Noometry

Model comparison

Kimi K2 Thinking Turbo vs Qwen2.5 7B Instruct

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 29.0 on the Noometry Index.

Last verified . 3 shared benchmarks.

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

  • They share 3 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 6 categories and Qwen2.5 7B Instruct in 0 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2 Thinking Turbo leads 47.4 to 12.6.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.1% for Kimi K2 Thinking Turbo and 2.5% for Qwen2.5 7B Instruct.

Side by side

Kimi K2 Thinking TurboQwen2.5 7B Instruct
ProviderMoonshot AIAlibaba (Qwen)
Noometry Index45.829.0
Released2025-11-062024-09
WeightsOpenOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.17
Output $ / M tokens—$0.70
Results tracked2115

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

Category by category

Coding Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 38.4 (#178), Qwen2.5 7B Instruct: 36.5 (#208)

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
LMArena WebDev1322—
BigCodeBench Instruct—37.6%
LMArena Coding1454—
BigCodeBench Complete—46.1%

Agentic & Tool Use Not comparable

Kimi K2 Thinking Turbo: —, Qwen2.5 7B Instruct: 23.8 (#124)

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
BALROG—7.8%

Reasoning Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 32.5 (#75), Qwen2.5 7B Instruct: 14.8 (#322)

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
Chess Puzzles20%0%
LMArena Hard Prompts1428—
DTBench—47.7%
LMCA—6.4%
Epoch Capabilities Index—118.51

Math Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 47.4 (#68), Qwen2.5 7B Instruct: 12.6 (#306)

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
OTIS Mock AIME 2024-202583.1%2.5%
Omni-MATH—29.4%
LMArena Math1429—

Knowledge Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 50.9 (#69), Qwen2.5 7B Instruct: 17.0 (#286)

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
GPQA Diamond84.2%35.5%
MMLU-Pro—53.9%
GPQA (HELM)—34.1%
LMArena Expert1439—
MMLU—72.9%

Multilingual Not comparable

Kimi K2 Thinking Turbo: 51.4 (#109), Qwen2.5 7B Instruct: —

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
LMArena Non-English1398—
LMArena Chinese1456—
LMArena French1425—
LMArena German1390—
LMArena Japanese1357—
LMArena Korean1330—
LMArena Russian1391—
LMArena Spanish1406—

Instruction Following Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 74.0 (#109), Qwen2.5 7B Instruct: 63.2 (#231)

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
IFEval—74.1%
LMArena Instruction Following1403—

Long Context Not comparable

Kimi K2 Thinking Turbo: 43.2 (#102), Qwen2.5 7B Instruct: —

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
LMArena Longer Query1415—

Writing & Preference Kimi K2 Thinking Turbo leads

Kimi K2 Thinking Turbo: 60.0 (#104), Qwen2.5 7B Instruct: 48.8 (#195)

BenchmarkKimi K2 Thinking TurboQwen2.5 7B Instruct
LMArena Text1415—
LMArena Creative Writing1374—
WildBench—73.1%
LMArena Multi-Turn1414—

Frequently asked questions

Is Kimi K2 Thinking Turbo better than Qwen2.5 7B Instruct?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 29.0 on the Noometry Index.

Is Kimi K2 Thinking Turbo or Qwen2.5 7B Instruct better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.4 versus 36.5 in the Noometry coding category.

How many benchmarks do Kimi K2 Thinking Turbo and Qwen2.5 7B Instruct share?

3 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper