Enter opens the highlighted result. Esc closes.

Gemma 3 12B vs Solar Pro 4

Solar Pro 4 leads Gemma 3 12B on the Artificial Analysis Intelligence Index, 28.2 to 3.8, and Gemma 3 12B costs 3.7x less per output token ($0.1625 vs $0.60 per million). Updated October 22, 2026; 28 benchmarks have a result for both.

Replace Gemma 3 12B Replace Solar Pro 4
Gemma 3 12BGoogle
Coding
No data
Overall
28.0
Output $/M
$0.1625
2
Solar Pro 4Upstage
Coding
No data
Overall
No data
Output $/M
$0.60
26
vs boards won of 28 shared

Gemma 3 12B or Solar Pro 4: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Gemma 3 12B for output tokens 3.7x cheaper ($0.1625 vs $0.60 per million) and work measured by AA Coding Index or SciCode, where it leads.

Model AGemma 3 12BGoogleNot benchmarkedNo coding benchmarkNo cost per solved taskModel BSolar Pro 4UpstageNot benchmarked1 independent benchmarkNo cost per solved task
Shared results
28
Gemma 3 12B only
15
Solar Pro 4 only
17
Like-for-like categories
6 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Gemma 3 12B not benchmarked, Solar Pro 4 not benchmarked.
Widest category
Coding, 31.0 points apart on average over 4 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): Gemma 3 12B 8.3% against Solar Pro 4 70.7%, 62.3 points apart on a 0 to 100 scale.
Output price
Gemma 3 12B $0.1625 against Solar Pro 4 $0.60 per million output tokens, 3.7x apart.
Context window
Gemma 3 12B takes 131K tokens, Solar Pro 4 524K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGemma 3 12BBarsSolar Pro 4Ties
Coding04
Intelligence01
Reasoning05
Math02
Knowledge04
General210
All shared boards226
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
Coding benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
LMArena WebDevNot measured1371Only Solar Pro 4 measured
AA Coding Index5.852.7Solar Pro 4
LiveCodeBench (Artificial Analysis run)13.7%Not measuredOnly Gemma 3 12B measured
SciCode16.4%48.0%Solar Pro 4
Terminal-Bench Hard (Artificial Analysis run)0.8%Not measuredOnly Gemma 3 12B measured
ALE-BenchNot measured179.3Only Solar Pro 4 measured
LMArena Text: coding12811438Solar Pro 4
LMArena Text: software and IT13131431Solar Pro 4
LMArena WebDev: ReactNot measured1363Only Solar Pro 4 measured
LMArena WebDev: HTMLNot measured1371Only Solar Pro 4 measured
SciCode0.0%Not measuredOnly Gemma 3 12B measured
Neither model has a result on the other 28 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
Intelligence benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
AA Intelligence Index3.828.2Solar Pro 4
Epoch Capabilities Index123.5Not measuredOnly Gemma 3 12B measured
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
Agentic work benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
AA Agentic Index0.1Not measuredOnly Gemma 3 12B measured
Design Arena: agents building web appsNot measured1105Only Solar Pro 4 measured
τ²-Bench Telecom10.8%Not measuredOnly Gemma 3 12B measured
Berkeley Function Calling Leaderboard (BFCL)30.4%Not measuredOnly Gemma 3 12B measured
Neither model has a result on the other 37 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
Reasoning benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
GPQA Diamond (Artificial Analysis run)34.9%89.1%Solar Pro 4
Humanity's Last Exam (Artificial Analysis run)4.2%29.8%Solar Pro 4
GPQA Diamond (Epoch AI run)39.5%Not measuredOnly Gemma 3 12B measured
LMArena Text: hard prompts13091400Solar Pro 4
LMArena Text: expert12481428Solar Pro 4
LMArena Text: hard prompts in English13181427Solar Pro 4
Neither model has a result on the other 16 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index02
Math benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
AA Math Index18.3Not measuredOnly Gemma 3 12B measured
AIME 2025 (Artificial Analysis run)18.3%Not measuredOnly Gemma 3 12B measured
OTIS Mock AIME16.7%Not measuredOnly Gemma 3 12B measured
LMArena Text: math13071421Solar Pro 4
LMArena Text: mathematical work13361427Solar Pro 4
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
Knowledge benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
MMLU Pro (Artificial Analysis run)59.5%Not measuredOnly Gemma 3 12B measured
LMArena Text: science13661404Solar Pro 4
LMArena Text: medicine and healthcare13341374Solar Pro 4
LMArena Text: legal and government13811383Solar Pro 4
LMArena Text: business and finance13761381Solar Pro 4
Neither model has a result on the other 13 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
Web design benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
Design Arena: websitesNot measured1176Only Solar Pro 4 measured
Design Arena: UI componentsNot measured1147Only Solar Pro 4 measured
Design Arena: game devNot measured1169Only Solar Pro 4 measured
Design Arena: data vizNot measured1177Only Solar Pro 4 measured
Design Arena: 3DNot measured1178Only Solar Pro 4 measured
Design Arena: all code categoriesNot measured1182Only Solar Pro 4 measured
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index210
General benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
IFBench36.7%Not measuredOnly Gemma 3 12B measured
Long context reasoning (AA-LCR)8.3%70.7%Solar Pro 4
DTBench48.8%Not measuredOnly Gemma 3 12B measured
LMCA4.5%Not measuredOnly Gemma 3 12B measured
LMArena Text13341388Solar Pro 4
LMArena Text: instruction following12991375Solar Pro 4
LMArena Text: creative writing13311317Gemma 3 12B
LMArena Text: English13491414Solar Pro 4
LMArena Text: non-English13181363Solar Pro 4
LMArena Text: ChineseNot measured1422Only Solar Pro 4 measured
LMArena Text: German13701358Gemma 3 12B
LMArena Text: JapaneseNot measured1320Only Solar Pro 4 measured
LMArena Text: KoreanNot measured1383Only Solar Pro 4 measured
LMArena Text: FrenchNot measured1400Only Solar Pro 4 measured
LMArena Text: SpanishNot measured1409Only Solar Pro 4 measured
LMArena Text: Russian13351357Solar Pro 4
LMArena Text: PolishNot measured1304Only Solar Pro 4 measured
LMArena Text: multi-turn13341385Solar Pro 4
LMArena Text: longer queries13171382Solar Pro 4
LMArena Text: writing and language13071344Solar Pro 4
LMArena Text: entertainment and media12971332Solar Pro 4
Neither model has a result on the other 25 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 3 12B and Solar Pro 4
BenchmarkGemma 3 12BSolar Pro 4Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Gemma 3 12B$0.0002Fits in one request
Solar Pro 4$0.0004Fits in one request

Gemma 3 12B costs less

Repository review

50K input + 3K output tokens

Gemma 3 12B$0.0042Fits in one request
Solar Pro 4$0.0093Fits in one request

Gemma 3 12B costs less

Agent loop

200K input + 10K output tokens

Gemma 3 12B$0.017Exceeds the context window
Solar Pro 4$0.036Fits in one request

Gemma 3 12B costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Gemma 3 12B and Solar Pro 4
SpecificationGoogle Gemma 3 12BUpstage Solar Pro 4
MakerGoogleUpstage
WeightsOpen weightsNo public weights listed
ReleasedMarch 13, 2025August 10, 2026
Context window131K524K
Input $/Mtok$0.075$0.15
Output $/Mtok$0.1625$0.60
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it01
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 3 12B better than Solar Pro 4 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 3 12B for output tokens 3.7x cheaper ($0.1625 vs $0.60 per million) and work measured by AA Coding Index or SciCode, where it leads.

Which is cheaper, Gemma 3 12B or Solar Pro 4?

Gemma 3 12B costs $0.075 per million input tokens and $0.1625 per million output tokens; Solar Pro 4 costs $0.15 and $0.60. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 3 12B or Solar Pro 4?

Solar Pro 4, with 524K tokens against 131K.

How many benchmarks is the Gemma 3 12B vs Solar Pro 4 comparison based on?

28 benchmarks have a result for both models as of October 22, 2026. Gemma 3 12B's coding index rests on 0 independent benchmarks and Solar Pro 4's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next