DeepSeek V4.1 Flash 1017 vs Gemini 3.1 Pro Preview
DeepSeek V4.1 Flash 1017 leads Gemini 3.1 Pro Preview on coding, 70.3 to 32.3 on the Vibe Coding Index, and DeepSeek V4.1 Flash 1017 costs 20.0x less per output token ($0.60 vs $12.00 per million). Updated October 22, 2026; 29 benchmarks have a result for both.
vs boards won of 29 shared
DeepSeek V4.1 Flash 1017 or Gemini 3.1 Pro Preview: which to pick
Pick DeepSeek V4.1 Flash 1017 for coding: it scores 70.3 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview.
Pick Gemini 3.1 Pro Preview for work measured by SciCode or Humanity's Last Exam (Artificial Analysis run), where it leads.
Model ADeepSeek V4.1 Flash 1017DeepSeek70.3/1004 independent benchmarksNo cost per solved taskModel BGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved task
- Shared results
- 29
- DeepSeek V4.1 Flash 1017 only
- 10
- Gemini 3.1 Pro Preview only
- 104
- 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
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 scores 70.3 against 32.3.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 leads, 39.5 against 29.7.
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
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
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 leads, 1311 against 1233.
Same board, both measured
General
Vals Index
No call
Only DeepSeek V4.1 Flash 1017 has a Vals Index result, 61.3%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 $0.0004, Gemini 3.1 Pro Preview $0.0080 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Gemini 3.1 Pro Preview has the number, $0.99.
Directional only
At a glance
- Coding index
- DeepSeek V4.1 Flash 1017 70.3 from 4 benchmarks, Gemini 3.1 Pro Preview 32.3 from 4 benchmarks.
- Widest category
- Knowledge, 31.0 points apart on average over 1 shared benchmark.
- Widest single gap
- Vibe Code Bench (Vals AI): DeepSeek V4.1 Flash 1017 87.7% against Gemini 3.1 Pro Preview 32.0%, 55.7 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4.1 Flash 1017 $0.60 against Gemini 3.1 Pro Preview $12.00 per million output tokens, 20.0x 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 | DeepSeek V4.1 Flash 1017 | Bars | Gemini 3.1 Pro Preview | Ties |
|---|---|---|---|---|
| Coding | 7 | 1 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 4 | 0 | ||
| Reasoning | 1 | 3 | ||
| Math | 3 | 0 | ||
| Knowledge | 0 | 1 | ||
| Web design | 6 | 1 | ||
| General | 1 | 0 | ||
| All shared boards | 23 | 6 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index71
| Benchmark | DeepSeek V4.1 Flash 1017 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| LiveBench coding | 96.0% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LMArena WebDev | 1664 | 1447 | DeepSeek V4.1 Flash 1017 |
| AA Coding Index | Not measured | 68.8 | Only Gemini 3.1 Pro Preview measured |
| LiveCodeBench (Vals AI) | Not measured | 88.5% | Only Gemini 3.1 Pro Preview measured |
| SWE-bench Verified (Vals AI) | Not measured | 78.8% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench 4 (Vals AI) | 31.8% | 2.5% | DeepSeek V4.1 Flash 1017 |
| Vibe Code Bench (Vals AI) | 87.7% | 32.0% | DeepSeek V4.1 Flash 1017 |
| Code migration (Vals AI) | 44.2% | 17.3% | DeepSeek V4.1 Flash 1017 |
| 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 |
| SciCode | 55.9% | 58.7% | Gemini 3.1 Pro Preview |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 53.8% | Only Gemini 3.1 Pro Preview measured |
| Terminal-Bench | Not measured | 80.2% | Only Gemini 3.1 Pro Preview measured |
| GSO-Bench | Not measured | 22.6% | Only Gemini 3.1 Pro Preview measured |
| WeirdML | Not measured | 72.1% | Only Gemini 3.1 Pro Preview measured |
| MirrorCode | Not measured | 8.9% | Only Gemini 3.1 Pro Preview measured |
| ALE-Bench | 1622.0 | 1160.6 | DeepSeek V4.1 Flash 1017 |
| LMArena Text: coding | Not measured | 1484 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: software and IT | Not measured | 1487 | Only Gemini 3.1 Pro Preview measured |
| LMArena WebDev: React | 1667 | 1438 | DeepSeek V4.1 Flash 1017 |
| LMArena WebDev: HTML | 1687 | 1490 | DeepSeek V4.1 Flash 1017 |
| LMArena WebDev: from an image | Not measured | 1481 | Only Gemini 3.1 Pro Preview measured |
| SciCode | Not measured | 14.3% | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4.1 Flash 1017 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 39.5 | 29.7 | DeepSeek V4.1 Flash 1017 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4.1 Flash 1017 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 8.2 | Only Gemini 3.1 Pro Preview measured |
| 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 |
| Design Arena: spreadsheets | 1245 | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench research | 79.5% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench browser | 76.0% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench long agentic | 50.9% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| SREBench (Vals AI) | Not measured | 0.0% | Only Gemini 3.1 Pro Preview measured |
| Finance Agent (Vals AI) | 57.0% | 43.0% | DeepSeek V4.1 Flash 1017 |
| Tax Agent Bench (Vals AI) | 44.4% | 9.3% | DeepSeek V4.1 Flash 1017 |
| Legal Research Bench (Vals AI) | 45.2% | 20.7% | DeepSeek V4.1 Flash 1017 |
| Harvey's Legal Agent Benchmark (Vals AI) | 14.2% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Excel Modeling Benchmark (Vals AI) | 61.8% | 52.6% | DeepSeek V4.1 Flash 1017 |
| 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 | Not measured | 95.6% | Only Gemini 3.1 Pro Preview measured |
| 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 |
| BALROG | Not measured | 57.0% | Only Gemini 3.1 Pro Preview measured |
| DeepResearch Bench | Not measured | 47.8% | Only Gemini 3.1 Pro Preview measured |
| PostTrainBench | Not measured | 22.0% | Only Gemini 3.1 Pro Preview measured |
| Vending-Bench 2 | Not measured | $911 | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 12 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | DeepSeek V4.1 Flash 1017 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 95.5% | Only Gemini 3.1 Pro Preview measured |
| LiveBench reasoning | 89.1% | Not measured | Only DeepSeek V4.1 Flash 1017 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) | Not measured | 94.1% | Only Gemini 3.1 Pro Preview measured |
| Humanity's Last Exam (Artificial Analysis run) | 43.3% | 47.0% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Epoch AI run) | 93.2% | 94.4% | Gemini 3.1 Pro Preview |
| ARC-AGI | Not measured | 98.0% | Only Gemini 3.1 Pro Preview measured |
| ARC-AGI-2 | Not measured | 77.1% | Only Gemini 3.1 Pro Preview measured |
| SimpleBench | Not measured | 79.6% | Only Gemini 3.1 Pro Preview measured |
| Chess puzzles | 46.0% | 51.0% | Gemini 3.1 Pro Preview |
| Mystery game puzzles | 49.0% | 34.0% | DeepSeek V4.1 Flash 1017 |
| EBR-bench | Not measured | 14.3% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts | Not measured | 1485 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: expert | Not measured | 1483 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts in English | Not measured | 1480 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: diagrams | Not measured | 1311 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: homework | Not measured | 1316 | 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 index30
| Benchmark | DeepSeek V4.1 Flash 1017 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| AIME | Not measured | 98.1% | Only Gemini 3.1 Pro Preview measured |
| OTIS Mock AIME | 99.4% | 95.6% | DeepSeek V4.1 Flash 1017 |
| FrontierMath, tiers 1 to 3 | 71.2% | 59.6% | DeepSeek V4.1 Flash 1017 |
| FrontierMath, tier 4 | 46.3% | 26.8% | DeepSeek V4.1 Flash 1017 |
| ProofBench | Not measured | 26.0% | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: math | Not measured | 1486 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: mathematical work | Not measured | 1478 | Only 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 index01
| Benchmark | DeepSeek V4.1 Flash 1017 | 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) | Not measured | 64.8% | Only Gemini 3.1 Pro Preview measured |
| CorpFin (Vals AI) | Not measured | 64.5% | Only Gemini 3.1 Pro Preview measured |
| TaxEval (Vals AI) | Not measured | 72.9% | Only Gemini 3.1 Pro Preview measured |
| MortgageTax (Vals AI) | Not measured | 69.4% | Only Gemini 3.1 Pro Preview measured |
| MedQA (Vals AI) | Not measured | 96.4% | Only Gemini 3.1 Pro Preview measured |
| MedCode (Vals AI) | Not measured | 59.1% | Only Gemini 3.1 Pro Preview measured |
| SimpleQA Verified | 42.5% | 73.5% | Gemini 3.1 Pro Preview |
| LMArena Text: science | Not measured | 1497 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: medicine and healthcare | Not measured | 1486 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: legal and government | Not measured | 1487 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: business and finance | Not measured | 1459 | Only Gemini 3.1 Pro Preview measured |
| FACTS Benchmark Suite | Not measured | 67.4% | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index61
| Benchmark | DeepSeek V4.1 Flash 1017 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1311 | 1233 | DeepSeek V4.1 Flash 1017 |
| Design Arena: UI components | 1303 | 1224 | DeepSeek V4.1 Flash 1017 |
| Design Arena: game dev | 1357 | 1202 | DeepSeek V4.1 Flash 1017 |
| Design Arena: data viz | 1330 | 1209 | DeepSeek V4.1 Flash 1017 |
| Design Arena: 3D | 1358 | 1234 | DeepSeek V4.1 Flash 1017 |
| Design Arena: all code categories | 1332 | 1231 | DeepSeek V4.1 Flash 1017 |
| Design Arena: SVG | Not measured | 1285 | Only Gemini 3.1 Pro Preview measured |
| Design Arena: ASCII art | 1242 | 1270 | Gemini 3.1 Pro Preview |
| LiveBench design | 83.4% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4.1 Flash 1017 | Gemini 3.1 Pro Preview | Leader |
|---|---|---|---|
| Vals Index | 61.3% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| LiveBench data analysis | 79.5% | Not measured | Only DeepSeek V4.1 Flash 1017 measured |
| Public Benefits Bench (Vals AI) | Not measured | 53.8% | Only Gemini 3.1 Pro Preview measured |
| SAGE (Vals AI) | Not measured | 48.7% | Only Gemini 3.1 Pro Preview measured |
| MedScribe (Vals AI) | Not measured | 76.1% | Only Gemini 3.1 Pro Preview measured |
| Vals Multimodal Index | Not measured | 56.1% | Only Gemini 3.1 Pro Preview measured |
| IFBench | Not measured | 77.1% | Only Gemini 3.1 Pro Preview measured |
| Long context reasoning (AA-LCR) | 82.7% | 82.0% | DeepSeek V4.1 Flash 1017 |
| DTBench | Not measured | 97.1% | Only Gemini 3.1 Pro Preview measured |
| LMCA | Not measured | 53.8% | Only Gemini 3.1 Pro Preview 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 | Not measured | 1480 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: instruction following | Not measured | 1466 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: creative writing | Not measured | 1482 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision | Not measured | 1296 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: English | Not measured | 1478 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: non-English | Not measured | 1476 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Chinese | Not measured | 1527 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: German | Not measured | 1490 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Japanese | Not measured | 1491 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Korean | Not measured | 1455 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: French | Not measured | 1487 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Spanish | Not measured | 1481 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Russian | Not measured | 1497 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: Polish | Not measured | 1498 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: multi-turn | Not measured | 1487 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: longer queries | Not measured | 1482 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: writing and language | Not measured | 1481 | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: entertainment and media | Not measured | 1465 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: English | Not measured | 1287 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: Chinese | Not measured | 1364 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: reading text | Not measured | 1304 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: humor | Not measured | 1322 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: captioning | Not measured | 1345 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: recognizing things | Not measured | 1330 | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: creative writing | Not measured | 1324 | Only Gemini 3.1 Pro Preview measured |
| LMArena Document | Not measured | 1444 | Only Gemini 3.1 Pro Preview measured |
| Neither model has a result on the other 6 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4.1 Flash 1017 | 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
DeepSeek V4.1 Flash 1017$0.0004Fits in one request
Gemini 3.1 Pro Preview$0.0080Fits in one request
DeepSeek V4.1 Flash 1017 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4.1 Flash 1017$0.0093Fits in one request
Gemini 3.1 Pro Preview$0.136Fits in one request
DeepSeek V4.1 Flash 1017 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4.1 Flash 1017$0.036Fits in one request
Gemini 3.1 Pro Preview$0.520Fits in one request
DeepSeek V4.1 Flash 1017 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 | DeepSeek V4.1 Flash 1017 | Google Gemini 3.1 Pro Preview |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | No public weights listed |
| Released | October 17, 2026 | February 19, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.15 | $2.00 |
| Output $/Mtok | $0.60 | $12.00 |
| Coding index | 70.3 | 32.3 |
| Independent measurements behind it | 4 | 4 |
| Cost per solved task | Not computable | $0.99 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4.1 Flash 1017 better than Gemini 3.1 Pro Preview for coding?
Pick DeepSeek V4.1 Flash 1017 for coding: it scores 70.3 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview for work measured by SciCode or Humanity's Last Exam (Artificial Analysis run), where it leads.
Which is cheaper, DeepSeek V4.1 Flash 1017 or Gemini 3.1 Pro Preview?
DeepSeek V4.1 Flash 1017 costs $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3.1 Pro Preview costs $2.00 and $12.00. Cost per solved task is known for Gemini 3.1 Pro Preview only.
Which has the bigger context window, DeepSeek V4.1 Flash 1017 or Gemini 3.1 Pro Preview?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4.1 Flash 1017 vs Gemini 3.1 Pro Preview comparison based on?
29 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4.1 Flash 1017's coding index rests on 4 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.