Noometry

Model comparison

Claude 3.5 Haiku vs GLM-4.6

GLM-4.6 is the stronger model overall, scoring 41.4 to 29.2 on the Noometry Index.

Last verified . 21 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

GLM-4.6 Z.ai (Zhipu)

41.4

Rank #135 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and GLM-4.6 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-4.6 leads 39.1 to 14.7.
  • The biggest single-benchmark swing is SciCode: 27.4% for Claude 3.5 Haiku and 38.4% for GLM-4.6.
  • GLM-4.6 has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuGLM-4.6
ProviderAnthropicZ.ai (Zhipu)
Noometry Index29.241.4
Released2024-10-222025-09-30
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.60
Output $ / M tokens—$2.20
Results tracked4929

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

Category by category

Coding GLM-4.6 leads

Claude 3.5 Haiku: 32.9 (#265), GLM-4.6: 40.1 (#148)

BenchmarkClaude 3.5 HaikuGLM-4.6
SciCode27.4%38.4%
LMArena Coding12861449
SWE-bench Verified (bash only)—55.4%
Aider Polyglot28%—
LMArena WebDev—1340
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—
ALE-Bench—340.82

Agentic & Tool Use GLM-4.6 leads

Claude 3.5 Haiku: 28.0 (#95), GLM-4.6: 32.3 (#66)

BenchmarkClaude 3.5 HaikuGLM-4.6
Terminal-Bench—24.5%
Berkeley Function Calling Leaderboard—72.4%
BALROG19.3%—

Reasoning GLM-4.6 leads

Claude 3.5 Haiku: 17.7 (#290), GLM-4.6: 23.7 (#172)

BenchmarkClaude 3.5 HaikuGLM-4.6
CritPt0%1.1%
LMArena Hard Prompts12511440
Kagi LLM Benchmark—47.4%
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math GLM-4.6 leads

Claude 3.5 Haiku: 14.7 (#300), GLM-4.6: 39.1 (#111)

BenchmarkClaude 3.5 HaikuGLM-4.6
LMArena Math12441432
FrontierMath (Feb 2025 set)0.3%3.8%
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath Tier 4 (v1)—2.1%

Knowledge GLM-4.6 leads

Claude 3.5 Haiku: 18.7 (#281), GLM-4.6: 40.2 (#124)

BenchmarkClaude 3.5 HaikuGLM-4.6
LMArena Expert12081431
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
Vectara Hallucination Rate—9.5%
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.8 (#117), GLM-4.6: —

BenchmarkClaude 3.5 HaikuGLM-4.6
LMArena Vision1092—
GeoBench34%—

Multilingual GLM-4.6 leads

Claude 3.5 Haiku: 40.0 (#218), GLM-4.6: 53.5 (#66)

BenchmarkClaude 3.5 HaikuGLM-4.6
LMArena Non-English12381426
LMArena Chinese12291499
LMArena French12641459
LMArena German12371447
LMArena Japanese11751393
LMArena Korean11731400
LMArena Russian12531419
LMArena Spanish12611436

Instruction Following GLM-4.6 leads

Claude 3.5 Haiku: 62.9 (#234), GLM-4.6: 74.3 (#98)

BenchmarkClaude 3.5 HaikuGLM-4.6
LMArena Instruction Following12411410
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context GLM-4.6 leads

Claude 3.5 Haiku: 38.3 (#200), GLM-4.6: 43.4 (#94)

BenchmarkClaude 3.5 HaikuGLM-4.6
LMArena Longer Query12611422

Writing & Preference GLM-4.6 leads

Claude 3.5 Haiku: 42.7 (#234), GLM-4.6: 61.1 (#90)

BenchmarkClaude 3.5 HaikuGLM-4.6
LMArena Text12551440
LMArena Creative Writing12331411
EQ-Bench Creative Writing11461411
LMArena Multi-Turn12651427
Short-Story Creative Writing73.5%—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than GLM-4.6?

GLM-4.6 is the stronger model overall, scoring 41.4 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or GLM-4.6 better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and GLM-4.6 share?

21 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and GLM-4.6 has 29.

Related comparisons

Go deeper