Noometry

Model comparison

Claude Haiku 5.5 vs GLM-4.5-Air

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 38.9 on the Noometry Index.

Last verified . 0 shared benchmarks.

Claude Haiku 5.5 Anthropic

49.5

Rank #52 Confirmed

GLM-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

Summary

  • The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 36.2.
  • Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.20 / $1.10 for GLM-4.5-Air.
  • Claude Haiku 5.5 accepts more context: 1M tokens versus 131K.
  • GLM-4.5-Air has downloadable open weights; the other is API-only.

Side by side

Claude Haiku 5.5GLM-4.5-Air
ProviderAnthropicZ.ai (Zhipu)
Noometry Index49.538.9
Released2026-10-072025-07-20
WeightsProprietaryOpen
Context window1M131K
Max output128K98K
Input $ / M tokens$0.10$0.20
Output $ / M tokens$0.50$1.10
Results tracked927

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

Category by category

Coding Claude Haiku 5.5 leads

Claude Haiku 5.5: 49.2 (#50), GLM-4.5-Air: 33.3 (#259)

BenchmarkClaude Haiku 5.5GLM-4.5-Air
LMArena WebDev1587—
GSO—2.9%
LMArena Coding—1397

Reasoning Claude Haiku 5.5 leads

Claude Haiku 5.5: 35.2 (#69), GLM-4.5-Air: 24.1 (#166)

BenchmarkClaude Haiku 5.5GLM-4.5-Air
Kagi LLM Benchmark—43%
NYT Connections (extended)65.7%—
LMArena Hard Prompts—1379
Mystery Game Puzzles30%—
ForecastBench—59.2

Math Claude Haiku 5.5 leads

Claude Haiku 5.5: 73.6 (#18), GLM-4.5-Air: 36.2 (#170)

BenchmarkClaude Haiku 5.5GLM-4.5-Air
FrontierMath (Tiers 1-3)75.1%—
FrontierMath Tier 446.3%—
OTIS Mock AIME 2024-202598.9%—
Omni-MATH—39.1%
LMArena Math—1396

Knowledge Claude Haiku 5.5 leads

Claude Haiku 5.5: 50.8 (#70), GLM-4.5-Air: 35.0 (#191)

BenchmarkClaude Haiku 5.5GLM-4.5-Air
GPQA Diamond89.6%—
Humanity's Last Exam—8.1%
SimpleQA Verified23.8%—
MMLU-Pro—76.2%
Vectara Hallucination Rate—9.3%
GPQA (HELM)—59.4%
LMArena Expert—1370

Multimodal Not comparable

Claude Haiku 5.5: 43.7 (#21), GLM-4.5-Air: —

BenchmarkClaude Haiku 5.5GLM-4.5-Air
Furniture Assembly47.5%—

Multilingual Not comparable

Claude Haiku 5.5: —, GLM-4.5-Air: 49.1 (#135)

BenchmarkClaude Haiku 5.5GLM-4.5-Air
LMArena Non-English—1366
LMArena Chinese—1426
LMArena French—1399
LMArena German—1377
LMArena Japanese—1348
LMArena Korean—1308
LMArena Russian—1373
LMArena Spanish—1386

Instruction Following Not comparable

Claude Haiku 5.5: —, GLM-4.5-Air: 69.6 (#171)

BenchmarkClaude Haiku 5.5GLM-4.5-Air
IFEval—81.2%
LMArena Instruction Following—1354

Long Context Not comparable

Claude Haiku 5.5: —, GLM-4.5-Air: 41.6 (#135)

BenchmarkClaude Haiku 5.5GLM-4.5-Air
LMArena Longer Query—1366

Writing & Preference Not comparable

Claude Haiku 5.5: —, GLM-4.5-Air: 55.9 (#139)

BenchmarkClaude Haiku 5.5GLM-4.5-Air
LMArena Text—1384
LMArena Creative Writing—1343
WildBench—78.9%
LMArena Multi-Turn—1371

Frequently asked questions

Is Claude Haiku 5.5 better than GLM-4.5-Air?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 38.9 on the Noometry Index.

Which is cheaper, Claude Haiku 5.5 or GLM-4.5-Air?

Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GLM-4.5-Air lists at $0.20 and $1.10.

Is Claude Haiku 5.5 or GLM-4.5-Air better for coding?

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 33.3 in the Noometry coding category.

Which has the bigger context window?

Claude Haiku 5.5 does, with 1M tokens against 131K.

How many benchmarks do Claude Haiku 5.5 and GLM-4.5-Air share?

0 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and GLM-4.5-Air has 27.

Related comparisons

Go deeper