Noometry

Model comparison

Claude Haiku 4.5 vs GLM-4.7

GLM-4.7 is the stronger model overall, scoring 42.0 to 39.5 on the Noometry Index.

Last verified . 31 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.5

Rank #165 Confirmed

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 4 categories and GLM-4.7 in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 37.7.
  • The biggest single-benchmark swing is SimpleQA Verified: 13.2% for Claude Haiku 4.5 and 32.2% for GLM-4.7.
  • GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
  • GLM-4.7 accepts more context: 205K tokens versus 200K.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

Claude Haiku 4.5GLM-4.7
ProviderAnthropicZ.ai (Zhipu)
Noometry Index39.542.0
Released2025-10-152025-12-22
WeightsProprietaryOpen
Context window200K205K
Max output64K131K
Input $ / M tokens$1$0.60
Output $ / M tokens$5$2.20
Results tracked5336

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

Category by category

Coding Too close to call

Claude Haiku 4.5: 44.0 (#78), GLM-4.7: 44.0 (#79)

BenchmarkClaude Haiku 4.5GLM-4.7
LMArena WebDev13301435
SciCode43.3%45.1%
LMArena Coding14531454
ALE-Bench653.48399.48
SWE-bench Verified (bash only)66.6%—
SWE-bench Multilingual64.7%—
WeirdML45.4%—

Agentic & Tool Use Claude Haiku 4.5 leads

Claude Haiku 4.5: 33.6 (#52), GLM-4.7: 26.5 (#103)

BenchmarkClaude Haiku 4.5GLM-4.7
Terminal-Bench35.5%33.4%
Vending-Bench 2458.892,377
Berkeley Function Calling Leaderboard68.7%—
DeepResearch Bench45.5%—
BALROG31.2%—
ExploitBench13.7%—

Reasoning GLM-4.7 leads

Claude Haiku 4.5: 15.1 (#320), GLM-4.7: 24.3 (#164)

BenchmarkClaude Haiku 4.5GLM-4.7
CritPt0%1.7%
Chess Puzzles8%6%
LMArena Hard Prompts14201443
Epoch Capabilities Index142.41143.51
ARC-AGI-24%—
SimpleBench—47.7%
NYT Connections (extended)14.3%—
ARC-AGI-147.7%—
DTBench73.6%—
LMCA30.9%—
ForecastBench61.4—

Math Claude Haiku 4.5 leads

Claude Haiku 4.5: 44.9 (#78), GLM-4.7: 38.6 (#135)

BenchmarkClaude Haiku 4.5GLM-4.7
OTIS Mock AIME 2024-202566.7%83.3%
LMArena Math13961423
FrontierMath (Feb 2025 set)5.9%2.4%
FrontierMath Tier 4 (v1)2.1%0%
ProofBench—6%
Omni-MATH56.1%—
MATH Level 596.4%—

Knowledge GLM-4.7 leads

Claude Haiku 4.5: 37.7 (#153), GLM-4.7: 47.0 (#80)

BenchmarkClaude Haiku 4.5GLM-4.7
GPQA Diamond71.2%83.3%
SimpleQA Verified13.2%32.2%
Vectara Hallucination Rate9.8%11.7%
LMArena Expert14421424
MMLU-Pro77.7%—
GPQA (HELM)60.5%—

Multimodal Not comparable

Claude Haiku 4.5: 26.8 (#118), GLM-4.7: —

BenchmarkClaude Haiku 4.5GLM-4.7
Blueprint-Bench 20%—
LMArena Document1420—

Multilingual GLM-4.7 leads

Claude Haiku 4.5: 49.9 (#129), GLM-4.7: 52.8 (#79)

BenchmarkClaude Haiku 4.5GLM-4.7
LMArena Non-English13771417
LMArena Chinese14171495
LMArena French14081432
LMArena German13751424
LMArena Japanese13391439
LMArena Korean13471399
LMArena Russian13811423
LMArena Spanish14201434

Instruction Following GLM-4.7 leads

Claude Haiku 4.5: 71.4 (#149), GLM-4.7: 74.4 (#95)

BenchmarkClaude Haiku 4.5GLM-4.7
LMArena Instruction Following14141411
IFEval80.1%—

Long Context Too close to call

Claude Haiku 4.5: 43.6 (#92), GLM-4.7: 42.8 (#116)

BenchmarkClaude Haiku 4.5GLM-4.7
LMArena Longer Query14271432
CL-bench—15.9%
CL-bench Life—10.9%

Writing & Preference GLM-4.7 leads

Claude Haiku 4.5: 57.9 (#123), GLM-4.7: 60.9 (#93)

BenchmarkClaude Haiku 4.5GLM-4.7
LMArena Text13961435
LMArena Creative Writing13721401
LMArena Multi-Turn14091446
EQ-Bench Creative Writing—1413
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than GLM-4.7?

GLM-4.7 is the stronger model overall, scoring 42.0 to 39.5 on the Noometry Index.

Which is cheaper, Claude Haiku 4.5 or GLM-4.7?

GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.

Is Claude Haiku 4.5 or GLM-4.7 better for coding?

They score almost the same on coding (44.0 vs 44.0); test both on your own repository before choosing.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 200K.

How many benchmarks do Claude Haiku 4.5 and GLM-4.7 share?

31 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper