Noometry

Moonshot AI, open weights

Kimi K2.5 Instant

Kimi K2.5 Instant by Moonshot AI ranks 89th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.6. Its strongest category is multimodal, where it ranks 50th.

Last verified

Noometry rank
#89 of 354
Index score
43.6
Evidence
Confirmed 18 results
Provider
Moonshot AI
Released
Unknown
Weights
Open weights
Reasoning
Unknown
Context window
—
Max output
—
Input price
Not listed
Output price
Not listed
Blended price
Not listed
Output speed
Not measured
Value
Not ranked
Knowledge cutoff
Unknown

Category scores

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

  1. Coding 42.6
  2. Reasoning 29.7
  3. Math 39.4
  4. Knowledge 40.2
  5. Multimodal 40.2
  6. Multilingual 52.0
  7. Instruction Following 75.3
  8. Long Context 43.9
  9. Writing & Preference 60.6
CategoryScoreRankResults
Coding42.6#972
Reasoning29.7#901
Math39.4#1051
Knowledge40.2#1231
Multimodal40.2#501
Multilingual52.0#941
Instruction Following75.3#651
Long Context43.9#831
Writing & Preference60.6#953

Strengths and weaknesses

Categories where Kimi K2.5 Instant places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Instruction Following75.3+4.1#65 of 305, top 22%
Reasoning29.7+6.1#90 of 350, top 26%
Long Context43.9+2.9#83 of 296, top 29%

Weakest categories

CategoryScorevs medianRank
Knowledge40.2+2.9#123 of 314, top 40%
Multimodal40.2+1.6#50 of 128, top 40%
Math39.4+2.8#105 of 327, top 33%

Closest competitors

The models ranked just above and below Kimi K2.5 Instant. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
MiniMax-M3#8543.8$0.52—Compare
Grok 4.3#8643.8$1.56—Compare
Qwen3 Max#8743.7$2.4048Compare
MiMo-V2-Omni#8843.6$0.18—Compare
Gemma 4 31B IT#9043.5$0.153Compare
Qwen3 235B-A22B#9143.5$1.2285Compare
Gemma 4 26B A4B IT#9243.5$0.11—Compare
MiMo-V2.5#9343.4$0.18—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 WebDev1404#70 of 113, top 62%LMArena2026-10-08
LMArena Coding1484#41 of 294, top 14%LMArena2026-10-08

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1443#77 of 297, top 26%LMArena2026-10-08

Math

BenchmarkScorePositionSettingSourceDate
LMArena Math1442#68 of 285, top 24%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
LMArena Expert1440#84 of 273, top 31%LMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1254#51 of 122, top 42%LMArena2026-10-09

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1406#94 of 297, top 32%LMArena2026-10-08
LMArena Chinese1449#102 of 285, top 36%LMArena2026-10-08
LMArena French1403#117 of 223, top 53%LMArena2026-10-08
LMArena German1413#83 of 231, top 36%LMArena2026-10-08
LMArena Korean1378#81 of 213, top 39%LMArena2026-10-08
LMArena Russian1404#101 of 283, top 36%LMArena2026-10-08
LMArena Spanish1447#58 of 226, top 26%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1430#61 of 298, top 21%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1435#72 of 291, top 25%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1420#92 of 297, top 31%LMArena2026-10-08
LMArena Creative Writing1381#103 of 295, top 35%LMArena2026-10-08
LMArena Multi-Turn1427#86 of 295, top 30%LMArena2026-10-08

Compare Kimi K2.5 Instant

Other Moonshot AI models

Frequently asked questions

How good is Kimi K2.5 Instant?

Kimi K2.5 Instant by Moonshot AI ranks 89th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.6. Its strongest category is multimodal, where it ranks 50th.

Is Kimi K2.5 Instant open source?

Yes. Kimi K2.5 Instant's weights are downloadable; check the license for commercial terms.

What are Kimi K2.5 Instant's strengths and weaknesses?

Relative to other ranked models, Kimi K2.5 Instant places best in instruction following, reasoning, long context and lowest in knowledge, multimodal, math.

What is Kimi K2.5 Instant best at?

Its best category is multimodal, where it ranks 50th on Noometry.