Noometry

Xiaomi, open weights

MiMo-V2-Flash

MiMo-V2-Flash by Xiaomi ranks 138th of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.3. Its strongest category is writing & preference, where it ranks 106th. API pricing starts at $0.14 per million input tokens and $0.28 per million output tokens, with a 262K-token context window.

Last verified

Noometry rank
#138 of 354
Index score
41.3
Evidence
Confirmed 21 results
Provider
Xiaomi
Released
December 16, 2025
Weights
Open weights
Reasoning
Yes
Context window
262K
Max output
66K
Input price
$0.14 / M
Output price
$0.28 / M
Blended price
$0.18 / M
Output speed
Not measured
Value
#34 of 219
Knowledge cutoff
December 2024
Input
text

Category scores

Each category score combines every public result we have in that category.

  1. Coding 36.1
  2. Reasoning 24.9
  3. Math 38.3
  4. Knowledge 39.7
  5. Multilingual 51.0
  6. Instruction Following 73.5
  7. Long Context 43.0
  8. Writing & Preference 59.7
CategoryScoreRankResults
Coding36.1#2113
Reasoning24.9#1572
Math38.3#1391
Knowledge39.7#1311
Multilingual51.0#1131
Instruction Following73.5#1201
Long Context43.0#1101
Writing & Preference59.7#1063

Strengths and weaknesses

Categories where MiMo-V2-Flash places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Writing & Preference59.7+5.9#106 of 312, top 34%
Long Context43.0+2.1#110 of 296, top 38%
Multilingual51.0+3.6#113 of 297, top 39%

Weakest categories

CategoryScorevs medianRank
Coding36.1−2.6#211 of 340, top 63%
Reasoning24.9+1.3#157 of 350, top 45%
Math38.3+1.8#139 of 327, top 43%

Closest competitors

The models ranked just above and below MiMo-V2-Flash. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
Grok 4.1#13441.5——Compare
GLM-4.6#13541.4$112Compare
Grok 4.1 Fast#13641.4$0.28—Compare
GLM-4.6V#13741.3$0.45—Compare
Hunyuan Turbos 20250226#13941.3——Compare
Kimi K2 (Jul 2025)#14041.2$1201Compare
Grok-3 mini#14141.2—10Compare
Claude Opus 4.1#14241.0$30—Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

Coding

BenchmarkScorePositionSettingSourceDate
LMArena WebDev1330#93 of 113, top 83%LMArena2026-10-08
LMArena WebDev1293LMArena2026-10-08
SciCode25.9%#113 of 121, top 94%Epoch AI
LMArena Coding1419LMArena2026-10-08
LMArena Coding1443#95 of 294, top 33%LMArena2026-10-08
ALE-Bench737.95#67 of 105, top 64%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
CritPt0%#122 of 134, top 92%Epoch AI
LMArena Hard Prompts1420#106 of 297, top 36%LMArena2026-10-08
LMArena Hard Prompts1404LMArena2026-10-08

Math

BenchmarkScorePositionSettingSourceDate
LMArena Math1396#131 of 285, top 46%LMArena2026-10-08
LMArena Math1378LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
LMArena Expert1425#102 of 273, top 38%LMArena2026-10-08
LMArena Expert1401LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1392#113 of 297, top 39%LMArena2026-10-08
LMArena Non-English1374LMArena2026-10-08
LMArena Chinese1462#87 of 285, top 31%LMArena2026-10-08
LMArena Chinese1427LMArena2026-10-08
LMArena French1419LMArena2026-10-08
LMArena French1429#93 of 223, top 42%LMArena2026-10-08
LMArena German1395#98 of 231, top 43%LMArena2026-10-08
LMArena German1384LMArena2026-10-08
LMArena Japanese1325#111 of 211, top 53%LMArena2026-10-08
LMArena Korean1358#97 of 213, top 46%LMArena2026-10-08
LMArena Korean1287LMArena2026-10-08
LMArena Russian1387#122 of 283, top 44%LMArena2026-10-08
LMArena Russian1373LMArena2026-10-08
LMArena Spanish1420#91 of 226, top 41%LMArena2026-10-08
LMArena Spanish1394LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1372LMArena2026-10-08
LMArena Instruction Following1392#112 of 298, top 38%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1409#107 of 291, top 37%LMArena2026-10-08
LMArena Longer Query1393LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1395LMArena2026-10-08
LMArena Text1411#109 of 297, top 37%LMArena2026-10-08
LMArena Creative Writing1375#106 of 295, top 36%LMArena2026-10-08
LMArena Creative Writing1348LMArena2026-10-08
LMArena Multi-Turn1378LMArena2026-10-08
LMArena Multi-Turn1404#119 of 295, top 41%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
xiaomi$0.14$0.28$0.00282026-10-10

All Xiaomi API prices → Estimate your cost →

Compare MiMo-V2-Flash

Other Xiaomi models

Frequently asked questions

How good is MiMo-V2-Flash?

MiMo-V2-Flash by Xiaomi ranks 138th of 354 ranked models on the Noometry Index as of October 2026, with a score of 41.3. Its strongest category is writing & preference, where it ranks 106th. API pricing starts at $0.14 per million input tokens and $0.28 per million output tokens, with a 262K-token context window.

How much does MiMo-V2-Flash cost?

MiMo-V2-Flash costs $0.14 per million input tokens and $0.28 per million output tokens on Xiaomi's own API, with cached input at $0.0028.

What is MiMo-V2-Flash's context window?

MiMo-V2-Flash accepts up to 262K tokens of input and can write up to 66K tokens in one response.

Is MiMo-V2-Flash open source?

Yes. MiMo-V2-Flash's weights are downloadable; check the license for commercial terms.

What are MiMo-V2-Flash's strengths and weaknesses?

Relative to other ranked models, MiMo-V2-Flash places best in writing & preference, long context, multilingual and lowest in coding, reasoning, math.

What is MiMo-V2-Flash best at?

Its best category is writing & preference, where it ranks 106th on Noometry.