Model comparison

Mistral Small 3 vs Solar Pro4

Solar Pro4 is the stronger model overall, scoring 42.1 to 31.2 on the Noometry Index. Mistral Small 3 costs 9.1× 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. 16 shared benchmarks.

Mistral Small 3

Mistral AI

31.2

Rank #278 Confirmed

Solar Pro4

Upstage

42.1

Rank #121 Confirmed

Summary

They share 16 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Solar Pro4 in 8 categories; 8 gaps are clear of the uncertainty.
The widest gap is in writing & preference, where Solar Pro4 leads 56.5 to 32.2.
Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
Solar Pro4 accepts more context: 524K tokens versus 33K.
Mistral Small 3 has downloadable open weights; the other is API-only.

Side by side

Mistral Small 3 and Solar Pro4 specifications
	Mistral Small 3	Solar Pro4
Provider	Mistral AI	Upstage
Noometry Index	31.2	42.1
Released	2025-01-30	2026-08-06
Weights	Open	Proprietary
Context window	33K	524K
Max output	16K	131K
Input $ / M tokens	$0.05	$0.30
Output $ / M tokens	$0.08	$1.20
Results tracked	24	18

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

Category by category

Coding Solar Pro4 leads

Mistral Small 3: 36.5 (#207), Solar Pro4: 40.1 (#149)

Coding benchmarks
Benchmark	Mistral Small 3	Solar Pro4
LMArena Coding	1246	1437
LMArena WebDev	—	1371
BigCodeBench Instruct	45.3%	—
BigCodeBench Complete	50.4%	—

Reasoning Solar Pro4 leads

Mistral Small 3: 18.9 (#273), Solar Pro4: 28.5 (#104)

Reasoning benchmarks
Benchmark	Mistral Small 3	Solar Pro4
LMArena Hard Prompts	1233	1399
Chess Puzzles	0%	—
Epoch Capabilities Index	127.07	—

Math Solar Pro4 leads

Mistral Small 3: 16.3 (#295), Solar Pro4: 38.8 (#128)

Math benchmarks
Benchmark	Mistral Small 3	Solar Pro4
LMArena Math	1240	1416
OTIS Mock AIME 2024-2025	6.7%	—

Knowledge Solar Pro4 leads

Mistral Small 3: 25.1 (#263), Solar Pro4: 39.8 (#129)

Knowledge benchmarks
Benchmark	Mistral Small 3	Solar Pro4
LMArena Expert	1202	1427
GPQA Diamond	47.3%	—
Confabulations	25.2%	—

Multilingual Solar Pro4 leads

Mistral Small 3: 37.3 (#236), Solar Pro4: 48.7 (#139)

Multilingual benchmarks
Benchmark	Mistral Small 3	Solar Pro4
LMArena Non-English	1198	1361
LMArena Chinese	1204	1415
LMArena French	1203	1397
LMArena German	1211	1364
LMArena Japanese	1111	1309
LMArena Korean	1188	1382
LMArena Russian	1216	1360
LMArena Spanish	—	1401

Instruction Following Solar Pro4 leads

Mistral Small 3: 63.7 (#229), Solar Pro4: 72.7 (#132)

Instruction Following benchmarks
Benchmark	Mistral Small 3	Solar Pro4
LMArena Instruction Following	1214	1377

Long Context Solar Pro4 leads

Mistral Small 3: 37.8 (#211), Solar Pro4: 42.1 (#130)

Long Context benchmarks
Benchmark	Mistral Small 3	Solar Pro4
LMArena Longer Query	1246	1381

Writing & Preference Solar Pro4 leads

Mistral Small 3: 32.2 (#280), Solar Pro4: 56.5 (#138)

Writing & Preference benchmarks
Benchmark	Mistral Small 3	Solar Pro4
LMArena Text	1234	1386
LMArena Creative Writing	1195	1316
LMArena Multi-Turn	1217	1385
EQ-Bench Creative Writing	707	—

Frequently asked questions

Is Mistral Small 3 better than Solar Pro4?

Which is cheaper, Mistral Small 3 or Solar Pro4?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.

Is Mistral Small 3 or Solar Pro4 better for coding?

Solar Pro4 scores higher on coding benchmarks: 40.1 versus 36.5 in the Noometry coding category.

Which has the bigger context window?

Solar Pro4 does, with 524K tokens against 33K.

How many benchmarks do Mistral Small 3 and Solar Pro4 share?

16 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Solar Pro4 has 18.