MiMo-V2.5
- Input
- $0.14/M tok
- Output
- $0.28/M tok
- Blended
- $0.175/M tok · 3:1
- Speed
- 36tok/s
- Context
- 1Mtokens
- Cost per task
- ~$0.12/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: MiMo-V2.5. Price = AA median host price.
Rankings
Coding
Verified#86 / 137rank by quality37.9±8.1quality / 1002/7 benchmarks measuredWriting & chat
Verified#57 / 162rank by quality58.7±4.1quality / 1003/5 benchmarks measuredVision
Verified#46 / 98rank by quality57.0±8.2quality / 1001/6 benchmarks measuredPrice frontierHard reasoning
Verified#78 / 218rank by quality53.8±3.7quality / 1003/4 benchmarks measuredPrice frontierAgents
Verified#80 / 187rank by quality37.2±4.3quality / 1004/7 benchmarks measured
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
~#14 of 21 (estimated)~73.2%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #13Claude Haiku 4.573.3%
- ~#14MiMo-V2.5Estimated73.2%
- #14Nemotron 3.5 Super VL71.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#20 of 24 (estimated)~52.7%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #18Gemini 3.5 Flash-Lite54.2%
- ~#20MiMo-V2.5Estimated52.7%
- #20Nemotron 3.5 Super VL51.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~47.9%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38MiMo-V2.5Estimated47.9%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#15 of 28 (estimated)~67.1%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #14Maple-Preview75.1%
- ~#15MiMo-V2.5Estimated67.1%
- #15Mistral Small 464.0%
No published score — estimated from related benchmarks
SciCodeVerified
#66 of 11843.9%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #65Ling-3.0-flash-VL44.2%
- #66MiMo-V2.543.9%
- #66Step 3.7 Flash43.9%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#24 of 26 (estimated)~32.0
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #23Gemini 3.8 Flash33.3
- ~#24MiMo-V2.5Estimated32.0
- #24GPT-6 Luna31.1
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#43 of 13967.1%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #42Step 3.7 Flash67.3%
- #43MiMo-V2.567.1%
- #44KAT Coder Pro V266.7%
artificialanalysis.ai · 2026-09-24
LMArena Text, Non-English (Elo)Verified
#36 of 561411 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #35Muse GlimmerFew votes1418
- #36MiMo-V2.51411
- #37Mistral Medium 3.51406
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#35 of 561434 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #34Qwen3.8 27B1437
- #35MiMo-V2.51434
- #36Mistral Medium 3.51426
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#15 of 26 (estimated)~1782 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #14Claude Sonnet 51794
- ~#15MiMo-V2.5Estimated1782
- #15Gemini 3.8 Flash1748
No published score — estimated from related benchmarks
Vision
MMMU-ProVerified
#35 of 8775.4%
- #1Claude Opus 5.587.7%
- #2GPT-6 Astra86.9%
- #34Ternary Bonsai 2 27B75.5%
- #35MiMo-V2.575.4%
- #36Step 3.7 Flash75.3%
artificialanalysis.ai · 2026-09-24
CharXiv ReasoningEstimated
~#10 of 12 (estimated)~77.9%
- #1Gemini 3.8 Flash86.2%
- #2Kimi K384.8%
- #9Inkling78.1%
- ~#10MiMo-V2.5Estimated77.9%
- #10Claude Sonnet 577.0%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#5 of 8 (estimated)~83.6%
- #1MiniMax-M391.6%
- #2Kimi K391.1%
- #4Gemini 3.1 Pro85.3%
- ~#5MiMo-V2.5Estimated83.6%
- #5Claude Haiku 4.579.6%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#31 of 48 (estimated)~12.5%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #29Inkling12.8%
- ~#31MiMo-V2.5Estimated12.5%
- #31Qwen3.5 397B A17B12.2%
No published score — estimated from related benchmarks
ChartographyEstimated
~#17 of 25 (estimated)~18.4%
- #1Claude Fable 5.273.4%
- #2GPT-6 Astra71.0%
- #16Grok 4.620.5%
- ~#17MiMo-V2.5Estimated18.4%
- #17Muse Glimmer17.2%
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#61 of 19284.9%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #60Ripple-65B Preview85.2%
- #61MiMo-V2.584.9%
- #61Nanbeige4.1-3B84.9%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#64 of 19827.2%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #63GPT-5.4 mini28.1%
- #64MiMo-V2.527.2%
- #65Solar Mini 425.8%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#11 of 34 (estimated)~90.5%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #10GLM-5.3-MXFP491.3%
- ~#11MiMo-V2.5Estimated90.5%
- #11Xing4.0-29B-A4B90.0%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#12 of 11990.6%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #11Ring-2.6-1T92.4%
- #12MiMo-V2.590.6%
- #13Kimi K2.7 Code90.1%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~65.6%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12MiMo-V2.5Estimated65.6%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#19 of 22 (estimated)~63.9%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19MiMo-V2.5Estimated63.9%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#44 of 91986 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #43GPT-5.4 mini1000
- #44MiMo-V2.5986
- #45Gemini 3.5 Flash-Lite970
artificialanalysis.ai · 2026-09-24