Noometry

Model comparison

GLM-5.2 vs Kimi K2.7 Code

GLM-5.2 is the stronger model overall, scoring 51.1 to 43.3 on the Noometry Index.

Last verified . 19 shared benchmarks.

GLM-5.2 Z.ai (Zhipu)

51.1

Rank #44 Confirmed

Kimi K2.7 Code Moonshot AI

43.3

Rank #94 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GLM-5.2 scores higher in 5 categories and Kimi K2.7 Code in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where GLM-5.2 leads 32.4 to 24.0.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 29.3% for GLM-5.2 and 12.2% for Kimi K2.7 Code.
  • Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
  • GLM-5.2 accepts more context: 1M tokens versus 262K.

Side by side

GLM-5.2Kimi K2.7 Code
ProviderZ.ai (Zhipu)Moonshot AI
Noometry Index51.143.3
Released2026-06-132026-06-12
WeightsOpenOpen
Context window1M262K
Max output131K262K
Input $ / M tokens$1.40$0.95
Output $ / M tokens$4.40$4
Results tracked5119

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

Category by category

Coding GLM-5.2 leads

GLM-5.2: 51.3 (#41), Kimi K2.7 Code: 42.9 (#95)

BenchmarkGLM-5.2Kimi K2.7 Code
DeepSWE43.8%30.5%
FrontierCode24.5%30.1%
LMArena WebDev16031473
SciCode50.5%47.5%
WeirdML70.1%54.1%
ALE-Bench1,047886.23
SWE-bench Verified78.7%—
LMArena Coding1485—

Agentic & Tool Use GLM-5.2 leads

GLM-5.2: 32.4 (#63), Kimi K2.7 Code: 24.0 (#122)

BenchmarkGLM-5.2Kimi K2.7 Code
APEX-Agents45.2%37.6%
GBAEval0%0.9%
Vending-Bench 28,3145,083
τ²-bench Banking37.1%—
PostTrainBench31.7%—

Reasoning GLM-5.2 leads

GLM-5.2: 42.3 (#52), Kimi K2.7 Code: 39.0 (#61)

BenchmarkGLM-5.2Kimi K2.7 Code
SimpleBench58.8%57.9%
CritPt20.9%10%
Chess Puzzles21%21%
Surface Evolver Bench55.6%48.8%
Epoch Capabilities Index151.78149.97
ARC-AGI-222.8%—
Kagi LLM Benchmark62.6%—
NYT Connections (extended)74.3%—
ARC-AGI-177%—
EBR-Bench9.5%—
LMArena Hard Prompts1480—
Mystery Game Puzzles19%—
DTBench93.6%—
LMCA45.8%—

Math GLM-5.2 leads

GLM-5.2: 55.7 (#43), Kimi K2.7 Code: 52.9 (#48)

BenchmarkGLM-5.2Kimi K2.7 Code
FrontierMath (Tiers 1-3)59.2%54%
FrontierMath Tier 429.3%12.2%
OTIS Mock AIME 2024-202586.4%95.6%
MathArena Final-Answer Competitions67.6%—
ProofBench35%—
LMArena Math1482—

Knowledge GLM-5.2 leads

GLM-5.2: 57.1 (#40), Kimi K2.7 Code: 53.5 (#57)

BenchmarkGLM-5.2Kimi K2.7 Code
GPQA Diamond91.9%87.9%
SimpleQA Verified34.2%36.5%
LMArena Expert1486—

Multilingual Not comparable

GLM-5.2: 55.8 (#26), Kimi K2.7 Code: —

BenchmarkGLM-5.2Kimi K2.7 Code
LMArena Non-English1459—
LMArena Chinese1519—
LMArena French1479—
LMArena German1468—
LMArena Japanese1451—
LMArena Korean1445—
LMArena Russian1466—
LMArena Spanish1477—

Instruction Following Not comparable

GLM-5.2: 76.9 (#34), Kimi K2.7 Code: —

BenchmarkGLM-5.2Kimi K2.7 Code
LMArena Instruction Following1465—

Long Context Not comparable

GLM-5.2: 45.3 (#43), Kimi K2.7 Code: —

BenchmarkGLM-5.2Kimi K2.7 Code
LMArena Longer Query1479—

Writing & Preference Not comparable

GLM-5.2: 70.4 (#21), Kimi K2.7 Code: —

BenchmarkGLM-5.2Kimi K2.7 Code
LMArena Text1470—
LMArena Creative Writing1462—
EQ-Bench Creative Writing1757—
EQ-Bench 41222—
LMArena Multi-Turn1469—

Frequently asked questions

Is GLM-5.2 better than Kimi K2.7 Code?

GLM-5.2 is the stronger model overall, scoring 51.1 to 43.3 on the Noometry Index.

Which is cheaper, GLM-5.2 or Kimi K2.7 Code?

Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.

Is GLM-5.2 or Kimi K2.7 Code better for coding?

GLM-5.2 scores higher on coding benchmarks: 51.3 versus 42.9 in the Noometry coding category.

Which has the bigger context window?

GLM-5.2 does, with 1M tokens against 262K.

How many benchmarks do GLM-5.2 and Kimi K2.7 Code share?

19 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Kimi K2.7 Code has 19.

Related comparisons

Go deeper