Enter opens the highlighted result. Esc closes.

Gemini 3.1 Pro Preview vs Gemini 4 Neon

Gemini 4 Neon leads Gemini 3.1 Pro Preview on coding, 86.9 to 32.3 on the Vibe Coding Index, and Gemini 3.1 Pro Preview costs 1.3x less per output token ($12.00 vs $15.00 per million). Updated November 22, 2026; 55 benchmarks have a result for both.

Gemini 3.1 Pro PreviewGoogle
Coding
32.3
Overall
66.5
Output $/M
$12.00
0
Gemini 4 NeonGoogle
Coding
86.9
Overall
89.1
Output $/M
$15.00
55
vs boards won of 55 shared

Gemini 3.1 Pro Preview or Gemini 4 Neon: which to pick

Pick Gemini 4 Neon for coding: it scores 86.9 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview.

Pick Gemini 3.1 Pro Preview for output tokens 1.3x cheaper ($12.00 vs $15.00 per million).

Shared results
55
Gemini 3.1 Pro Preview only
84
Gemini 4 Neon only
14
Like-for-like categories
7 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
Gemini 3.1 Pro Preview 32.3 from 4 benchmarks, Gemini 4 Neon 86.9 from 4 benchmarks.
Widest category
Agentic work, 48.6 points apart on average over 7 shared benchmarks.
Widest single gap
Vending-Bench 2: Gemini 3.1 Pro Preview $911 against Gemini 4 Neon $16,843, 94.3 points apart on a 0 to 100 scale.
Output price
Gemini 3.1 Pro Preview $12.00 against Gemini 4 Neon $15.00 per million output tokens, 1.3x apart.
Context window
Both take 1.05M tokens.

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
CategoryGemini 3.1 Pro PreviewBarsGemini 4 NeonTies
Coding09
Agentic work07
Reasoning010
Math05
Knowledge05
Web design05
General014
All shared boards055
CodingLike-for-likeSix of these boards feed the Vibe Coding Index09
Coding benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
LiveBench codingNot measured89.7%Only Gemini 4 Neon measured
LMArena WebDev14461765Gemini 4 Neon
LiveCodeBench (Vals AI)88.5%Not measuredOnly Gemini 3.1 Pro Preview measured
SWE-bench Verified (Vals AI)78.8%Not measuredOnly Gemini 3.1 Pro Preview measured
Terminal-Bench 4 (Vals AI)2.5%61.6%Gemini 4 Neon
Vibe Code Bench (Vals AI)32.0%93.7%Gemini 4 Neon
Code migration (Vals AI)17.3%Not measuredOnly Gemini 3.1 Pro Preview measured
ProgramBench (Vals AI)0.0%Not measuredOnly Gemini 3.1 Pro Preview measured
IOI (Vals AI)51.8%Not measuredOnly Gemini 3.1 Pro Preview measured
Terminal-Bench 2.1 (Vals AI)70.8%Not measuredOnly Gemini 3.1 Pro Preview measured
Vibe Code Bench 1-100 (Vals AI)6.7%Not measuredOnly Gemini 3.1 Pro Preview measured
SciCode58.7%Not measuredOnly Gemini 3.1 Pro Preview measured
Terminal-Bench Hard (Artificial Analysis run)53.8%Not measuredOnly Gemini 3.1 Pro Preview measured
Terminal-Bench 4.0 (Artificial Analysis run)4.0%63.6%Gemini 4 Neon
FrontierCode 2.0Not measured44.4%Only Gemini 4 Neon measured
Terminal-Bench80.2%Not measuredOnly Gemini 3.1 Pro Preview measured
GSO-Bench22.6%Not measuredOnly Gemini 3.1 Pro Preview measured
WeirdML72.1%Not measuredOnly Gemini 3.1 Pro Preview measured
MirrorCode8.9%Not measuredOnly Gemini 3.1 Pro Preview measured
ALE-Bench1160.6Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: coding14831555Gemini 4 Neon
LMArena Text: software and IT14861542Gemini 4 Neon
LMArena WebDev: React14371787Gemini 4 Neon
LMArena WebDev: HTML14881803Gemini 4 Neon
LMArena WebDev: from an image1480Not measuredOnly Gemini 3.1 Pro Preview measured
SciCode14.3%Not measuredOnly Gemini 3.1 Pro Preview measured
GameBench 264.798.0Gemini 4 Neon
CursorBench 4.0Not measured65.4%Only Gemini 4 Neon measured
Neither model has a result on the other 24 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Intelligence benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
AA Intelligence IndexNot measured61.4Only Gemini 4 Neon measured
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index07
Agentic work benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
Design Arena: agents building web apps1093Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building full-stack apps1045Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building mobile apps1086Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building Android apps1033Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building Godot games1124Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building games1061Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: HTML slides1054Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: PowerPoint slides1047Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: spreadsheets918Not measuredOnly Gemini 3.1 Pro Preview measured
LiveBench researchNot measured94.5%Only Gemini 4 Neon measured
LiveBench browserNot measured95.6%Only Gemini 4 Neon measured
LiveBench long agenticNot measured82.6%Only Gemini 4 Neon measured
SREBench (Vals AI)0.0%Not measuredOnly Gemini 3.1 Pro Preview measured
Finance Agent (Vals AI)43.0%Not measuredOnly Gemini 3.1 Pro Preview measured
Tax Agent Bench (Vals AI)9.3%54.9%Gemini 4 Neon
Legal Research Bench (Vals AI)20.7%56.3%Gemini 4 Neon
Harvey's Legal Agent Benchmark (Vals AI)Not measured19.6%Only Gemini 4 Neon measured
Excel Modeling Benchmark (Vals AI)52.6%Not measuredOnly Gemini 3.1 Pro Preview measured
BioMysteryBench (Vals AI)60.0%80.0%Gemini 4 Neon
Terminal-Bench-Science (Vals AI)1.4%62.9%Gemini 4 Neon
Vals Science Index27.4%62.6%Gemini 4 Neon
τ²-Bench Telecom95.6%Not measuredOnly Gemini 3.1 Pro Preview measured
APEX-Agents35.1%82.9%Gemini 4 Neon
METR time horizons77.0%Not measuredOnly Gemini 3.1 Pro Preview measured
BALROG57.0%Not measuredOnly Gemini 3.1 Pro Preview measured
DeepResearch Bench47.8%Not measuredOnly Gemini 3.1 Pro Preview measured
PostTrainBench18.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Vending-Bench 2$911$16,843Gemini 4 Neon
τ³-Banking26.0%Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 15 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index010
Reasoning benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
GPQA Diamond95.5%Not measuredOnly Gemini 3.1 Pro Preview measured
LiveBench reasoningNot measured89.6%Only Gemini 4 Neon measured
MysteryMechanism (Vals AI)20.7%45.0%Gemini 4 Neon
MMMU Pro (Vals AI)88.2%Not measuredOnly Gemini 3.1 Pro Preview measured
GPQA Diamond (Artificial Analysis run)94.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Humanity's Last Exam (Artificial Analysis run)47.0%Not measuredOnly Gemini 3.1 Pro Preview measured
HLE-Diamond (Artificial Analysis run)31.4%71.3%Gemini 4 Neon
CritPt v2, hard subset (Artificial Analysis run)Not measured61.5%Only Gemini 4 Neon measured
GPQA Diamond (Epoch AI run)94.4%96.3%Gemini 4 Neon
ARC-AGI98.0%Not measuredOnly Gemini 3.1 Pro Preview measured
ARC-AGI-277.1%Not measuredOnly Gemini 3.1 Pro Preview measured
SimpleBench79.6%94.4%Gemini 4 Neon
Chess puzzles51.0%83.0%Gemini 4 Neon
Mystery game puzzles34.0%85.0%Gemini 4 Neon
EBR-bench14.3%98.1%Gemini 4 Neon
LMArena Text: hard prompts14851547Gemini 4 Neon
LMArena Text: expert14841560Gemini 4 Neon
LMArena Text: hard prompts in English14801524Gemini 4 Neon
LMArena Vision: diagrams1311Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: homework1317Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index05
Math benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
AIME98.1%Not measuredOnly Gemini 3.1 Pro Preview measured
OTIS Mock AIME95.6%100.0%Gemini 4 Neon
FrontierMath, tiers 1 to 359.6%91.2%Gemini 4 Neon
FrontierMath, tier 426.8%97.6%Gemini 4 Neon
ProofBench26.0%Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: math14851548Gemini 4 Neon
LMArena Text: mathematical work14771566Gemini 4 Neon
MathArena27.3%Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
MMLU Pro91.0%Not measuredOnly Gemini 3.1 Pro Preview measured
LegalBench (Vals AI)87.4%Not measuredOnly Gemini 3.1 Pro Preview measured
CaseLaw (Vals AI)64.8%Not measuredOnly Gemini 3.1 Pro Preview measured
CorpFin (Vals AI)64.5%Not measuredOnly Gemini 3.1 Pro Preview measured
TaxEval (Vals AI)72.9%Not measuredOnly Gemini 3.1 Pro Preview measured
MortgageTax (Vals AI)69.4%Not measuredOnly Gemini 3.1 Pro Preview measured
MedQA (Vals AI)96.4%Not measuredOnly Gemini 3.1 Pro Preview measured
MedCode (Vals AI)59.1%Not measuredOnly Gemini 3.1 Pro Preview measured
AA-OmniscienceNot measured54.8Only Gemini 4 Neon measured
SimpleQA Verified73.5%75.2%Gemini 4 Neon
GeoBench84.0%Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: science14961549Gemini 4 Neon
LMArena Text: medicine and healthcare14861534Gemini 4 Neon
LMArena Text: legal and government14871518Gemini 4 Neon
LMArena Text: business and finance14601493Gemini 4 Neon
FACTS Benchmark Suite69.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index05
Web design benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
Design Arena: websites12211347Gemini 4 Neon
Design Arena: UI components12091349Gemini 4 Neon
Design Arena: game dev11741394Gemini 4 Neon
Design Arena: data viz1203Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: 3D12011490Gemini 4 Neon
Design Arena: all code categories12121391Gemini 4 Neon
Design Arena: SVG1269Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: ASCII art1255Not measuredOnly Gemini 3.1 Pro Preview measured
LiveBench designNot measured81.5%Only Gemini 4 Neon measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index014
General benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
Vals IndexNot measured70.9%Only Gemini 4 Neon measured
LiveBench data analysisNot measured85.3%Only Gemini 4 Neon measured
Public Benefits Bench (Vals AI)53.8%Not measuredOnly Gemini 3.1 Pro Preview measured
SAGE (Vals AI)83.2%Not measuredOnly Gemini 3.1 Pro Preview measured
MedScribe (Vals AI)76.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Vals Multimodal Index56.1%Not measuredOnly Gemini 3.1 Pro Preview measured
IFBench77.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Long context reasoning (AA-LCR)82.0%Not measuredOnly Gemini 3.1 Pro Preview measured
GDPval-AA799Not measuredOnly Gemini 3.1 Pro Preview measured
DTBench97.1%Not measuredOnly Gemini 3.1 Pro Preview measured
LMCA53.8%Not measuredOnly Gemini 3.1 Pro Preview measured
CL-bench20.8%Not measuredOnly Gemini 3.1 Pro Preview measured
Furniture assembly26.7%89.2%Gemini 4 Neon
ExploitBench26.1%Not measuredOnly Gemini 3.1 Pro Preview measured
CL-bench Life16.9%Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text14801524Gemini 4 Neon
LMArena Text: instruction following14651535Gemini 4 Neon
LMArena Text: creative writing14831519Gemini 4 Neon
LMArena Vision1296Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: English14781511Gemini 4 Neon
LMArena Text: non-English14761524Gemini 4 Neon
LMArena Text: Chinese15291598Gemini 4 Neon
LMArena Text: German1491Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: Japanese1495Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: Korean1457Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: French14871563Gemini 4 Neon
LMArena Text: Spanish14801505Gemini 4 Neon
LMArena Text: Russian14971554Gemini 4 Neon
LMArena Text: Polish1498Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: multi-turn14861525Gemini 4 Neon
LMArena Text: longer queries14821533Gemini 4 Neon
LMArena Text: writing and language14811517Gemini 4 Neon
LMArena Text: entertainment and media14651495Gemini 4 Neon
LMArena Vision: English1286Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: Chinese1362Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: reading text1305Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: humor1324Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: captioning1343Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: recognizing things1327Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: creative writing1324Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Document1443Not measuredOnly Gemini 3.1 Pro Preview measured
EQ-Bench 41132Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 7 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.1 Pro Preview and Gemini 4 Neon
BenchmarkGemini 3.1 Pro PreviewGemini 4 NeonLeader
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

Gemini 3.1 Pro Preview$0.0080Fits in one request
Gemini 4 Neon$0.011Fits in one request

Gemini 3.1 Pro Preview costs less

Repository review

50K input + 3K output tokens

Gemini 3.1 Pro Preview$0.136Fits in one request
Gemini 4 Neon$0.195Fits in one request

Gemini 3.1 Pro Preview costs less

Agent loop

200K input + 10K output tokens

Gemini 3.1 Pro Preview$0.520Fits in one request
Gemini 4 Neon$0.750Fits in one request

Gemini 3.1 Pro Preview 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 Gemini 3.1 Pro Preview and Gemini 4 Neon
SpecificationGoogle Gemini 3.1 Pro PreviewGoogle Gemini 4 Neon
MakerGoogleGoogle
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 19, 2026November 18, 2026
Context window1.05M1.05M
Input $/Mtok$2.00$3.00
Output $/Mtok$12.00$15.00
Coding index32.386.9
Independent measurements behind it44
Cost per solved task$0.99Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.1 Pro Preview better than Gemini 4 Neon for coding?

Pick Gemini 4 Neon for coding: it scores 86.9 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview for output tokens 1.3x cheaper ($12.00 vs $15.00 per million).

Which is cheaper, Gemini 3.1 Pro Preview or Gemini 4 Neon?

Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; Gemini 4 Neon costs $3.00 and $15.00. Cost per solved task is known for Gemini 3.1 Pro Preview only.

Which has the bigger context window, Gemini 3.1 Pro Preview or Gemini 4 Neon?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.1 Pro Preview vs Gemini 4 Neon comparison based on?

55 benchmarks have a result for both models as of November 22, 2026. Gemini 3.1 Pro Preview's coding index rests on 4 independent benchmarks and Gemini 4 Neon's on 4. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gemini-3-1-pro-preview-vs-gemini-4-neon" title="Gemini 3.1 Pro Preview vs Gemini 4 Neon, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gemini-3-1-pro-preview-vs-gemini-4-neon">LLMBenchmark.ai, Gemini 3.1 Pro Preview vs Gemini 4 Neon</a></p>