Noometry

Model comparison

Gemma 4 31B IT vs Solar Pro4

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 42.1 on the Noometry Index.

Last verified . 15 shared benchmarks.

Gemma 4 31B IT Google

43.5

Rank #90 Confirmed

Solar Pro4 Upstage

42.1

Rank #121 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Gemma 4 31B IT scores higher in 6 categories and Solar Pro4 in 2 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in multilingual, where Gemma 4 31B IT leads 53.8 to 48.7.
  • Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
  • Solar Pro4 accepts more context: 524K tokens versus 262K.
  • Gemma 4 31B IT has downloadable open weights; the other is API-only.

Side by side

Gemma 4 31B ITSolar Pro4
ProviderGoogleUpstage
Noometry Index43.542.1
Released2026-04-022026-08-06
WeightsOpenProprietary
Context window262K524K
Max output33K131K
Input $ / M tokens$0.09$0.30
Output $ / M tokens$0.34$1.20
Results tracked3518

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

Category by category

Coding Gemma 4 31B IT leads

Gemma 4 31B IT: 42.3 (#108), Solar Pro4: 40.1 (#149)

BenchmarkGemma 4 31B ITSolar Pro4
LMArena WebDev13661371
LMArena Coding14591437
SciCode43.4%—
WeirdML52.3%—
ALE-Bench925.5—

Reasoning Solar Pro4 leads

Gemma 4 31B IT: 27.2 (#122), Solar Pro4: 28.5 (#104)

BenchmarkGemma 4 31B ITSolar Pro4
LMArena Hard Prompts14481399
Kagi LLM Benchmark63.5%—
NYT Connections (extended)70.6%—
CritPt1.4%—
Chess Puzzles5%—
Thematic Generalization53%—
DTBench82.7%—
LMCA39.3%—
Surface Evolver Bench30.6%—
Epoch Capabilities Index142.74—

Math Gemma 4 31B IT leads

Gemma 4 31B IT: 43.2 (#81), Solar Pro4: 38.8 (#128)

BenchmarkGemma 4 31B ITSolar Pro4
LMArena Math14651416
OTIS Mock AIME 2024-202573.3%—

Knowledge Solar Pro4 leads

Gemma 4 31B IT: 37.9 (#151), Solar Pro4: 39.8 (#129)

BenchmarkGemma 4 31B ITSolar Pro4
LMArena Expert14651427
GPQA Diamond75.8%—
SimpleQA Verified10.4%—
Vectara Hallucination Rate7.4%—

Multimodal Not comparable

Gemma 4 31B IT: 41.6 (#34), Solar Pro4: —

BenchmarkGemma 4 31B ITSolar Pro4
LMArena Vision1277—
LMArena Document1425—

Multilingual Gemma 4 31B IT leads

Gemma 4 31B IT: 53.8 (#57), Solar Pro4: 48.7 (#139)

BenchmarkGemma 4 31B ITSolar Pro4
LMArena Non-English14311361
LMArena Chinese14761415
LMArena French14351397
LMArena Russian14601360
LMArena Spanish14441401
LMArena German—1364
LMArena Japanese—1309
LMArena Korean—1382

Instruction Following Gemma 4 31B IT leads

Gemma 4 31B IT: 75.5 (#61), Solar Pro4: 72.7 (#132)

BenchmarkGemma 4 31B ITSolar Pro4
LMArena Instruction Following14331377

Long Context Gemma 4 31B IT leads

Gemma 4 31B IT: 44.2 (#71), Solar Pro4: 42.1 (#130)

BenchmarkGemma 4 31B ITSolar Pro4
LMArena Longer Query14461381

Writing & Preference Gemma 4 31B IT leads

Gemma 4 31B IT: 60.5 (#96), Solar Pro4: 56.5 (#138)

BenchmarkGemma 4 31B ITSolar Pro4
LMArena Text14431386
LMArena Creative Writing14151316
LMArena Multi-Turn14521385
EQ-Bench Creative Writing1368—
EQ-Bench 41120—

Frequently asked questions

Is Gemma 4 31B IT better than Solar Pro4?

Gemma 4 31B IT is the stronger model overall, scoring 43.5 to 42.1 on the Noometry Index.

Which is cheaper, Gemma 4 31B IT or Solar Pro4?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.

Is Gemma 4 31B IT or Solar Pro4 better for coding?

Gemma 4 31B IT scores higher on coding benchmarks: 42.3 versus 40.1 in the Noometry coding category.

Which has the bigger context window?

Solar Pro4 does, with 524K tokens against 262K.

How many benchmarks do Gemma 4 31B IT and Solar Pro4 share?

15 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Solar Pro4 has 18.

Related comparisons

Go deeper