Model comparison

GLM-4.5-Air vs Solar Pro4

Solar Pro4 is the stronger model overall, scoring 42.1 to 38.9 on the Noometry Index.

Last verified October 10, 2026. 17 shared benchmarks.

GLM-4.5-Air Z.ai (Zhipu)

38.9

Rank #177 Confirmed

Solar Pro4

Upstage

42.1

Rank #121 Confirmed

Summary

They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 1 category and Solar Pro4 in 7 categories; 5 gaps are clear of the uncertainty.
The widest gap is in coding, where Solar Pro4 leads 40.1 to 33.3.
GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
Solar Pro4 accepts more context: 524K tokens versus 131K.
GLM-4.5-Air has downloadable open weights; the other is API-only.

Side by side

GLM-4.5-Air and Solar Pro4 specifications
	GLM-4.5-Air	Solar Pro4
Provider	Z.ai (Zhipu)	Upstage
Noometry Index	38.9	42.1
Released	2025-07-20	2026-08-06
Weights	Open	Proprietary
Context window	131K	524K
Max output	98K	131K
Input $ / M tokens	$0.20	$0.30
Output $ / M tokens	$1.10	$1.20
Results tracked	27	18

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

Category by category

Coding Solar Pro4 leads

GLM-4.5-Air: 33.3 (#259), Solar Pro4: 40.1 (#149)

Coding benchmarks
Benchmark	GLM-4.5-Air	Solar Pro4
LMArena Coding	1397	1437
LMArena WebDev	—	1371
GSO	2.9%	—

Reasoning Solar Pro4 leads

GLM-4.5-Air: 24.1 (#166), Solar Pro4: 28.5 (#104)

Reasoning benchmarks
Benchmark	GLM-4.5-Air	Solar Pro4
LMArena Hard Prompts	1379	1399
Kagi LLM Benchmark	43%	—
ForecastBench	59.2	—

Math Solar Pro4 leads

GLM-4.5-Air: 36.2 (#170), Solar Pro4: 38.8 (#128)

Math benchmarks
Benchmark	GLM-4.5-Air	Solar Pro4
LMArena Math	1396	1416
Omni-MATH	39.1%	—

Knowledge Solar Pro4 leads

GLM-4.5-Air: 35.0 (#191), Solar Pro4: 39.8 (#129)

Knowledge benchmarks
Benchmark	GLM-4.5-Air	Solar Pro4
LMArena Expert	1370	1427
Humanity's Last Exam	8.1%	—
MMLU-Pro	76.2%	—
Vectara Hallucination Rate	9.3%	—
GPQA (HELM)	59.4%	—

Multilingual Too close to call

GLM-4.5-Air: 49.1 (#135), Solar Pro4: 48.7 (#139)

Multilingual benchmarks
Benchmark	GLM-4.5-Air	Solar Pro4
LMArena Non-English	1366	1361
LMArena Chinese	1426	1415
LMArena French	1399	1397
LMArena German	1377	1364
LMArena Japanese	1348	1309
LMArena Korean	1308	1382
LMArena Russian	1373	1360
LMArena Spanish	1386	1401

Instruction Following Solar Pro4 leads

GLM-4.5-Air: 69.6 (#171), Solar Pro4: 72.7 (#132)

Instruction Following benchmarks
Benchmark	GLM-4.5-Air	Solar Pro4
LMArena Instruction Following	1354	1377
IFEval	81.2%	—

Long Context Too close to call

GLM-4.5-Air: 41.6 (#135), Solar Pro4: 42.1 (#130)

Long Context benchmarks
Benchmark	GLM-4.5-Air	Solar Pro4
LMArena Longer Query	1366	1381

Writing & Preference Too close to call

GLM-4.5-Air: 55.9 (#139), Solar Pro4: 56.5 (#138)

Writing & Preference benchmarks
Benchmark	GLM-4.5-Air	Solar Pro4
LMArena Text	1384	1386
LMArena Creative Writing	1343	1316
LMArena Multi-Turn	1371	1385
WildBench	78.9%	—

Frequently asked questions

Is GLM-4.5-Air better than Solar Pro4?

Solar Pro4 is the stronger model overall, scoring 42.1 to 38.9 on the Noometry Index.

Which is cheaper, GLM-4.5-Air or Solar Pro4?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.

Is GLM-4.5-Air or Solar Pro4 better for coding?

Solar Pro4 scores higher on coding benchmarks: 40.1 versus 33.3 in the Noometry coding category.

Which has the bigger context window?

Solar Pro4 does, with 524K tokens against 131K.

How many benchmarks do GLM-4.5-Air and Solar Pro4 share?

17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Solar Pro4 has 18.