Noometry

Model comparison

Claude Opus 4.6 vs GLM-4.7

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 42.0 on the Noometry Index. GLM-4.7 costs 10× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

GLM-4.7 Z.ai (Zhipu)

42.0

Rank #124 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and GLM-4.7 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 24.3.
  • The biggest single-benchmark swing is Terminal-Bench: 79.8% for Claude Opus 4.6 and 33.4% for GLM-4.7.
  • GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 205K.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.6GLM-4.7
ProviderAnthropicZ.ai (Zhipu)
Noometry Index58.242.0
Released2026-02-042025-12-22
WeightsProprietaryOpen
Context window1M205K
Max output128K131K
Input $ / M tokens$5$0.60
Output $ / M tokens$25$2.20
Results tracked6836

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

Category by category

Coding Claude Opus 4.6 leads

Claude Opus 4.6: 57.2 (#20), GLM-4.7: 44.0 (#79)

BenchmarkClaude Opus 4.6GLM-4.7
LMArena WebDev15471435
LMArena Coding15361454
ALE-Bench996.5399.48
SWE-bench Verified78.7%—
FrontierCode26.6%—
SWE-bench Verified (bash only)75.6%—
SWE-bench Multilingual72%—
SciCode—45.1%
GSO41.2%—
WeirdML78%—
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), GLM-4.7: 26.5 (#103)

BenchmarkClaude Opus 4.6GLM-4.7
Terminal-Bench79.8%33.4%
Vending-Bench 28,0182,377
APEX-Agents46.3%—
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
GBAEval44.1%—
LMArena Search1253—
METR Time Horizons78.9%—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), GLM-4.7: 24.3 (#164)

BenchmarkClaude Opus 4.6GLM-4.7
SimpleBench67.6%47.7%
Chess Puzzles17%6%
LMArena Hard Prompts15271443
Epoch Capabilities Index155.24143.51
ARC-AGI-269.2%—
Kagi LLM Benchmark83.6%—
NYT Connections (extended)92.1%—
ARC-AGI-194%—
CritPt—1.7%
EnigmaEval7.6%—
Thematic Generalization80.6%—
EBR-Bench12.7%—
Mystery Game Puzzles25%—
DTBench91.2%—
LMCA55.8%—
ForecastBench60—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), GLM-4.7: 38.6 (#135)

BenchmarkClaude Opus 4.6GLM-4.7
OTIS Mock AIME 2024-202594.4%83.3%
ProofBench50%6%
LMArena Math15191423
FrontierMath (Feb 2025 set)40.7%2.4%
FrontierMath Tier 4 (v1)22.9%0%
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions78.5%—

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), GLM-4.7: 47.0 (#80)

BenchmarkClaude Opus 4.6GLM-4.7
GPQA Diamond90.5%83.3%
SimpleQA Verified47%32.2%
Vectara Hallucination Rate12.2%11.7%
LMArena Expert15461424
Humanity's Last Exam34.4%—

Multimodal Not comparable

Claude Opus 4.6: 37.3 (#74), GLM-4.7: —

BenchmarkClaude Opus 4.6GLM-4.7
LMArena Vision1316—
Furniture Assembly28.3%—
LMArena Document1507—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), GLM-4.7: 52.8 (#79)

BenchmarkClaude Opus 4.6GLM-4.7
LMArena Non-English14891417
LMArena Chinese15511495
LMArena French15131432
LMArena German15021424
LMArena Japanese14841439
LMArena Korean14641399
LMArena Russian14971423
LMArena Spanish15101434

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), GLM-4.7: 74.4 (#95)

BenchmarkClaude Opus 4.6GLM-4.7
LMArena Instruction Following15231411

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), GLM-4.7: 42.8 (#116)

BenchmarkClaude Opus 4.6GLM-4.7
CL-bench20.7%15.9%
CL-bench Life17%10.9%
LMArena Longer Query15201432

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), GLM-4.7: 60.9 (#93)

BenchmarkClaude Opus 4.6GLM-4.7
LMArena Text15031435
LMArena Creative Writing15051401
EQ-Bench Creative Writing18091413
LMArena Multi-Turn15131446
EQ-Bench 41223—

Frequently asked questions

Is Claude Opus 4.6 better than GLM-4.7?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 42.0 on the Noometry Index. GLM-4.7 costs 10× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.6 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 Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or GLM-4.7 better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 44.0 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 205K.

How many benchmarks do Claude Opus 4.6 and GLM-4.7 share?

34 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and GLM-4.7 has 36.

Related comparisons

Go deeper