8MiMo-V2.5Estimated73.7%
  5. #8Mistral Small 464.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15MiMo-V2.5Estimated<41.1
No published score — estimated from related benchmarks

Writing & chat

MMMLUEstimated
~#3 of 5 (estimated)~86.7%
  1. #1Gemini 3.1 Pro92.6%
  2. #2Gemma 4 31B88.4%
  3. ~#3MiMo-V2.5Estimated86.7%
  4. #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Verified
#33 of 531411 Elo
  1. #1Claude Opus 5.51501
  2. #2Claude Fable 5.1Few votes1496
  3. #32Muse GlimmerFew votes1418
  4. #33MiMo-V2.51411
  5. #34Mistral Medium 3.51406
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#32 of 531434 Elo
  1. #1Claude Opus 5.51509
  2. #2Claude Fable 5.11501
  3. #31Qwen3.8 27B1437
  4. #32MiMo-V2.51434
  5. #33Mistral Medium 3.51426
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#13 of 26 (estimated)~1807 Elo
  1. #1GPT-6 Astra2173
  2. #2Claude Fable 5.12162
  3. #12Qwen3.8 2.4T A95B1843
  4. ~#13MiMo-V2.5Estimated1807
  5. #13Muse Glimmer1798
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2MiMo-V2.5Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#6 of 9 (estimated)~78.5%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. #5Muse Glimmer78.8%
  4. ~#6MiMo-V2.5Estimated78.5%
  5. #6Inkling78.1%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~84.4%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #4Gemini 3.1 Pro85.3%
  4. ~#5MiMo-V2.5Estimated84.4%
  5. #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#26 of 43 (estimated)~12.8%
  1. #1GPT-6 Astra31.0%
  2. #2Muse Spark 1.326.6%
  3. #24Inkling12.8%
  4. ~#26MiMo-V2.5Estimated12.8%
  5. #26Qwen3.5 397B A17B12.2%
No published score — estimated from related benchmarks
ChartographyEstimated
~#15 of 23 (estimated)~20.2%
  1. #1GPT-6 Astra71.0%
  2. #2Claude Opus 5.566.3%
  3. #14Grok 4.620.5%
  4. ~#15MiMo-V2.5Estimated20.2%
  5. #15Muse Glimmer17.2%
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#5 of 25 (estimated)~92.5%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #4gpt-oss-120b93.4%
  4. ~#5MiMo-V2.5Estimated92.5%
  5. #5Xing4.0-29B-A4B90.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#30 of 75 (estimated)~26.5
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #29Quasar 438B26.7
  4. ~#30MiMo-V2.5Estimated26.5
  5. #30Apodex 1.126.4
No published score — estimated from related benchmarks

Agents

OSWorld-VerifiedEstimated
~#10 of 12 (estimated)~66.3%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #9Nex-N2.5-Mini71.2%
  4. ~#10MiMo-V2.5Estimated66.3%
  5. #10Muse Glimmer65.9%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5MiMo-V2.5Estimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~63.2%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15MiMo-V2.5Estimated63.2%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks