Noometry

Model comparison

GLM-5.3 vs Mercury 2

GLM-5.3 is the stronger model overall, scoring 54.8 to 39.1 on the Noometry Index. Mercury 2 costs 5.7× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.

Last verified . 16 shared benchmarks.

GLM-5.3 Z.ai (Zhipu)

54.8

Rank #26 Confirmed

Mercury 2 Inception

39.1

Rank #175 Confirmed

Summary

  • They share 16 benchmarks with published results for both. GLM-5.3 scores higher in 7 categories and Mercury 2 in 0 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in coding, where GLM-5.3 leads 59.5 to 33.5.
  • The biggest single-benchmark swing is WeirdML: 75.4% for GLM-5.3 and 43.2% for Mercury 2.
  • Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.40 / $4.40 for GLM-5.3.
  • GLM-5.3 accepts more context: 1M tokens versus 128K.
  • GLM-5.3 has downloadable open weights; the other is API-only.

Side by side

GLM-5.3Mercury 2
ProviderZ.ai (Zhipu)Inception
Noometry Index54.839.1
Released2026-08-142026-02-20
WeightsOpenProprietary
Context window1M128K
Max output131K50K
Input $ / M tokens$1.40$0.25
Output $ / M tokens$4.40$0.75
Results tracked4217

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

Category by category

Coding GLM-5.3 leads

GLM-5.3: 59.5 (#14), Mercury 2: 33.5 (#255)

BenchmarkGLM-5.3Mercury 2
LMArena WebDev16221171
SciCode59%38.7%
WeirdML75.4%43.2%
LMArena Coding14961391
ALE-Bench1,317785.58
DeepSWE69%—
FrontierCode40.1%—
CursorBench42.6%—
FrontierSWE30.2%—

Agentic & Tool Use Not comparable

GLM-5.3: 36.4 (#38), Mercury 2: —

BenchmarkGLM-5.3Mercury 2
APEX-Agents56.6%—
Vending-Bench 28,164—

Reasoning GLM-5.3 leads

GLM-5.3: 46.1 (#46), Mercury 2: 23.8 (#170)

BenchmarkGLM-5.3Mercury 2
CritPt19.1%0.8%
LMArena Hard Prompts14891362
NYT Connections (extended)74.2%—
Chess Puzzles21%—
Mystery Game Puzzles33%—
DTBench87.7%—
LMCA55.5%—
Bench to the Future 30.15—
Epoch Capabilities Index155.61—

Math Not comparable

GLM-5.3: 62.3 (#33), Mercury 2: —

BenchmarkGLM-5.3Mercury 2
FrontierMath (Tiers 1-3)68.8%—
FrontierMath Tier 429.3%—
OTIS Mock AIME 2024-202591.1%—
ProofBench49%—
LMArena Math1489—

Knowledge GLM-5.3 leads

GLM-5.3: 58.3 (#37), Mercury 2: 36.2 (#172)

BenchmarkGLM-5.3Mercury 2
LMArena Expert15161358
GPQA Diamond90.9%—
SimpleQA Verified41%—
Vectara Hallucination Rate—12.3%

Multilingual GLM-5.3 leads

GLM-5.3: 55.7 (#28), Mercury 2: 46.6 (#157)

BenchmarkGLM-5.3Mercury 2
LMArena Non-English14571331
LMArena Chinese15281417
LMArena Russian14631304
LMArena French1499—
LMArena German1499—
LMArena Japanese1453—
LMArena Korean1472—
LMArena Spanish1460—

Instruction Following GLM-5.3 leads

GLM-5.3: 77.5 (#23), Mercury 2: 70.2 (#165)

BenchmarkGLM-5.3Mercury 2
LMArena Instruction Following14771329

Long Context GLM-5.3 leads

GLM-5.3: 45.4 (#41), Mercury 2: 40.5 (#154)

BenchmarkGLM-5.3Mercury 2
LMArena Longer Query14821330

Writing & Preference GLM-5.3 leads

GLM-5.3: 75.7 (#6), Mercury 2: 53.8 (#155)

BenchmarkGLM-5.3Mercury 2
LMArena Text14711355
LMArena Creative Writing14571289
LMArena Multi-Turn14721358
EQ-Bench Creative Writing2075—

Frequently asked questions

Is GLM-5.3 better than Mercury 2?

GLM-5.3 is the stronger model overall, scoring 54.8 to 39.1 on the Noometry Index. Mercury 2 costs 5.7× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.

Which is cheaper, GLM-5.3 or Mercury 2?

Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GLM-5.3 lists at $1.40 and $4.40.

Is GLM-5.3 or Mercury 2 better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.5 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

GLM-5.3 does, with 1M tokens against 128K.

How many benchmarks do GLM-5.3 and Mercury 2 share?

16 benchmarks have published results for both models. GLM-5.3 has 42 scored results on Noometry and Mercury 2 has 17.

Related comparisons

Go deeper