Noometry

Model comparison

GLM-5.3 vs Mercury 2.5

GLM-5.3 is the stronger model overall, scoring 54.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 32× less per token, which makes it the better buy when GLM-5.3's lead doesn't matter for your workload.

Last verified . 4 shared benchmarks.

GLM-5.3 Z.ai (Zhipu)

54.8

Rank #26 Confirmed

Mercury 2.5 Inception

33.5

Rank #242 Reported

Summary

  • They share 4 benchmarks with published results for both. GLM-5.3 scores higher in 3 categories and Mercury 2.5 in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where GLM-5.3 leads 62.3 to 23.3.
  • The biggest single-benchmark swing is ProofBench: 49% for GLM-5.3 and 3% for Mercury 2.5.
  • Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $1.40 / $4.40 for GLM-5.3.
  • GLM-5.3 accepts more context: 1M tokens versus 260K.
  • GLM-5.3 has downloadable open weights; the other is API-only.

Side by side

GLM-5.3Mercury 2.5
ProviderZ.ai (Zhipu)Inception
Noometry Index54.833.5
Released2026-08-142026-09-08
WeightsOpenProprietary
Context window1M260K
Max output131K66K
Input $ / M tokens$1.40$0.04
Output $ / M tokens$4.40$0.15
Results tracked424

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 2.5: 39.5 (#156)

BenchmarkGLM-5.3Mercury 2.5
SciCode59%38.5%
ALE-Bench1,317301.65
DeepSWE69%—
FrontierCode40.1%—
CursorBench42.6%—
LMArena WebDev1622—
FrontierSWE30.2%—
WeirdML75.4%—
LMArena Coding1496—

Agentic & Tool Use Not comparable

GLM-5.3: 36.4 (#38), Mercury 2.5: —

BenchmarkGLM-5.3Mercury 2.5
APEX-Agents56.6%—
Vending-Bench 28,164—

Reasoning GLM-5.3 leads

GLM-5.3: 46.1 (#46), Mercury 2.5: 22.4 (#193)

BenchmarkGLM-5.3Mercury 2.5
CritPt19.1%0%
NYT Connections (extended)74.2%—
Chess Puzzles21%—
LMArena Hard Prompts1489—
Mystery Game Puzzles33%—
DTBench87.7%—
LMCA55.5%—
Bench to the Future 30.15—
Epoch Capabilities Index155.61—

Math GLM-5.3 leads

GLM-5.3: 62.3 (#33), Mercury 2.5: 23.3 (#272)

BenchmarkGLM-5.3Mercury 2.5
ProofBench49%3%
FrontierMath (Tiers 1-3)68.8%—
FrontierMath Tier 429.3%—
OTIS Mock AIME 2024-202591.1%—
LMArena Math1489—

Knowledge Not comparable

GLM-5.3: 58.3 (#37), Mercury 2.5: —

BenchmarkGLM-5.3Mercury 2.5
GPQA Diamond90.9%—
SimpleQA Verified41%—
LMArena Expert1516—

Multilingual Not comparable

GLM-5.3: 55.7 (#28), Mercury 2.5: —

BenchmarkGLM-5.3Mercury 2.5
LMArena Non-English1457—
LMArena Chinese1528—
LMArena French1499—
LMArena German1499—
LMArena Japanese1453—
LMArena Korean1472—
LMArena Russian1463—
LMArena Spanish1460—

Instruction Following Not comparable

GLM-5.3: 77.5 (#23), Mercury 2.5: —

BenchmarkGLM-5.3Mercury 2.5
LMArena Instruction Following1477—

Long Context Not comparable

GLM-5.3: 45.4 (#41), Mercury 2.5: —

BenchmarkGLM-5.3Mercury 2.5
LMArena Longer Query1482—

Writing & Preference Not comparable

GLM-5.3: 75.7 (#6), Mercury 2.5: —

BenchmarkGLM-5.3Mercury 2.5
LMArena Text1471—
LMArena Creative Writing1457—
EQ-Bench Creative Writing2075—
LMArena Multi-Turn1472—

Frequently asked questions

Is GLM-5.3 better than Mercury 2.5?

GLM-5.3 is the stronger model overall, scoring 54.8 to 33.5 on the Noometry Index. Mercury 2.5 costs 32× 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 2.5?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; GLM-5.3 lists at $1.40 and $4.40.

Is GLM-5.3 or Mercury 2.5 better for coding?

GLM-5.3 scores higher on coding benchmarks: 59.5 versus 39.5 in the Noometry coding category.

Which has the bigger context window?

GLM-5.3 does, with 1M tokens against 260K.

How many benchmarks do GLM-5.3 and Mercury 2.5 share?

4 benchmarks have published results for both models. GLM-5.3 has 42 scored results on Noometry and Mercury 2.5 has 4.

Related comparisons

Go deeper