Model comparison

Gemma 3 4B vs Solar Pro4

Solar Pro4 is the stronger model overall, scoring 42.1 to 28.1 on the Noometry Index. Gemma 3 4B costs 10× less per token, which makes it the better buy when Solar Pro4's lead doesn't matter for your workload.

Last verified October 10, 2026. 12 shared benchmarks.

Gemma 3 4B

Google

28.1

Rank #326 Confirmed

Solar Pro4

Upstage

42.1

Rank #121 Confirmed

Summary

They share 12 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in knowledge, where Solar Pro4 leads 39.8 to 11.8.
Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
Solar Pro4 accepts more context: 524K tokens versus 131K.
Gemma 3 4B has downloadable open weights; the other is API-only.

Side by side

Gemma 3 4B and Solar Pro4 specifications
	Gemma 3 4B	Solar Pro4
Provider	Google	Upstage
Noometry Index	28.1	42.1
Released	2025-03-12	2026-08-06
Weights	Open	Proprietary
Context window	131K	524K
Max output	4K	131K
Input $ / M tokens	$0.04	$0.30
Output $ / M tokens	$0.08	$1.20
Results tracked	22	18

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

Category by category

Coding Solar Pro4 leads

Gemma 3 4B: 35.9 (#215), Solar Pro4: 40.1 (#149)

Coding benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
LMArena Coding	1230	1437
LMArena WebDev	—	1371

Agentic & Tool Use Not comparable

Gemma 3 4B: 20.9 (#142), Solar Pro4: —

Agentic & Tool Use benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
Berkeley Function Calling Leaderboard	19.6%	—

Reasoning Solar Pro4 leads

Gemma 3 4B: 13.2 (#335), Solar Pro4: 28.5 (#104)

Reasoning benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
LMArena Hard Prompts	1253	1399
Kagi LLM Benchmark	25.2%	—
Chess Puzzles	0%	—
DTBench	50.9%	—
LMCA	2.8%	—
Epoch Capabilities Index	116.02	—

Math Solar Pro4 leads

Gemma 3 4B: 16.8 (#292), Solar Pro4: 38.8 (#128)

Math benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
LMArena Math	1239	1416
OTIS Mock AIME 2024-2025	7.5%	—

Knowledge Solar Pro4 leads

Gemma 3 4B: 11.8 (#299), Solar Pro4: 39.8 (#129)

Knowledge benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
LMArena Expert	1223	1427
GPQA Diamond	23.2%	—
Vectara Hallucination Rate	6.4%	—

Multilingual Solar Pro4 leads

Gemma 3 4B: 42.5 (#194), Solar Pro4: 48.7 (#139)

Multilingual benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
LMArena Non-English	1273	1361
LMArena German	1281	1364
LMArena Russian	1294	1360
LMArena Chinese	—	1415
LMArena French	—	1397
LMArena Japanese	—	1309
LMArena Korean	—	1382
LMArena Spanish	—	1401

Instruction Following Solar Pro4 leads

Gemma 3 4B: 65.2 (#225), Solar Pro4: 72.7 (#132)

Instruction Following benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
LMArena Instruction Following	1239	1377

Long Context Solar Pro4 leads

Gemma 3 4B: 38.7 (#194), Solar Pro4: 42.1 (#130)

Long Context benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
LMArena Longer Query	1273	1381

Writing & Preference Solar Pro4 leads

Gemma 3 4B: 42.0 (#239), Solar Pro4: 56.5 (#138)

Writing & Preference benchmarks
Benchmark	Gemma 3 4B	Solar Pro4
LMArena Text	1291	1386
LMArena Creative Writing	1271	1316
LMArena Multi-Turn	1255	1385
EQ-Bench Creative Writing	1068	—

Frequently asked questions

Is Gemma 3 4B better than Solar Pro4?

Which is cheaper, Gemma 3 4B or Solar Pro4?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.

Is Gemma 3 4B or Solar Pro4 better for coding?

Solar Pro4 scores higher on coding benchmarks: 40.1 versus 35.9 in the Noometry coding category.

Which has the bigger context window?

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

How many benchmarks do Gemma 3 4B and Solar Pro4 share?

12 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Solar Pro4 has 18.