Noometry

Model comparison

GLM-4.7 vs Mercury 2

GLM-4.7 is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index. Mercury 2 costs 2.7× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Last verified . 16 shared benchmarks.

GLM-4.7 Z.ai (Zhipu)

41.7

Rank #117 Confirmed

Mercury 2 Inception

38.8

Rank #167 Confirmed

Summary

  • They share 16 benchmarks with published results for both. GLM-4.7 scores higher in 7 categories and Mercury 2 in 0 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 35.6.
  • The biggest single-benchmark swing is SciCode: 45.1% for GLM-4.7 and 38.7% for Mercury 2.
  • Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.60 / $2.20 for GLM-4.7.
  • GLM-4.7 accepts more context: 205K tokens versus 128K.
  • GLM-4.7 has downloadable open weights; the other is API-only.

Side by side

GLM-4.7Mercury 2
ProviderZ.ai (Zhipu)Inception
Noometry Index41.738.8
Released2025-12-222026-02-20
WeightsOpenProprietary
Context window205K128K
Max output131K50K
Input $ / M tokens$0.60$0.25
Output $ / M tokens$2.20$0.75
Results tracked3617

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

Category by category

Coding GLM-4.7 leads

GLM-4.7: 43.6 (#74), Mercury 2: 33.2 (#250)

BenchmarkGLM-4.7Mercury 2
LMArena WebDev14351170
SciCode45.1%38.7%
LMArena Coding14541391
ALE-Bench399.48785.58
WeirdML—43.2%

Agentic & Tool Use Not comparable

GLM-4.7: 26.4 (#96), Mercury 2: —

BenchmarkGLM-4.7Mercury 2
Terminal-Bench33.4%—
Vending-Bench 22,377—

Reasoning Too close to call

GLM-4.7: 23.7 (#161), Mercury 2: 23.0 (#170)

BenchmarkGLM-4.7Mercury 2
CritPt1.7%0.8%
LMArena Hard Prompts14431362
SimpleBench47.7%—
Chess Puzzles6%—
Epoch Capabilities Index143.53—

Math Not comparable

GLM-4.7: 37.7 (#92), Mercury 2: —

BenchmarkGLM-4.7Mercury 2
OTIS Mock AIME 2024-202583.3%—
ProofBench6%—
LMArena Math1423—
FrontierMath (Feb 2025 set)2.4%—
FrontierMath Tier 4 (v1)0%—

Knowledge GLM-4.7 leads

GLM-4.7: 47.0 (#74), Mercury 2: 35.6 (#170)

BenchmarkGLM-4.7Mercury 2
Vectara Hallucination Rate11.7%12.3%
LMArena Expert14241358
GPQA Diamond83.3%—
SimpleQA Verified32.2%—

Multilingual GLM-4.7 leads

GLM-4.7: 53.0 (#75), Mercury 2: 46.8 (#153)

BenchmarkGLM-4.7Mercury 2
LMArena Non-English14171331
LMArena Chinese14951416
LMArena Russian14231303
LMArena French1432—
LMArena German1426—
LMArena Japanese1439—
LMArena Korean1401—
LMArena Spanish1433—

Instruction Following GLM-4.7 leads

GLM-4.7: 74.6 (#90), Mercury 2: 70.4 (#161)

BenchmarkGLM-4.7Mercury 2
LMArena Instruction Following14111328

Long Context GLM-4.7 leads

GLM-4.7: 42.8 (#111), Mercury 2: 40.4 (#149)

BenchmarkGLM-4.7Mercury 2
LMArena Longer Query14321329
CL-bench15.9%—
CL-bench Life10.9%—

Writing & Preference GLM-4.7 leads

GLM-4.7: 61.1 (#89), Mercury 2: 54.0 (#151)

BenchmarkGLM-4.7Mercury 2
LMArena Text14361355
LMArena Creative Writing14011289
LMArena Multi-Turn14461358
EQ-Bench Creative Writing1413—

Frequently asked questions

Is GLM-4.7 better than Mercury 2?

GLM-4.7 is the stronger model overall, scoring 41.7 to 38.8 on the Noometry Index. Mercury 2 costs 2.7× less per token, which makes it the better buy when GLM-4.7's lead doesn't matter for your workload.

Which is cheaper, GLM-4.7 or Mercury 2?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GLM-4.7 lists at $0.60 and $2.20.

Is GLM-4.7 or Mercury 2 better for coding?

GLM-4.7 scores higher on coding benchmarks: 43.6 versus 33.2 in the Noometry coding category.

Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 128K.

How many benchmarks do GLM-4.7 and Mercury 2 share?

16 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Mercury 2 has 17.

Related comparisons

Go deeper