Model comparison

GLM-4.7-Flash vs Hy3

Hy3 is the stronger model overall, scoring 44.2 to 38.8 on the Noometry Index. GLM-4.7-Flash costs 1.6× less per token, which makes it the better buy when Hy3's lead doesn't matter for your workload.

Last verified October 11, 2026. 16 shared benchmarks.

GLM-4.7-Flash Z.ai (Zhipu)

38.8

Rank #180 Confirmed

Hy3

Tencent

44.2

Rank #79 Confirmed

Summary

They share 16 benchmarks with published results for both. GLM-4.7-Flash scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Hy3 leads 62.2 to 47.4.
GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $0.13 / $0.53 for Hy3.
Hy3 accepts more context: 262K tokens versus 200K.

Side by side

GLM-4.7-Flash and Hy3 specifications
	GLM-4.7-Flash	Hy3
Provider	Z.ai (Zhipu)	Tencent
Noometry Index	38.8	44.2
Released	2026-01-19	2026-07-06
Weights	Open	Open
Context window	200K	262K
Max output	131K	128K
Input $ / M tokens	$0.06	$0.13
Output $ / M tokens	$0.40	$0.53
Results tracked	21	19

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

Category by category

Coding Hy3 leads

GLM-4.7-Flash: 40.6 (#135), Hy3: 46.8 (#63)

Coding benchmarks
Benchmark	GLM-4.7-Flash	Hy3
LMArena Coding	1383	1464
LMArena WebDev	—	1508

Reasoning Hy3 leads

GLM-4.7-Flash: 20.9 (#229), Hy3: 26.1 (#136)

Reasoning benchmarks
Benchmark	GLM-4.7-Flash	Hy3
LMArena Hard Prompts	1356	1447
NYT Connections (extended)	—	41.2%
Chess Puzzles	0%	—

Math Hy3 leads

GLM-4.7-Flash: 36.1 (#173), Hy3: 40.1 (#93)

Math benchmarks
Benchmark	GLM-4.7-Flash	Hy3
LMArena Math	1355	1475
OTIS Mock AIME 2024-2025	58.3%	—

Knowledge Hy3 leads

GLM-4.7-Flash: 35.5 (#184), Hy3: 40.8 (#114)

Knowledge benchmarks
Benchmark	GLM-4.7-Flash	Hy3
LMArena Expert	1357	1460
GPQA Diamond	60.5%	—
Vectara Hallucination Rate	9.3%	—

Multilingual Hy3 leads

GLM-4.7-Flash: 46.5 (#158), Hy3: 53.5 (#65)

Multilingual benchmarks
Benchmark	GLM-4.7-Flash	Hy3
LMArena Non-English	1330	1426
LMArena Chinese	1403	1493
LMArena French	1332	1461
LMArena German	1337	1439
LMArena Korean	1283	1395
LMArena Russian	1332	1432
LMArena Spanish	1350	1456
LMArena Japanese	—	1392

Instruction Following Hy3 leads

GLM-4.7-Flash: 70.1 (#167), Hy3: 75.1 (#70)

Instruction Following benchmarks
Benchmark	GLM-4.7-Flash	Hy3
LMArena Instruction Following	1327	1426

Long Context Hy3 leads

GLM-4.7-Flash: 40.9 (#148), Hy3: 44.1 (#75)

Long Context benchmarks
Benchmark	GLM-4.7-Flash	Hy3
LMArena Longer Query	1345	1442

Writing & Preference Hy3 leads

GLM-4.7-Flash: 47.4 (#210), Hy3: 62.2 (#81)

Writing & Preference benchmarks
Benchmark	GLM-4.7-Flash	Hy3
LMArena Text	1351	1439
LMArena Creative Writing	1297	1402
LMArena Multi-Turn	1342	1436
EQ-Bench Creative Writing	1125	—

Frequently asked questions

Is GLM-4.7-Flash better than Hy3?

Which is cheaper, GLM-4.7-Flash or Hy3?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; Hy3 lists at $0.13 and $0.53.

Is GLM-4.7-Flash or Hy3 better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 40.6 in the Noometry coding category.

Which has the bigger context window?

Hy3 does, with 262K tokens against 200K.

How many benchmarks do GLM-4.7-Flash and Hy3 share?

16 benchmarks have published results for both models. GLM-4.7-Flash has 21 scored results on Noometry and Hy3 has 19.