Noometry

Moonshot AI, open weights

Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo by Moonshot AI ranks 70th of 354 ranked models on the Noometry Index as of October 2026, with a score of 45.8. Its strongest category is math, where it ranks 68th.

Last verified

Noometry rank
#70 of 354
Index score
45.8
Evidence
Confirmed 21 results
Provider
Moonshot AI
Released
November 6, 2025
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 38.4
  2. Reasoning 32.5
  3. Math 47.4
  4. Knowledge 50.9
  5. Multilingual 51.4
  6. Instruction Following 74.0
  7. Long Context 43.2
  8. Writing & Preference 60.0
CategoryScoreRankResults
Coding38.4#1782
Reasoning32.5#752
Math47.4#682
Knowledge50.9#692
Multilingual51.4#1091
Instruction Following74.0#1091
Long Context43.2#1021
Writing & Preference60.0#1043

Strengths and weaknesses

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

Strongest categories

CategoryScorevs medianRank
Math47.4+10.8#68 of 327, top 21%
Reasoning32.5+8.9#75 of 350, top 22%
Knowledge50.9+13.6#69 of 314, top 22%

Weakest categories

CategoryScorevs medianRank
Coding38.4−0.4#178 of 340, top 53%
Multilingual51.4+4.0#109 of 297, top 37%
Instruction Following74.0+2.7#109 of 305, top 36%

Closest competitors

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

ModelRankScoreBlended $/MSpeed
GLM-5#6646.1$1.5523Compare
Qwen3.5 397B-A17B#6746.0$1.359Compare
Qwen3.8 27B#6846.0$1.11—Compare
GPT-5.3 Codex#6945.8$4.81—Compare
Qwen3.5 Max Preview#7145.3——Compare
Qwen3.7 Plus#7245.3$0.70—Compare
Hy4 preview#7345.3$1.13—Compare
MiMo-V2.5-Pro#7445.2$0.54—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 WebDev1322#95 of 113, top 85%LMArena2026-10-08
LMArena Coding1454#82 of 294, top 28%LMArena2026-10-08

Reasoning

BenchmarkScorePositionSettingSourceDate
Chess Puzzles20%#59 of 129, top 46%Epoch AI2025-12-10
LMArena Hard Prompts1428#92 of 297, top 31%LMArena2026-10-08

Math

BenchmarkScorePositionSettingSourceDate
OTIS Mock AIME 2024-202583.1%#76 of 173, top 44%Epoch AI2025-11-13
LMArena Math1429#89 of 285, top 32%LMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond84.2%#67 of 186, top 37%Epoch AI2025-11-11
LMArena Expert1439#88 of 273, top 33%LMArena2026-10-08

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1398#109 of 297, top 37%LMArena2026-10-08
LMArena Chinese1456#98 of 285, top 35%LMArena2026-10-08
LMArena French1425#96 of 223, top 44%LMArena2026-10-08
LMArena German1390#104 of 231, top 46%LMArena2026-10-08
LMArena Japanese1357#93 of 211, top 45%LMArena2026-10-08
LMArena Korean1330#114 of 213, top 54%LMArena2026-10-08
LMArena Russian1391#117 of 283, top 42%LMArena2026-10-08
LMArena Spanish1406#104 of 226, top 47%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1403#103 of 298, top 35%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1415#97 of 291, top 34%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1415#105 of 297, top 36%LMArena2026-10-08
LMArena Creative Writing1374#108 of 295, top 37%LMArena2026-10-08
LMArena Multi-Turn1414#103 of 295, top 35%LMArena2026-10-08

Compare Kimi K2 Thinking Turbo

Other Moonshot AI models

Frequently asked questions

How good is Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo by Moonshot AI ranks 70th of 354 ranked models on the Noometry Index as of October 2026, with a score of 45.8. Its strongest category is math, where it ranks 68th.

Is Kimi K2 Thinking Turbo open source?

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

What are Kimi K2 Thinking Turbo's strengths and weaknesses?

Relative to other ranked models, Kimi K2 Thinking Turbo places best in math, reasoning, knowledge and lowest in coding, multilingual, instruction following.

What is Kimi K2 Thinking Turbo best at?

Its best category is math, where it ranks 68th on Noometry.