Noometry

Model comparison

GLM-5.1 vs Kimi K2 Thinking Turbo

GLM-5.1 is the stronger model overall, scoring 47.8 to 45.8 on the Noometry Index.

Last verified . 21 shared benchmarks.

GLM-5.1 Z.ai (Zhipu)

47.8

Rank #59 Confirmed

Kimi K2 Thinking Turbo Moonshot AI

45.8

Rank #70 Confirmed

Summary

  • They share 21 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Kimi K2 Thinking Turbo in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GLM-5.1 leads 48.7 to 38.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 83.1% for Kimi K2 Thinking Turbo.

Side by side

GLM-5.1Kimi K2 Thinking Turbo
ProviderZ.ai (Zhipu)Moonshot AI
Noometry Index47.845.8
Released2026-04-072025-11-06
WeightsOpenOpen
Context window200K—
Max output131K—
Input $ / M tokens$1.40—
Output $ / M tokens$4.40—
Results tracked4121

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

Category by category

Coding GLM-5.1 leads

GLM-5.1: 48.7 (#55), Kimi K2 Thinking Turbo: 38.4 (#178)

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
LMArena WebDev15081322
LMArena Coding14851454
SWE-bench Verified74.2%—
SciCode43.8%—
WeirdML57.1%—
ALE-Bench887.1—

Agentic & Tool Use Not comparable

GLM-5.1: 24.9 (#113), Kimi K2 Thinking Turbo: —

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
APEX-Agents40.9%—
ExploitBench18.1%—
GBAEval0%—
Vending-Bench 25,634—

Reasoning GLM-5.1 leads

GLM-5.1: 39.1 (#60), Kimi K2 Thinking Turbo: 32.5 (#75)

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
Chess Puzzles19%20%
LMArena Hard Prompts14721428
SimpleBench55.1%—
NYT Connections (extended)77.7%—
CritPt4.6%—
Thematic Generalization69.8%—
Epoch Capabilities Index149.84—

Math GLM-5.1 leads

GLM-5.1: 49.7 (#60), Kimi K2 Thinking Turbo: 47.4 (#68)

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
OTIS Mock AIME 2024-202593.3%83.1%
LMArena Math14731429
FrontierMath (Tiers 1-3)36.8%—
MathArena Final-Answer Competitions67.1%—
ProofBench22.2%—
FrontierMath (Feb 2025 set)33.4%—
FrontierMath Tier 4 (v1)12.5%—

Knowledge GLM-5.1 leads

GLM-5.1: 54.9 (#50), Kimi K2 Thinking Turbo: 50.9 (#69)

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
GPQA Diamond89.9%84.2%
LMArena Expert14761439
SimpleQA Verified34%—

Multilingual GLM-5.1 leads

GLM-5.1: 55.0 (#36), Kimi K2 Thinking Turbo: 51.4 (#109)

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
LMArena Non-English14471398
LMArena Chinese15151456
LMArena French14741425
LMArena German14651390
LMArena Japanese14341357
LMArena Korean14181330
LMArena Russian14541391
LMArena Spanish14691406

Instruction Following GLM-5.1 leads

GLM-5.1: 76.3 (#42), Kimi K2 Thinking Turbo: 74.0 (#109)

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
LMArena Instruction Following14511403

Long Context GLM-5.1 leads

GLM-5.1: 44.9 (#53), Kimi K2 Thinking Turbo: 43.2 (#102)

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
LMArena Longer Query14661415

Writing & Preference GLM-5.1 leads

GLM-5.1: 66.9 (#31), Kimi K2 Thinking Turbo: 60.0 (#104)

BenchmarkGLM-5.1Kimi K2 Thinking Turbo
LMArena Text14611415
LMArena Creative Writing14531374
LMArena Multi-Turn14721414
EQ-Bench Creative Writing1592—

Frequently asked questions

Is GLM-5.1 better than Kimi K2 Thinking Turbo?

GLM-5.1 is the stronger model overall, scoring 47.8 to 45.8 on the Noometry Index.

Is GLM-5.1 or Kimi K2 Thinking Turbo better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 38.4 in the Noometry coding category.

How many benchmarks do GLM-5.1 and Kimi K2 Thinking Turbo share?

21 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Kimi K2 Thinking Turbo has 21.

Related comparisons

Go deeper