Gemini 3.1 Pro Preview vs Grok 4.3
Updated October 21, 2026. 102 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Gemini 3.1 Pro Preview for coding: it scores 35.3 on the Vibe Coding Index against 22.5 for Grok 4.3.
Pick Grok 4.3 when output tokens cost 4.8x less, or when a solved task costs $0.31 against $0.99.
- Shared results
- 102
- Gemini 3.1 Pro Preview only
- 29
- Grok 4.3 only
- 2
- Like-for-like categories
- 8 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview scores 35.3 against 22.5.
One benchmark behind each score
Intelligence
AA Intelligence Index
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 29.7 against 24.9.
Same board, both measured
Agentic work
AA Agentic Index
Grok 4.3
Grok 4.3 leads, 15.5 against 8.2.
Same board, both measured
Reasoning
GPQA Diamond
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 91.4%.
Same board, both measured
Math
AIME
No call
Only Gemini 3.1 Pro Preview has a AIME result, 98.1%.
Directional only
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 85.8%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 1234 against 1196.
Same board, both measured
Long documents
Listed context window
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Grok 4.3
Gemini 3.1 Pro Preview $0.0080, Grok 4.3 $0.0025 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Grok 4.3
Gemini 3.1 Pro Preview $0.99, Grok 4.3 $0.31.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3.1 Pro Preview 35.3 from 1 benchmark, Grok 4.3 22.5 from 1 benchmark.
- Widest category
- Knowledge, 14.5 points apart on average over 12 shared benchmarks.
- Widest single gap
- SimpleQA Verified: Gemini 3.1 Pro Preview 73.5% against Grok 4.3 33.2%, 40.3 points apart on a 0 to 100 scale.
- Output price
- Gemini 3.1 Pro Preview $12.00 against Grok 4.3 $2.50 per million output tokens, 4.8x apart.
- Context window
- Gemini 3.1 Pro Preview takes 1.05M tokens, Grok 4.3 1M.
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 | Grok 4.3 | Ties |
|---|---|---|---|---|
| Coding | 16 | 0 | 1 tie | |
| Intelligence | 1 | 0 | ||
| Agentic work | 12 | 3 | ||
| Reasoning | 11 | 0 | ||
| Math | 6 | 0 | ||
| Knowledge | 10 | 2 | ||
| Web design | 8 | 0 | ||
| General | 31 | 1 | ||
| All shared boards | 95 | 6 | 1 tie |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index160
| Benchmark | Gemini 3.1 Pro Preview | Grok 4.3 | Leader |
|---|---|---|---|
| LMArena WebDev | 1447 | 1358 | Gemini 3.1 Pro Preview |
| AA Coding Index | 68.8 | 42.2 | Gemini 3.1 Pro Preview |
| LiveCodeBench (Vals AI) | 88.5% | 84.5% | Gemini 3.1 Pro Preview |
| SWE-bench Verified (Vals AI) | 78.8% | 71.4% | 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% | 19.4% | Gemini 3.1 Pro Preview |
| Code migration (Vals AI) | 17.3% | 6.8% | 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% | 42.0% | Gemini 3.1 Pro Preview |
| Vibe Code Bench 1-100 (Vals AI) | 6.7% | Not measured | Only Gemini 3.1 Pro Preview measured |
| SkillsBench (Vals AI) | Not measured | 40.6% | Only Grok 4.3 measured |
| SciCode | 58.7% | 48.3% | Gemini 3.1 Pro Preview |
| Terminal-Bench Hard (Artificial Analysis run) | 53.8% | 37.9% | Gemini 3.1 Pro Preview |
| Terminal-Bench | 80.2% | Not measured | Only Gemini 3.1 Pro Preview measured |
| GSO-Bench | 22.6% | Not measured | Only Gemini 3.1 Pro Preview measured |
| WeirdML | 72.1% | 49.9% | Gemini 3.1 Pro Preview |
| MirrorCode | 8.9% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ALE-Bench | 1160.6 | 944.2 | Gemini 3.1 Pro Preview |
| LMArena Text: coding | 1484 | 1415 | Gemini 3.1 Pro Preview |
| LMArena Text: software and IT | 1487 | 1416 | Gemini 3.1 Pro Preview |
| LMArena WebDev: React | 1438 | 1353 | Gemini 3.1 Pro Preview |
| LMArena WebDev: HTML | 1490 | 1367 | Gemini 3.1 Pro Preview |
| LMArena WebDev: from an image | 1481 | 1375 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 3.1 Pro Preview | Grok 4.3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 29.7 | 24.9 | 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 index123
| Benchmark | Gemini 3.1 Pro Preview | Grok 4.3 | Leader |
|---|---|---|---|
| AA Agentic Index | 8.2 | 15.5 | Grok 4.3 |
| Design Arena: agents building web apps | 1125 | 1126 | Grok 4.3 |
| Design Arena: agents building full-stack apps | 1068 | 1006 | Gemini 3.1 Pro Preview |
| Design Arena: agents building mobile apps | 1094 | 1059 | Gemini 3.1 Pro Preview |
| Design Arena: agents building Android apps | 1055 | 967 | Gemini 3.1 Pro Preview |
| Design Arena: agents building Godot games | 1236 | 914 | Gemini 3.1 Pro Preview |
| Design Arena: agents building games | 1114 | 1007 | Gemini 3.1 Pro Preview |
| Design Arena: HTML slides | 1153 | 1008 | Gemini 3.1 Pro Preview |
| Design Arena: PowerPoint slides | 1064 | 1012 | 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% | 37.7% | Gemini 3.1 Pro Preview |
| Tax Agent Bench (Vals AI) | 9.3% | 6.2% | Gemini 3.1 Pro Preview |
| Legal Research Bench (Vals AI) | 20.7% | 15.4% | Gemini 3.1 Pro Preview |
| Excel Modeling Benchmark (Vals AI) | 52.6% | 18.4% | 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% | 97.7% | Grok 4.3 |
| 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% | Not measured | Only Gemini 3.1 Pro Preview measured |
| DeepResearch Bench | 47.8% | Not measured | Only Gemini 3.1 Pro Preview measured |
| PostTrainBench | 22.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Vending-Bench 2 | $911 | $35 | Gemini 3.1 Pro Preview |
| LMArena Search | Not measured | 1166 | Only Grok 4.3 measured |
| Neither model has a result on the other 14 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
| Benchmark | Gemini 3.1 Pro Preview | Grok 4.3 | Leader |
|---|---|---|---|
| GPQA Diamond | 95.5% | 91.4% | 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% | 83.1% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Artificial Analysis run) | 94.1% | 90.1% | Gemini 3.1 Pro Preview |
| Humanity's Last Exam (Artificial Analysis run) | 47.0% | 37.2% | Gemini 3.1 Pro Preview |
| GPQA Diamond (Epoch AI run) | 94.4% | 88.8% | Gemini 3.1 Pro Preview |
| ARC-AGI | 98.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| ARC-AGI-2 | 77.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| SimpleBench | 79.6% | Not measured | Only Gemini 3.1 Pro Preview measured |
| Chess puzzles | 51.0% | 18.0% | Gemini 3.1 Pro Preview |
| Mystery game puzzles | 34.0% | Not measured | Only Gemini 3.1 Pro Preview measured |
| EBR-bench | 14.3% | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Text: hard prompts | 1485 | 1396 | Gemini 3.1 Pro Preview |
| LMArena Text: expert | 1483 | 1384 | Gemini 3.1 Pro Preview |
| LMArena Text: hard prompts in English | 1480 | 1402 | Gemini 3.1 Pro Preview |
| LMArena Vision: diagrams | 1311 | 1241 | Gemini 3.1 Pro Preview |
| LMArena Vision: homework | 1316 | 1241 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemini 3.1 Pro Preview | Grok 4.3 | Leader |
|---|---|---|---|
| AIME | 98.1% | Not measured | Only Gemini 3.1 Pro Preview measured |
| OTIS Mock AIME | 95.6% | 93.3% | Gemini 3.1 Pro Preview |
| FrontierMath, tiers 1 to 3 | 59.6% | 42.8% | Gemini 3.1 Pro Preview |
| FrontierMath, tier 4 | 26.8% | 14.6% | Gemini 3.1 Pro Preview |
| ProofBench | 26.0% | 11.0% | Gemini 3.1 Pro Preview |
| LMArena Text: math | 1486 | 1387 | Gemini 3.1 Pro Preview |
| LMArena Text: mathematical work | 1478 | 1396 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index102
| Benchmark | Gemini 3.1 Pro Preview | Grok 4.3 | Leader |
|---|---|---|---|
| MMLU Pro | 91.0% | 85.8% | Gemini 3.1 Pro Preview |
| LegalBench (Vals AI) | 87.4% | 84.5% | Gemini 3.1 Pro Preview |
| CaseLaw (Vals AI) | 64.8% | 79.3% | Grok 4.3 |
| CorpFin (Vals AI) | 64.5% | 68.5% | Grok 4.3 |
| TaxEval (Vals AI) | 72.9% | 70.8% | Gemini 3.1 Pro Preview |
| MortgageTax (Vals AI) | 69.4% | 48.3% | Gemini 3.1 Pro Preview |
| MedQA (Vals AI) | 96.4% | Not measured | Only Gemini 3.1 Pro Preview measured |
| MedCode (Vals AI) | 59.1% | 38.1% | Gemini 3.1 Pro Preview |
| SimpleQA Verified | 73.5% | 33.2% | Gemini 3.1 Pro Preview |
| LMArena Text: science | 1497 | 1399 | Gemini 3.1 Pro Preview |
| LMArena Text: medicine and healthcare | 1486 | 1384 | Gemini 3.1 Pro Preview |
| LMArena Text: legal and government | 1487 | 1386 | Gemini 3.1 Pro Preview |
| LMArena Text: business and finance | 1459 | 1381 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Gemini 3.1 Pro Preview | Grok 4.3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1234 | 1196 | Gemini 3.1 Pro Preview |
| Design Arena: UI components | 1226 | 1192 | Gemini 3.1 Pro Preview |
| Design Arena: game dev | 1203 | 1174 | Gemini 3.1 Pro Preview |
| Design Arena: data viz | 1209 | 1180 | Gemini 3.1 Pro Preview |
| Design Arena: 3D | 1234 | 1125 | Gemini 3.1 Pro Preview |
| Design Arena: all code categories | 1231 | 1187 | Gemini 3.1 Pro Preview |
| Design Arena: SVG | 1285 | 1081 | Gemini 3.1 Pro Preview |
| Design Arena: ASCII art | 1270 | 1125 | Gemini 3.1 Pro Preview |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index311
| Benchmark | Gemini 3.1 Pro Preview | Grok 4.3 | Leader |
|---|---|---|---|
| Public Benefits Bench (Vals AI) | 53.8% | 51.7% | Gemini 3.1 Pro Preview |
| SAGE (Vals AI) | 48.7% | 19.7% | Gemini 3.1 Pro Preview |
| MedScribe (Vals AI) | 76.1% | 74.4% | Gemini 3.1 Pro Preview |
| Vals Multimodal Index | 56.1% | 43.3% | Gemini 3.1 Pro Preview |
| IFBench | 77.1% | 83.3% | Grok 4.3 |
| Long context reasoning (AA-LCR) | 82.0% | 75.0% | Gemini 3.1 Pro Preview |
| DTBench | 97.1% | 90.7% | Gemini 3.1 Pro Preview |
| LMCA | 53.8% | 38.3% | 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 | 1397 | Gemini 3.1 Pro Preview |
| LMArena Text: instruction following | 1466 | 1366 | Gemini 3.1 Pro Preview |
| LMArena Text: creative writing | 1482 | 1380 | Gemini 3.1 Pro Preview |
| LMArena Vision | 1296 | 1229 | Gemini 3.1 Pro Preview |
| LMArena Text: English | 1478 | 1404 | Gemini 3.1 Pro Preview |
| LMArena Text: non-English | 1476 | 1385 | Gemini 3.1 Pro Preview |
| LMArena Text: Chinese | 1527 | 1422 | Gemini 3.1 Pro Preview |
| LMArena Text: German | 1490 | 1395 | Gemini 3.1 Pro Preview |
| LMArena Text: Japanese | 1491 | 1379 | Gemini 3.1 Pro Preview |
| LMArena Text: Korean | 1455 | 1354 | Gemini 3.1 Pro Preview |
| LMArena Text: French | 1487 | 1411 | Gemini 3.1 Pro Preview |
| LMArena Text: Spanish | 1481 | 1399 | Gemini 3.1 Pro Preview |
| LMArena Text: Russian | 1497 | 1399 | Gemini 3.1 Pro Preview |
| LMArena Text: Polish | 1498 | 1398 | Gemini 3.1 Pro Preview |
| LMArena Text: multi-turn | 1487 | 1406 | Gemini 3.1 Pro Preview |
| LMArena Text: longer queries | 1482 | 1393 | Gemini 3.1 Pro Preview |
| LMArena Text: writing and language | 1481 | 1385 | Gemini 3.1 Pro Preview |
| LMArena Text: entertainment and media | 1465 | 1370 | Gemini 3.1 Pro Preview |
| LMArena Vision: English | 1287 | 1235 | Gemini 3.1 Pro Preview |
| LMArena Vision: Chinese | 1364 | 1257 | Gemini 3.1 Pro Preview |
| LMArena Vision: reading text | 1304 | 1235 | Gemini 3.1 Pro Preview |
| LMArena Vision: humor | 1322 | 1222 | Gemini 3.1 Pro Preview |
| LMArena Vision: captioning | 1345 | Not measured | Only Gemini 3.1 Pro Preview measured |
| LMArena Vision: recognizing things | 1330 | 1217 | Gemini 3.1 Pro Preview |
| LMArena Vision: creative writing | 1324 | 1237 | Gemini 3.1 Pro Preview |
| 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 | Grok 4.3 | 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
Grok 4.3 costs less
Repository review
50K input + 3K output tokens
Grok 4.3 costs less
Agent loop
200K input + 10K output tokens
Grok 4.3 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 | SpaceXAI Grok 4.3 |
|---|---|---|
| Maker | xAI | |
| Weights | No public weights listed | No public weights listed |
| Released | February 19, 2026 | April 30, 2026 |
| Context window | 1.05M | 1M |
| Input $/Mtok | $2.00 | $1.25 |
| Output $/Mtok | $12.00 | $2.50 |
| Coding index | 35.3 | 22.5 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | $0.99 | $0.31 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3.1 Pro Preview better than Grok 4.3 for coding?
Pick Gemini 3.1 Pro Preview for coding: it scores 35.3 on the Vibe Coding Index against 22.5 for Grok 4.3. Pick Grok 4.3 when output tokens cost 4.8x less, or when a solved task costs $0.31 against $0.99.
Which is cheaper, Gemini 3.1 Pro Preview or Grok 4.3?
Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; Grok 4.3 costs $1.25 and $2.50. Per solved SWE-bench Verified task, Gemini 3.1 Pro Preview costs $0.99 and Grok 4.3 $0.31.
Which has the bigger context window, Gemini 3.1 Pro Preview or Grok 4.3?
Gemini 3.1 Pro Preview, with 1.05M tokens against 1M.
How many benchmarks is the Gemini 3.1 Pro Preview vs Grok 4.3 comparison based on?
102 benchmarks have a result for both models as of October 21, 2026. Gemini 3.1 Pro Preview's coding index rests on 1 independent benchmark and Grok 4.3's on 1. Where only one model has a result, the page says so instead of naming a winner.