Gemini 3.1 Pro Preview vs Gemini 3 Flash Preview
Gemini 3 Flash Preview leads Gemini 3.1 Pro Preview on coding, 43.7 to 32.3 on the Vibe Coding Index, and Gemini 3 Flash Preview costs 4.0x less per output token ($3.00 vs $12.00 per million). Updated October 22, 2026; 63 benchmarks have a result for both.
vs boards won of 63 shared, 1 tied
Gemini 3.1 Pro Preview or Gemini 3 Flash Preview: which to pick
Pick Gemini 3 Flash Preview for coding: it scores 43.7 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview, though on 2 benchmarks against 4.
Pick Gemini 3.1 Pro Preview for work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.
Model AGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved taskModel BGemini 3 Flash PreviewGoogle43.7/1002 independent benchmarks$0.37 per solved task
- Shared results
- 63
- Gemini 3.1 Pro Preview only
- 70
- Gemini 3 Flash Preview only
- 8
- Like-for-like categories
- 8 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.
Coding
Vibe Coding Index, six public coding benchmarks
Gemini 3 Flash Preview
Gemini 3 Flash Preview scores 43.7 against 32.3.
4 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 29.7 against 26.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.1 Pro Preview has a AA Agentic Index result, 8.2.
Directional only
Reasoning
GPQA Diamond
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 87.9%.
Same board, both measured
Math
AIME
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 98.1% against 95.6%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 88.6%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 1233 against 1196.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3 Flash Preview
Gemini 3.1 Pro Preview $0.0080, Gemini 3 Flash Preview $0.0020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3 Flash Preview
Gemini 3.1 Pro Preview $0.99, Gemini 3 Flash Preview $0.37.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3.1 Pro Preview 32.3 from 4 benchmarks, Gemini 3 Flash Preview 43.7 from 2 benchmarks.
- Widest category
- Reasoning, 12.3 points apart on average over 10 shared benchmarks.
- Widest single gap
- ARC-AGI-2: Gemini 3.1 Pro Preview 77.1% against Gemini 3 Flash Preview 33.6%, 43.5 points apart on a 0 to 100 scale.
- Output price
- Gemini 3.1 Pro Preview $12.00 against Gemini 3 Flash Preview $3.00 per million output tokens, 4.0x 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.
| Category | Gemini 3.1 Pro Preview | Bars | Gemini 3 Flash Preview | Ties |
|---|---|---|---|---|
| Coding | 10 | 1 | 1 tie | |
| Intelligence | 1 | 0 | ||
| Agentic work | 10 | 4 | ||
| Reasoning | 10 | 0 | ||
| Math | 5 | 0 | ||
| Knowledge | 8 | 2 | ||
| Web design | 4 | 0 | ||
| General | 5 | 2 | ||
| All shared boards | 53 | 9 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index101
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 75.8% | Only Gemini 3 Flash Preview measured |
| LMArena WebDev | 1447 | Not measured | Only Gemini 3.1 Pro Preview measured |
| AA Coding Index | 68.8 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LiveCodeBench (Vals AI) | 88.5% | 85.6% | Gemini 3.1 Pro Preview |
| SWE-bench Verified (Vals AI) | 78.8% | 75.0% | Gemini 3.1 Pro Preview |
| Terminal-Bench 4 (Vals AI) | 2.5% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vibe Code Bench (Vals AI) | 32.0% | 20.2% | Gemini 3.1 Pro Preview |
| Code migration (Vals AI) | 17.3% | 6.4% | Gemini 3.1 Pro Preview |
| ProgramBench (Vals AI) | 0.0% | 0.0% | Tie |
| IOI (Vals AI) | 51.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench 2.1 (Vals AI) | 70.8% | 53.9% | Gemini 3.1 Pro Preview |
| Vibe Code Bench 1-100 (Vals AI) | 6.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 90.8% | Only Gemini 3 Flash Preview measured |
| SciCode | 58.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench Hard (Artificial Analysis run) | 53.8% | 38.6% | Gemini 3.1 Pro Preview |
| Terminal-Bench | 80.2% | 64.3% | Gemini 3.1 Pro Preview |
| GSO-Bench | 22.6% | 9.8% | Gemini 3.1 Pro Preview |
| WeirdML | 72.1% | 61.6% | Gemini 3.1 Pro Preview |
| MirrorCode | 8.9% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ALE-Bench | 1160.6 | 1367.2 | Gemini 3 Flash Preview |
| LMArena Text: coding | 1484 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: software and IT | 1487 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena WebDev: React | 1438 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena WebDev: HTML | 1490 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena WebDev: from an image | 1481 | Not measured | Only Gemini 3.1 Pro Preview measured |
| SciCode | 14.3% | 12.7% | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 13 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.7 | 26.3 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index104
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 8.2 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building web apps | 1125 | 1111 | Gemini 3.1 Pro Preview |
| Design Arena: agents building full-stack apps | 1068 | 1063 | Gemini 3.1 Pro Preview |
| Design Arena: agents building mobile apps | 1094 | 1090 | Gemini 3.1 Pro Preview |
| Design Arena: agents building Android apps | 1049 | 1051 | Gemini 3 Flash Preview |
| Design Arena: agents building Godot games | 1236 | 1161 | Gemini 3.1 Pro Preview |
| Design Arena: agents building games | 1113 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: HTML slides | 1103 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: PowerPoint slides | 1041 | 1036 | Gemini 3.1 Pro Preview |
| SREBench (Vals AI) | 0.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Finance Agent (Vals AI) | 43.0% | 42.5% | Gemini 3.1 Pro Preview |
| Tax Agent Bench (Vals AI) | 9.3% | 11.8% | Gemini 3 Flash Preview |
| Legal Research Bench (Vals AI) | 20.7% | 18.3% | Gemini 3.1 Pro Preview |
| Excel Modeling Benchmark (Vals AI) | 52.6% | 26.0% | Gemini 3.1 Pro Preview |
| BioMysteryBench (Vals AI) | 60.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench-Science (Vals AI) | 1.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vals Science Index | 27.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| τ²-Bench Telecom | 95.6% | 80.4% | Gemini 3.1 Pro Preview |
| APEX-Agents | 35.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| METR time horizons | 77.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| BALROG | 57.0% | 48.1% | Gemini 3.1 Pro Preview |
| DeepResearch Bench | 47.8% | 49.8% | Gemini 3 Flash Preview |
| PostTrainBench | 22.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vending-Bench 2 | $911 | $3,635 | Gemini 3 Flash Preview |
| Neither model has a result on the other 17 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| GPQA Diamond | 95.5% | 87.9% | Gemini 3.1 Pro Preview |
| MysteryMechanism (Vals AI) | 20.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MMMU Pro (Vals AI) | 88.2% | 87.6% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Artificial Analysis run) | 94.1% | 89.8% | Gemini 3.1 Pro Preview |
| Humanity's Last Exam (Artificial Analysis run) | 47.0% | 36.6% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Epoch AI run) | 94.4% | 89.4% | Gemini 3.1 Pro Preview |
| ARC-AGI | 98.0% | 84.7% | Gemini 3.1 Pro Preview |
| ARC-AGI-2 | 77.1% | 33.6% | Gemini 3.1 Pro Preview |
| SimpleBench | 79.6% | 61.1% | Gemini 3.1 Pro Preview |
| Chess puzzles | 51.0% | 39.0% | Gemini 3.1 Pro Preview |
| Mystery game puzzles | 34.0% | 26.0% | Gemini 3.1 Pro Preview |
| EBR-bench | 14.3% | Not measured | Only Gemini 3.1 Pro Preview measured |
| VPCT | Not measured | 72.6% | Only Gemini 3 Flash Preview measured |
| LMArena Text: hard prompts | 1485 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: expert | 1483 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts in English | 1480 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: diagrams | 1311 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: homework | 1316 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AIME | 98.1% | 95.6% | Gemini 3.1 Pro Preview |
| MGSM (Vals AI) | Not measured | 93.3% | Only Gemini 3 Flash Preview measured |
| AA Math Index | Not measured | 97.0 | Only Gemini 3 Flash Preview measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 97.0% | Only Gemini 3 Flash Preview measured |
| OTIS Mock AIME | 95.6% | 95.6% | Gemini 3.1 Pro Preview |
| FrontierMath, tiers 1 to 3 | 59.6% | 51.2% | Gemini 3.1 Pro Preview |
| FrontierMath, tier 4 | 26.8% | 17.1% | Gemini 3.1 Pro Preview |
| ProofBench | 26.0% | 15.0% | Gemini 3.1 Pro Preview |
| LMArena Text: math | 1486 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: mathematical work | 1478 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| MMLU Pro | 91.0% | 88.6% | Gemini 3.1 Pro Preview |
| LegalBench (Vals AI) | 87.4% | 86.9% | Gemini 3.1 Pro Preview |
| CaseLaw (Vals AI) | 64.8% | 55.8% | Gemini 3.1 Pro Preview |
| CorpFin (Vals AI) | 64.5% | 66.4% | Gemini 3 Flash Preview |
| TaxEval (Vals AI) | 72.9% | 73.9% | Gemini 3 Flash Preview |
| MortgageTax (Vals AI) | 69.4% | 68.7% | Gemini 3.1 Pro Preview |
| MedQA (Vals AI) | 96.4% | 95.8% | Gemini 3.1 Pro Preview |
| MedCode (Vals AI) | 59.1% | 55.9% | Gemini 3.1 Pro Preview |
| MMLU Pro (Artificial Analysis run) | Not measured | 89.0% | Only Gemini 3 Flash Preview measured |
| SimpleQA Verified | 73.5% | 66.8% | Gemini 3.1 Pro Preview |
| GeoBench | Not measured | 88.0% | Only Gemini 3 Flash Preview measured |
| LMArena Text: science | 1497 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: medicine and healthcare | 1486 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: legal and government | 1487 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: business and finance | 1459 | Not measured | Only Gemini 3.1 Pro Preview measured |
| FACTS Benchmark Suite | 67.4% | 63.4% | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1233 | 1196 | Gemini 3.1 Pro Preview |
| Design Arena: UI components | 1224 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: game dev | 1202 | 1166 | Gemini 3.1 Pro Preview |
| Design Arena: data viz | 1209 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: 3D | 1234 | 1183 | Gemini 3.1 Pro Preview |
| Design Arena: all code categories | 1231 | 1189 | Gemini 3.1 Pro Preview |
| Design Arena: SVG | 1285 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Design Arena: ASCII art | 1270 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index52
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 53.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| SAGE (Vals AI) | 48.7% | 51.8% | Gemini 3 Flash Preview |
| MedScribe (Vals AI) | 76.1% | 69.9% | Gemini 3.1 Pro Preview |
| Vals Multimodal Index | 56.1% | 52.2% | Gemini 3.1 Pro Preview |
| IFBench | 77.1% | 78.0% | Gemini 3 Flash Preview |
| Long context reasoning (AA-LCR) | 82.0% | 78.0% | Gemini 3.1 Pro Preview |
| DTBench | 97.1% | 89.1% | Gemini 3.1 Pro Preview |
| LMCA | 53.8% | 43.1% | Gemini 3.1 Pro Preview |
| CL-bench | 20.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Furniture assembly | 26.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ExploitBench | 26.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| CL-bench Life | 16.9% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text | 1480 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: instruction following | 1466 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: creative writing | 1482 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision | 1296 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: English | 1478 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: non-English | 1476 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Chinese | 1527 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: German | 1490 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Japanese | 1491 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Korean | 1455 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: French | 1487 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Spanish | 1481 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Russian | 1497 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Polish | 1498 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: multi-turn | 1487 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: longer queries | 1482 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: writing and language | 1481 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: entertainment and media | 1465 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: English | 1287 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: Chinese | 1364 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: reading text | 1304 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: humor | 1322 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: captioning | 1345 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: recognizing things | 1330 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: creative writing | 1324 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Document | 1444 | Not measured | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 8 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3.1 Pro Preview | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| 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 3 Flash Preview$0.0020Fits in one request
Gemini 3 Flash Preview costs less
Repository review
50K input + 3K output tokens
Gemini 3.1 Pro Preview$0.136Fits in one request
Gemini 3 Flash Preview$0.034Fits in one request
Gemini 3 Flash Preview costs less
Agent loop
200K input + 10K output tokens
Gemini 3.1 Pro Preview$0.520Fits in one request
Gemini 3 Flash Preview$0.130Fits in one request
Gemini 3 Flash 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.
| Specification | Google Gemini 3.1 Pro Preview | Google Gemini 3 Flash Preview |
|---|---|---|
| Maker | ||
| Weights | No public weights listed | No public weights listed |
| Released | February 19, 2026 | December 17, 2025 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $2.00 | $0.50 |
| Output $/Mtok | $12.00 | $3.00 |
| Coding index | 32.3 | 43.7 |
| Independent measurements behind it | 4 | 2 |
| Cost per solved task | $0.99 | $0.37 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3.1 Pro Preview better than Gemini 3 Flash Preview for coding?
Pick Gemini 3 Flash Preview for coding: it scores 43.7 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview, though on 2 benchmarks against 4. Pick Gemini 3.1 Pro Preview for work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.
Which is cheaper, Gemini 3.1 Pro Preview or Gemini 3 Flash Preview?
Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; Gemini 3 Flash Preview costs $0.50 and $3.00. Per solved SWE-bench Verified task, Gemini 3.1 Pro Preview costs $0.99 and Gemini 3 Flash Preview $0.37.
Which has the bigger context window, Gemini 3.1 Pro Preview or Gemini 3 Flash Preview?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 3.1 Pro Preview vs Gemini 3 Flash Preview comparison based on?
63 benchmarks have a result for both models as of October 22, 2026. Gemini 3.1 Pro Preview's coding index rests on 4 independent benchmarks and Gemini 3 Flash Preview's on 2. Where only one model has a result, the page says so instead of naming a winner.