Noometry

Model comparison

Claude 3 Haiku vs GLM-5.3-Flash

GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 25.7 on the Noometry Index.

Last verified . 21 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

GLM-5.3-Flash Z.ai (Zhipu)

49.6

Rank #45 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and GLM-5.3-Flash in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-5.3-Flash leads 53.1 to 9.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 93.9% for GLM-5.3-Flash.
  • GLM-5.3-Flash has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuGLM-5.3-Flash
ProviderAnthropicZ.ai (Zhipu)
Noometry Index25.749.6
Released2024-03-072026-08-20
WeightsProprietaryOpen
Context window—1M
Max output—131K
Input $ / M tokens—$0.15
Output $ / M tokens—$0.50
Results tracked3736

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

Category by category

Coding GLM-5.3-Flash leads

Claude 3 Haiku: 26.1 (#320), GLM-5.3-Flash: 53.7 (#26)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
LMArena Coding11991506
DeepSWE—63.4%
FrontierCode—31.8%
LMArena WebDev—1614
SciCode—51.6%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—303.55
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, GLM-5.3-Flash: 34.3 (#41)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
APEX-Agents—52.8%
GDP.pdf—14%

Reasoning GLM-5.3-Flash leads

Claude 3 Haiku: 15.7 (#303), GLM-5.3-Flash: 31.7 (#69)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
LMArena Hard Prompts11741490
Epoch Capabilities Index118.3151.9
Kagi LLM Benchmark34.2%—
CritPt—15.4%
Chess Puzzles—14%
Mystery Game Puzzles—8%
DTBench50.1%—
LMCA8.8%—
Surface Evolver Bench—52.5%
Bench to the Future 3—0.15
ForecastBench53.2—
WinoGrande74.2%—

Math GLM-5.3-Flash leads

Claude 3 Haiku: 9.2 (#313), GLM-5.3-Flash: 53.1 (#38)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
OTIS Mock AIME 2024-20251.8%93.9%
LMArena Math11881499
FrontierMath (Tiers 1-3)—55.8%
FrontierMath Tier 4—17.1%
ProofBench—21%
MATH Level 514.9%—

Knowledge GLM-5.3-Flash leads

Claude 3 Haiku: 17.3 (#280), GLM-5.3-Flash: 58.4 (#33)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
GPQA Diamond36.3%90.2%
LMArena Expert11481512
Confabulations34.2%—
MMLU73.8%—

Multimodal GLM-5.3-Flash leads

Claude 3 Haiku: 23.1 (#123), GLM-5.3-Flash: 42.6 (#25)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
LMArena Vision9501304
ScienceQA72%—

Multilingual GLM-5.3-Flash leads

Claude 3 Haiku: 36.1 (#238), GLM-5.3-Flash: 56.2 (#24)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
LMArena Non-English11781462
LMArena Chinese11551529
LMArena French11941495
LMArena German11741457
LMArena Japanese11021420
LMArena Korean11081443
LMArena Russian12041472
LMArena Spanish11651471

Instruction Following GLM-5.3-Flash leads

Claude 3 Haiku: 61.5 (#242), GLM-5.3-Flash: 77.8 (#17)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
LMArena Instruction Following11741480

Long Context GLM-5.3-Flash leads

Claude 3 Haiku: 36.1 (#232), GLM-5.3-Flash: 45.3 (#41)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
LMArena Longer Query11911479

Writing & Preference GLM-5.3-Flash leads

Claude 3 Haiku: 29.8 (#286), GLM-5.3-Flash: 65.4 (#49)

BenchmarkClaude 3 HaikuGLM-5.3-Flash
LMArena Text11951471
LMArena Creative Writing11571440
LMArena Multi-Turn11901471
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than GLM-5.3-Flash?

GLM-5.3-Flash is the stronger model overall, scoring 49.6 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or GLM-5.3-Flash better for coding?

GLM-5.3-Flash scores higher on coding benchmarks: 53.7 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and GLM-5.3-Flash share?

21 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and GLM-5.3-Flash has 36.

Related comparisons

Go deeper