Noometry

Model comparison

Claude 3.5 Haiku vs GLM-4.7

GLM-4.7 is the stronger model overall, scoring 41.7 to 28.9 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude 3.5 Haiku Anthropic

28.9

Rank #309 Confirmed

GLM-4.7 Z.ai (Zhipu)

41.7

Rank #117 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and GLM-4.7 in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 18.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Claude 3.5 Haiku and 83.3% for GLM-4.7.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuGLM-4.7
ProviderAnthropicZ.ai (Zhipu)
Noometry Index28.941.7
Released2024-10-222025-12-22
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.60
Output $ / M tokens—$2.20
Results tracked4936

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

Category by category

Coding GLM-4.7 leads

Claude 3.5 Haiku: 32.6 (#258), GLM-4.7: 43.6 (#74)

BenchmarkClaude 3.5 HaikuGLM-4.7
SciCode27.4%45.1%
LMArena Coding12871454
Aider Polyglot28%—
LMArena WebDev—1435
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—
ALE-Bench—399.48

Agentic & Tool Use Claude 3.5 Haiku leads

Claude 3.5 Haiku: 27.7 (#90), GLM-4.7: 26.4 (#96)

BenchmarkClaude 3.5 HaikuGLM-4.7
Terminal-Bench—33.4%
BALROG19.3%—
Vending-Bench 2—2,377

Reasoning GLM-4.7 leads

Claude 3.5 Haiku: 17.1 (#286), GLM-4.7: 23.7 (#161)

BenchmarkClaude 3.5 HaikuGLM-4.7
CritPt0%1.7%
LMArena Hard Prompts12511443
Epoch Capabilities Index127.15143.53
SimpleBench—47.7%
Chess Puzzles—6%
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
LiveBench43.5%—

Math GLM-4.7 leads

Claude 3.5 Haiku: 13.7 (#294), GLM-4.7: 37.7 (#92)

BenchmarkClaude 3.5 HaikuGLM-4.7
OTIS Mock AIME 2024-20254.3%83.3%
LMArena Math12441423
FrontierMath (Feb 2025 set)0.3%2.4%
ProofBench—6%
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath Tier 4 (v1)—0%

Knowledge GLM-4.7 leads

Claude 3.5 Haiku: 18.7 (#276), GLM-4.7: 47.0 (#74)

BenchmarkClaude 3.5 HaikuGLM-4.7
GPQA Diamond38.1%83.3%
LMArena Expert12081424
SimpleQA Verified—32.2%
MMLU-Pro60.5%—
Confabulations36.7%—
Vectara Hallucination Rate—11.7%
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.3 (#113), GLM-4.7: —

BenchmarkClaude 3.5 HaikuGLM-4.7
LMArena Vision1092—
GeoBench34%—

Multilingual GLM-4.7 leads

Claude 3.5 Haiku: 40.2 (#213), GLM-4.7: 53.0 (#75)

BenchmarkClaude 3.5 HaikuGLM-4.7
LMArena Non-English12381417
LMArena Chinese12291495
LMArena French12621432
LMArena German12371426
LMArena Japanese11751439
LMArena Korean11721401
LMArena Russian12531423
LMArena Spanish12611433

Instruction Following GLM-4.7 leads

Claude 3.5 Haiku: 63.1 (#229), GLM-4.7: 74.6 (#90)

BenchmarkClaude 3.5 HaikuGLM-4.7
LMArena Instruction Following12411411
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context GLM-4.7 leads

Claude 3.5 Haiku: 38.3 (#195), GLM-4.7: 42.8 (#111)

BenchmarkClaude 3.5 HaikuGLM-4.7
LMArena Longer Query12611432
CL-bench—15.9%
CL-bench Life—10.9%

Writing & Preference GLM-4.7 leads

Claude 3.5 Haiku: 42.9 (#228), GLM-4.7: 61.1 (#89)

BenchmarkClaude 3.5 HaikuGLM-4.7
LMArena Text12551436
LMArena Creative Writing12331401
EQ-Bench Creative Writing11461413
LMArena Multi-Turn12651446
Short-Story Creative Writing73.5%—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than GLM-4.7?

GLM-4.7 is the stronger model overall, scoring 41.7 to 28.9 on the Noometry Index.

Is Claude 3.5 Haiku or GLM-4.7 better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 32.6 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and GLM-4.7 share?

24 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper