Noometry

Model comparison

GLM-4.7 vs Kimi K2 Thinking Turbo

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 42.0 on the Noometry Index.

Last verified . 21 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GLM-4.7 scores higher in 4 categories and Kimi K2 Thinking Turbo in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Kimi K2 Thinking Turbo leads 47.4 to 38.6.
  • The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 20% for Kimi K2 Thinking Turbo.

Side by side

GLM-4.7Kimi K2 Thinking Turbo
ProviderZ.ai (Zhipu)Moonshot AI
Noometry Index42.045.8
Released2025-12-222025-11-06
WeightsOpenOpen
Context window205K—
Max output131K—
Input $ / M tokens$0.60—
Output $ / M tokens$2.20—
Results tracked3621

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

Category by category

Coding GLM-4.7 leads

GLM-4.7: 44.0 (#79), Kimi K2 Thinking Turbo: 38.4 (#178)

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
LMArena WebDev14351322
LMArena Coding14541454
SciCode45.1%—
ALE-Bench399.48—

Agentic & Tool Use Not comparable

GLM-4.7: 26.5 (#103), Kimi K2 Thinking Turbo: —

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
Terminal-Bench33.4%—
Vending-Bench 22,377—

Reasoning Kimi K2 Thinking Turbo leads

GLM-4.7: 24.3 (#164), Kimi K2 Thinking Turbo: 32.5 (#75)

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
Chess Puzzles6%20%
LMArena Hard Prompts14431428
SimpleBench47.7%—
CritPt1.7%—
Epoch Capabilities Index143.51—

Math Kimi K2 Thinking Turbo leads

GLM-4.7: 38.6 (#135), Kimi K2 Thinking Turbo: 47.4 (#68)

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
OTIS Mock AIME 2024-202583.3%83.1%
LMArena Math14231429
ProofBench6%—
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge Kimi K2 Thinking Turbo leads

GLM-4.7: 47.0 (#80), Kimi K2 Thinking Turbo: 50.9 (#69)

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
GPQA Diamond83.3%84.2%
LMArena Expert14241439
SimpleQA Verified32.2%—
Vectara Hallucination Rate11.7%—

Multilingual GLM-4.7 leads

GLM-4.7: 52.8 (#79), Kimi K2 Thinking Turbo: 51.4 (#109)

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
LMArena Non-English14171398
LMArena Chinese14951456
LMArena French14321425
LMArena German14241390
LMArena Japanese14391357
LMArena Korean13991330
LMArena Russian14231391
LMArena Spanish14341406

Instruction Following Too close to call

GLM-4.7: 74.4 (#95), Kimi K2 Thinking Turbo: 74.0 (#109)

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
LMArena Instruction Following14111403

Long Context Too close to call

GLM-4.7: 42.8 (#116), Kimi K2 Thinking Turbo: 43.2 (#102)

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
LMArena Longer Query14321415
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference Too close to call

GLM-4.7: 60.9 (#93), Kimi K2 Thinking Turbo: 60.0 (#104)

BenchmarkGLM-4.7Kimi K2 Thinking Turbo
LMArena Text14351415
LMArena Creative Writing14011374
LMArena Multi-Turn14461414
EQ-Bench Creative Writing1413—

Frequently asked questions

Is GLM-4.7 better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 42.0 on the Noometry Index.

Is GLM-4.7 or Kimi K2 Thinking Turbo better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 38.4 in the Noometry coding category.

How many benchmarks do GLM-4.7 and Kimi K2 Thinking Turbo share?

21 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper