Gemini 2.5 Pro vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads Gemini 2.5 Pro on coding, 32.3 to 19.1 on the Vibe Coding Index, and Gemini 2.5 Pro costs 1.2x less per output token ($10.00 vs $12.00 per million). Updated October 22, 2026; 80 benchmarks have a result for both.
vs boards won of 80 shared
Gemini 2.5 Pro or Gemini 3.1 Pro Preview: which to pick
Pick Gemini 3.1 Pro Preview for coding: it scores 32.3 on the Vibe Coding Index against 19.1 for Gemini 2.5 Pro.
Pick Gemini 2.5 Pro for output tokens 1.2x cheaper ($10.00 vs $12.00 per million) and a lower cost per solved task ($0.64 against $0.99).
Model AGemini 2.5 ProGoogle19.1/1003 independent benchmarks$0.64 per solved taskModel BGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved task
- Shared results
- 80
- Gemini 2.5 Pro only
- 10
- Gemini 3.1 Pro Preview only
- 53
- 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 3.1 Pro Preview
Gemini 3.1 Pro Preview scores 32.3 against 19.1.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 29.7 against 16.1.
Same board, both measured
Agentic work
AA Agentic Index
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 8.2 against 1.6.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Gemini 3.1 Pro Preview has a GPQA Diamond result, 95.5%.
Directional only
Math
AIME
No call
Only Gemini 3.1 Pro Preview has a AIME result, 98.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Gemini 3.1 Pro Preview has a MMLU Pro result, 91.0%.
Directional only
Web design
Design Arena: websites
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 1233 against 1167.
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 2.5 Pro
Gemini 2.5 Pro $0.0063, Gemini 3.1 Pro Preview $0.0080 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 2.5 Pro
Gemini 2.5 Pro $0.64, Gemini 3.1 Pro Preview $0.99.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 2.5 Pro 19.1 from 3 benchmarks, Gemini 3.1 Pro Preview 32.3 from 4 benchmarks.
- Widest category
- Coding, 25.5 points apart on average over 13 shared benchmarks.
- Widest single gap
- ARC-AGI-2: Gemini 2.5 Pro 4.9% against Gemini 3.1 Pro Preview 77.1%, 72.2 points apart on a 0 to 100 scale.
- Output price
- Gemini 2.5 Pro $10.00 against Gemini 3.1 Pro Preview $12.00 per million output tokens, 1.2x 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 2.5 Pro | Bars | Gemini 3.1 Pro Preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 13 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 4 | ||
| Reasoning | 0 | 10 | ||
| Math | 0 | 5 | ||
| Knowledge | 0 | 9 | ||
| Web design | 1 | 5 | ||
| General | 0 | 32 | ||
| All shared boards | 1 | 79 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index013
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| SWE-bench Verified | 53.6% | Not measured | Only Gemini 2.5 Pro measured |
| LMArena WebDev | 1226 | 1447 | Gemini 3.1 Pro Preview |
| AA Coding Index | 33.3 | 68.8 | Gemini 3.1 Pro Preview |
| LiveCodeBench (Vals AI) | Not measured | 88.5% | Only Gemini 3.1 Pro Preview measured |
| SWE-bench Verified (Vals AI) | 54.4% | 78.8% | Gemini 3.1 Pro Preview |
| Terminal-Bench 4 (Vals AI) | Not measured | 2.5% | Only Gemini 3.1 Pro Preview measured |
| Vibe Code Bench (Vals AI) | 0.4% | 32.0% | Gemini 3.1 Pro Preview |
| Code migration (Vals AI) | Not measured | 17.3% | Only Gemini 3.1 Pro Preview measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Gemini 3.1 Pro Preview measured |
| IOI (Vals AI) | Not measured | 51.8% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 70.8% | Only Gemini 3.1 Pro Preview measured |
| Vibe Code Bench 1-100 (Vals AI) | Not measured | 6.7% | Only Gemini 3.1 Pro Preview measured |
| LiveCodeBench (Artificial Analysis run) | 80.1% | Not measured | Only Gemini 2.5 Pro measured |
| SciCode | 46.3% | 58.7% | Gemini 3.1 Pro Preview |
| Terminal-Bench Hard (Artificial Analysis run) | 26.5% | 53.8% | Gemini 3.1 Pro Preview |
| Terminal-Bench | 32.6% | 80.2% | Gemini 3.1 Pro Preview |
| GSO-Bench | 3.9% | 22.6% | Gemini 3.1 Pro Preview |
| WeirdML | 54.0% | 72.1% | Gemini 3.1 Pro Preview |
| MirrorCode | Not measured | 8.9% | Only Gemini 3.1 Pro Preview measured |
| ALE-Bench | Not measured | 1160.6 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: coding | 1452 | 1484 | Gemini 3.1 Pro Preview |
| LMArena Text: software and IT | 1459 | 1487 | Gemini 3.1 Pro Preview |
| LMArena WebDev: React | Not measured | 1438 | Only Gemini 3.1 Pro Preview measured |
| LMArena WebDev: HTML | 1235 | 1490 | Gemini 3.1 Pro Preview |
| LMArena WebDev: from an image | 1285 | 1481 | Gemini 3.1 Pro Preview |
| SciCode | Not measured | 14.3% | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 13 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.1 | 29.7 | Gemini 3.1 Pro Preview |
| Epoch Capabilities Index | 145.1 | Not measured | Only Gemini 2.5 Pro measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 1.6 | 8.2 | Gemini 3.1 Pro Preview |
| Design Arena: agents building web apps | Not measured | 1125 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building full-stack apps | Not measured | 1068 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building mobile apps | Not measured | 1094 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building Android apps | Not measured | 1049 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building Godot games | Not measured | 1236 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: agents building games | Not measured | 1113 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: HTML slides | Not measured | 1103 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: PowerPoint slides | Not measured | 1041 | Only Gemini 3.1 Pro Preview measured |
| SREBench (Vals AI) | Not measured | 0.0% | Only Gemini 3.1 Pro Preview measured |
| Finance Agent (Vals AI) | Not measured | 43.0% | Only Gemini 3.1 Pro Preview measured |
| Tax Agent Bench (Vals AI) | Not measured | 9.3% | Only Gemini 3.1 Pro Preview measured |
| Legal Research Bench (Vals AI) | Not measured | 20.7% | Only Gemini 3.1 Pro Preview measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 52.6% | Only Gemini 3.1 Pro Preview measured |
| BioMysteryBench (Vals AI) | Not measured | 60.0% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 1.4% | Only Gemini 3.1 Pro Preview measured |
| Vals Science Index | Not measured | 27.4% | Only Gemini 3.1 Pro Preview measured |
| τ²-Bench Telecom | 54.1% | 95.6% | Gemini 3.1 Pro Preview |
| APEX-Agents | Not measured | 35.1% | Only Gemini 3.1 Pro Preview measured |
| METR time horizons | Not measured | 77.0% | Only Gemini 3.1 Pro Preview measured |
| GDPval | 23.3% | Not measured | Only Gemini 2.5 Pro measured |
| BALROG | Not measured | 57.0% | Only Gemini 3.1 Pro Preview measured |
| DeepResearch Bench | 41.5% | 47.8% | Gemini 3.1 Pro Preview |
| PostTrainBench | Not measured | 22.0% | Only Gemini 3.1 Pro Preview measured |
| Vending-Bench 2 | $574 | $911 | Gemini 3.1 Pro Preview |
| BrowseComp-Plus | 29.5% | Not measured | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 15 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index010
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 95.5% | Only Gemini 3.1 Pro Preview measured |
| MysteryMechanism (Vals AI) | Not measured | 20.7% | Only Gemini 3.1 Pro Preview measured |
| MMMU Pro (Vals AI) | Not measured | 88.2% | Only Gemini 3.1 Pro Preview measured |
| GPQA Diamond (Artificial Analysis run) | 84.4% | 94.1% | Gemini 3.1 Pro Preview |
| Humanity's Last Exam (Artificial Analysis run) | 22.5% | 47.0% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Epoch AI run) | 85.3% | 94.4% | Gemini 3.1 Pro Preview |
| ARC-AGI | 41.0% | 98.0% | Gemini 3.1 Pro Preview |
| ARC-AGI-2 | 4.9% | 77.1% | Gemini 3.1 Pro Preview |
| SimpleBench | Not measured | 79.6% | Only Gemini 3.1 Pro Preview measured |
| Chess puzzles | Not measured | 51.0% | Only Gemini 3.1 Pro Preview measured |
| Mystery game puzzles | Not measured | 34.0% | Only Gemini 3.1 Pro Preview measured |
| EBR-bench | Not measured | 14.3% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts | 1455 | 1485 | Gemini 3.1 Pro Preview |
| LMArena Text: expert | 1452 | 1483 | Gemini 3.1 Pro Preview |
| LMArena Text: hard prompts in English | 1453 | 1480 | Gemini 3.1 Pro Preview |
| LMArena Vision: diagrams | 1274 | 1311 | Gemini 3.1 Pro Preview |
| LMArena Vision: homework | 1281 | 1316 | Gemini 3.1 Pro Preview |
| Kagi LLM Benchmark | 70.3% | Not measured | Only Gemini 2.5 Pro measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AIME | Not measured | 98.1% | Only Gemini 3.1 Pro Preview measured |
| AA Math Index | 87.7 | Not measured | Only Gemini 2.5 Pro measured |
| AIME 2025 (Artificial Analysis run) | 87.7% | Not measured | Only Gemini 2.5 Pro measured |
| OTIS Mock AIME | 84.7% | 95.6% | Gemini 3.1 Pro Preview |
| FrontierMath, tiers 1 to 3 | 24.6% | 59.6% | Gemini 3.1 Pro Preview |
| FrontierMath, tier 4 | 0.0% | 26.8% | Gemini 3.1 Pro Preview |
| ProofBench | Not measured | 26.0% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: math | 1450 | 1486 | Gemini 3.1 Pro Preview |
| LMArena Text: mathematical work | 1454 | 1478 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index09
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 91.0% | Only Gemini 3.1 Pro Preview measured |
| LegalBench (Vals AI) | Not measured | 87.4% | Only Gemini 3.1 Pro Preview measured |
| CaseLaw (Vals AI) | 63.9% | 64.8% | Gemini 3.1 Pro Preview |
| CorpFin (Vals AI) | 60.8% | 64.5% | Gemini 3.1 Pro Preview |
| TaxEval (Vals AI) | Not measured | 72.9% | Only Gemini 3.1 Pro Preview measured |
| MortgageTax (Vals AI) | 68.9% | 69.4% | Gemini 3.1 Pro Preview |
| MedQA (Vals AI) | Not measured | 96.4% | Only Gemini 3.1 Pro Preview measured |
| MedCode (Vals AI) | 50.6% | 59.1% | Gemini 3.1 Pro Preview |
| MMLU Pro (Artificial Analysis run) | 86.2% | Not measured | Only Gemini 2.5 Pro measured |
| SimpleQA Verified | Not measured | 73.5% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: science | 1480 | 1497 | Gemini 3.1 Pro Preview |
| LMArena Text: medicine and healthcare | 1476 | 1486 | Gemini 3.1 Pro Preview |
| LMArena Text: legal and government | 1480 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: business and finance | 1439 | 1459 | Gemini 3.1 Pro Preview |
| FACTS Benchmark Suite | 61.5% | 67.4% | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index15
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1167 | 1233 | Gemini 3.1 Pro Preview |
| Design Arena: UI components | 1137 | 1224 | Gemini 3.1 Pro Preview |
| Design Arena: game dev | 1111 | 1202 | Gemini 3.1 Pro Preview |
| Design Arena: data viz | 1222 | 1209 | Gemini 2.5 Pro |
| Design Arena: 3D | 1080 | 1234 | Gemini 3.1 Pro Preview |
| Design Arena: all code categories | 1152 | 1231 | Gemini 3.1 Pro Preview |
| Design Arena: SVG | Not measured | 1285 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: ASCII art | Not measured | 1270 | 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 index032
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | Not measured | 53.8% | Only Gemini 3.1 Pro Preview measured |
| SAGE (Vals AI) | 41.9% | 48.7% | Gemini 3.1 Pro Preview |
| MedScribe (Vals AI) | 73.5% | 76.1% | Gemini 3.1 Pro Preview |
| Vals Multimodal Index | Not measured | 56.1% | Only Gemini 3.1 Pro Preview measured |
| IFBench | 48.7% | 77.1% | Gemini 3.1 Pro Preview |
| Long context reasoning (AA-LCR) | 69.0% | 82.0% | Gemini 3.1 Pro Preview |
| DTBench | 82.4% | 97.1% | Gemini 3.1 Pro Preview |
| LMCA | 34.8% | 53.8% | Gemini 3.1 Pro Preview |
| Creative writing (Lech Mazur) | 83.8% | Not measured | Only Gemini 2.5 Pro measured |
| CL-bench | Not measured | 20.8% | Only Gemini 3.1 Pro Preview measured |
| Furniture assembly | Not measured | 26.7% | Only Gemini 3.1 Pro Preview measured |
| ExploitBench | Not measured | 26.1% | Only Gemini 3.1 Pro Preview measured |
| CL-bench Life | Not measured | 16.9% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text | 1458 | 1480 | Gemini 3.1 Pro Preview |
| LMArena Text: instruction following | 1437 | 1466 | Gemini 3.1 Pro Preview |
| LMArena Text: creative writing | 1454 | 1482 | Gemini 3.1 Pro Preview |
| LMArena Vision | 1263 | 1296 | Gemini 3.1 Pro Preview |
| LMArena Text: English | 1458 | 1478 | Gemini 3.1 Pro Preview |
| LMArena Text: non-English | 1452 | 1476 | Gemini 3.1 Pro Preview |
| LMArena Text: Chinese | 1507 | 1527 | Gemini 3.1 Pro Preview |
| LMArena Text: German | 1487 | 1490 | Gemini 3.1 Pro Preview |
| LMArena Text: Japanese | 1461 | 1491 | Gemini 3.1 Pro Preview |
| LMArena Text: Korean | 1434 | 1455 | Gemini 3.1 Pro Preview |
| LMArena Text: French | 1473 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: Spanish | 1474 | 1481 | Gemini 3.1 Pro Preview |
| LMArena Text: Russian | 1461 | 1497 | Gemini 3.1 Pro Preview |
| LMArena Text: Polish | 1479 | 1498 | Gemini 3.1 Pro Preview |
| LMArena Text: multi-turn | 1453 | 1487 | Gemini 3.1 Pro Preview |
| LMArena Text: longer queries | 1449 | 1482 | Gemini 3.1 Pro Preview |
| LMArena Text: writing and language | 1454 | 1481 | Gemini 3.1 Pro Preview |
| LMArena Text: entertainment and media | 1441 | 1465 | Gemini 3.1 Pro Preview |
| LMArena Vision: English | 1261 | 1287 | Gemini 3.1 Pro Preview |
| LMArena Vision: Chinese | 1300 | 1364 | Gemini 3.1 Pro Preview |
| LMArena Vision: reading text | 1270 | 1304 | Gemini 3.1 Pro Preview |
| LMArena Vision: humor | 1262 | 1322 | Gemini 3.1 Pro Preview |
| LMArena Vision: captioning | 1304 | 1345 | Gemini 3.1 Pro Preview |
| LMArena Vision: recognizing things | 1283 | 1330 | Gemini 3.1 Pro Preview |
| LMArena Vision: creative writing | 1265 | 1324 | Gemini 3.1 Pro Preview |
| LMArena Document | 1421 | 1444 | Gemini 3.1 Pro Preview |
| 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
| Benchmark | Gemini 2.5 Pro | Gemini 3.1 Pro 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 2.5 Pro$0.0063Fits in one request
Gemini 3.1 Pro Preview$0.0080Fits in one request
Gemini 2.5 Pro costs less
Repository review
50K input + 3K output tokens
Gemini 2.5 Pro$0.092Fits in one request
Gemini 3.1 Pro Preview$0.136Fits in one request
Gemini 2.5 Pro costs less
Agent loop
200K input + 10K output tokens
Gemini 2.5 Pro$0.350Fits in one request
Gemini 3.1 Pro Preview$0.520Fits in one request
Gemini 2.5 Pro 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 2.5 Pro | Google Gemini 3.1 Pro Preview |
|---|---|---|
| Maker | ||
| Weights | No public weights listed | No public weights listed |
| Released | June 17, 2025 | February 19, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $1.25 | $2.00 |
| Output $/Mtok | $10.00 | $12.00 |
| Coding index | 19.1 | 32.3 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | $0.64 | $0.99 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 2.5 Pro better than Gemini 3.1 Pro Preview for coding?
Pick Gemini 3.1 Pro Preview for coding: it scores 32.3 on the Vibe Coding Index against 19.1 for Gemini 2.5 Pro. Pick Gemini 2.5 Pro for output tokens 1.2x cheaper ($10.00 vs $12.00 per million) and a lower cost per solved task ($0.64 against $0.99).
Which is cheaper, Gemini 2.5 Pro or Gemini 3.1 Pro Preview?
Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Gemini 3.1 Pro Preview costs $2.00 and $12.00. Per solved SWE-bench Verified task, Gemini 2.5 Pro costs $0.64 and Gemini 3.1 Pro Preview $0.99.
Which has the bigger context window, Gemini 2.5 Pro or Gemini 3.1 Pro Preview?
Neither: both take 1.05M tokens.
How many benchmarks is the Gemini 2.5 Pro vs Gemini 3.1 Pro Preview comparison based on?
80 benchmarks have a result for both models as of October 22, 2026. Gemini 2.5 Pro's coding index rests on 3 independent benchmarks and Gemini 3.1 Pro Preview's on 4. Where only one model has a result, the page says so instead of naming a winner.