Gemini 3.1 Pro Preview vs Grok 4.20

Grok 4.20 leads Gemini 3.1 Pro Preview on coding, 33.3 to 32.3 on the Vibe Coding Index, and Grok 4.20 costs 4.8x less per output token ($2.50 vs $12.00 per million). Updated October 21, 2026; 53 benchmarks have a result for both.

Replace Gemini 3.1 Pro Preview Replace Grok 4.20

Gemini 3.1 Pro PreviewGoogle

Coding: 32.3
Overall: 54.0
Output $/M: $12.00

Grok 4.20xAI

Coding: 33.3
Overall: 41.0
Output $/M: $2.50

vs boards won of 53 shared

Gemini 3.1 Pro Preview or Grok 4.20: which to pick

Gemini 3.1 Pro Preview and Grok 4.20 are level for coding, 32.3 against 33.3 on the Vibe Coding Index, so price and context decide.

Pick Gemini 3.1 Pro Preview for work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads. Pick Grok 4.20 for output tokens 4.8x cheaper ($2.50 vs $12.00 per million) and a lower cost per solved task ($0.72 against $0.99).

Model AGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved task Model BGrok 4.20xAI33.3/1002 independent benchmarks$0.72 per solved task

53802

Shared results: 53
Gemini 3.1 Pro Preview only: 80
Grok 4.20 only: 2
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
No call
Level: 32.3 against 33.3, inside 2 points.
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 25.7.
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
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 88.6%.
Same board, both measured
Math
AIME
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 98.1% against 96.5%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 86.3%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 1234 against 1229.
Same board, both measured
Long documents
Listed context window
Grok 4.20
Grok 4.20 takes 2M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Grok 4.20
Gemini 3.1 Pro Preview $0.0080, Grok 4.20 $0.0025 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Grok 4.20
Gemini 3.1 Pro Preview $0.99, Grok 4.20 $0.72.
Published attempt cost and pass rate

At a glance

Coding index: Gemini 3.1 Pro Preview 32.3 from 4 benchmarks, Grok 4.20 33.3 from 2 benchmarks.
Widest category: Coding, 17.6 points apart on average over 8 shared benchmarks.
Widest single gap: Excel Modeling Benchmark (Vals AI): Gemini 3.1 Pro Preview 52.6% against Grok 4.20 11.7%, 40.9 points apart on a 0 to 100 scale.
Output price: Gemini 3.1 Pro Preview $12.00 against Grok 4.20 $2.50 per million output tokens, 4.8x apart.
Context window: Gemini 3.1 Pro Preview takes 1.05M tokens, Grok 4.20 2M.

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
Category	Gemini 3.1 Pro Preview	Grok 4.20
Coding	8	0
Intelligence	1	0
Agentic work	8	4
Reasoning	6	0
Math	1	0
Knowledge	7	1
Web design	7	1
General	7	2
All shared boards	45	8

CodingLike-for-likeSix of these boards feed the Vibe Coding Index80

Coding benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	Leader
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%	84.3%	Gemini 3.1 Pro Preview
SWE-bench Verified (Vals AI)	78.8%	72.2%	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%	4.1%	Gemini 3.1 Pro Preview
Code migration (Vals AI)	17.3%	0.3%	Gemini 3.1 Pro Preview
ProgramBench (Vals AI)	0.0%	Not measured	Only Gemini 3.1 Pro Preview measured
IOI (Vals AI)	51.8%	Not measured	Only Gemini 3.1 Pro Preview measured
Terminal-Bench 2.1 (Vals AI)	70.8%	44.2%	Gemini 3.1 Pro Preview
Vibe Code Bench 1-100 (Vals AI)	6.7%	Not measured	Only Gemini 3.1 Pro Preview measured
SciCode	58.7%	Not measured	Only Gemini 3.1 Pro Preview measured
Terminal-Bench Hard (Artificial Analysis run)	53.8%	37.9%	Gemini 3.1 Pro Preview
Terminal-Bench	80.2%	57.3%	Gemini 3.1 Pro Preview
GSO-Bench	22.6%	Not measured	Only Gemini 3.1 Pro Preview measured
WeirdML	72.1%	52.3%	Gemini 3.1 Pro Preview
MirrorCode	8.9%	Not measured	Only Gemini 3.1 Pro Preview measured
ALE-Bench	1160.6	Not measured	Only Gemini 3.1 Pro Preview measured
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%	Not measured	Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 15 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10

Intelligence benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	Leader
AA Intelligence Index	29.7	25.7	Gemini 3.1 Pro Preview
Epoch Capabilities Index	Not measured	152.1	Only Grok 4.20 measured

Agentic workLike-for-likePublic boards, shown as published, kept out of the index84

Agentic work benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	Leader
AA Agentic Index	8.2	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: agents building web apps	1125	1144	Grok 4.20
Design Arena: agents building full-stack apps	1068	1054	Gemini 3.1 Pro Preview
Design Arena: agents building mobile apps	1093	1090	Gemini 3.1 Pro Preview
Design Arena: agents building Android apps	1048	1052	Grok 4.20
Design Arena: agents building Godot games	1236	1089	Gemini 3.1 Pro Preview
Design Arena: agents building games	1114	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: HTML slides	1153	1180	Grok 4.20
Design Arena: PowerPoint slides	1066	Not measured	Only Gemini 3.1 Pro Preview measured
SREBench (Vals AI)	0.0%	Not measured	Only Gemini 3.1 Pro Preview measured
Finance Agent (Vals AI)	43.0%	28.5%	Gemini 3.1 Pro Preview
Tax Agent Bench (Vals AI)	9.3%	7.0%	Gemini 3.1 Pro Preview
Legal Research Bench (Vals AI)	20.7%	13.9%	Gemini 3.1 Pro Preview
Excel Modeling Benchmark (Vals AI)	52.6%	11.7%	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%	93.0%	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%	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	$4,663	Grok 4.20
Neither model has a result on the other 17 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index60

Reasoning benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	Leader
GPQA Diamond	95.5%	88.6%	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%	83.5%	Gemini 3.1 Pro Preview
GPQA Diamond (Artificial Analysis run)	94.1%	91.1%	Gemini 3.1 Pro Preview
Humanity's Last Exam (Artificial Analysis run)	47.0%	34.5%	Gemini 3.1 Pro Preview
GPQA Diamond (Epoch AI run)	94.4%	Not measured	Only Gemini 3.1 Pro Preview measured
ARC-AGI	98.0%	89.5%	Gemini 3.1 Pro Preview
ARC-AGI-2	77.1%	65.1%	Gemini 3.1 Pro Preview
SimpleBench	79.6%	Not measured	Only Gemini 3.1 Pro Preview measured
Chess puzzles	51.0%	Not measured	Only Gemini 3.1 Pro Preview measured
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	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
Kagi LLM Benchmark	Not measured	75.0%	Only Grok 4.20 measured
Neither model has a result on the other 4 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index10

Math benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	Leader
AIME	98.1%	96.5%	Gemini 3.1 Pro Preview
OTIS Mock AIME	95.6%	Not measured	Only Gemini 3.1 Pro Preview measured
FrontierMath, tiers 1 to 3	59.6%	Not measured	Only Gemini 3.1 Pro Preview measured
FrontierMath, tier 4	26.8%	Not measured	Only Gemini 3.1 Pro Preview measured
ProofBench	26.0%	Not measured	Only Gemini 3.1 Pro Preview measured
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 6 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index71

Knowledge benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	Leader
MMLU Pro	91.0%	86.3%	Gemini 3.1 Pro Preview
LegalBench (Vals AI)	87.4%	77.7%	Gemini 3.1 Pro Preview
CaseLaw (Vals AI)	64.8%	54.4%	Gemini 3.1 Pro Preview
CorpFin (Vals AI)	64.5%	63.7%	Gemini 3.1 Pro Preview
TaxEval (Vals AI)	72.9%	74.1%	Grok 4.20
MortgageTax (Vals AI)	69.4%	45.4%	Gemini 3.1 Pro Preview
MedQA (Vals AI)	96.4%	94.5%	Gemini 3.1 Pro Preview
MedCode (Vals AI)	59.1%	32.2%	Gemini 3.1 Pro Preview
SimpleQA Verified	73.5%	Not measured	Only Gemini 3.1 Pro 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%	Not measured	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 index71

Web design benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	Leader
Design Arena: websites	1234	1229	Gemini 3.1 Pro Preview
Design Arena: UI components	1227	1199	Gemini 3.1 Pro Preview
Design Arena: game dev	1203	1192	Gemini 3.1 Pro Preview
Design Arena: data viz	1209	1217	Grok 4.20
Design Arena: 3D	1234	1193	Gemini 3.1 Pro Preview
Design Arena: all code categories	1231	1221	Gemini 3.1 Pro Preview
Design Arena: SVG	1285	1164	Gemini 3.1 Pro Preview
Design Arena: ASCII art	1270	1174	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 index72

General benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	Leader
Public Benefits Bench (Vals AI)	53.8%	Not measured	Only Gemini 3.1 Pro Preview measured
SAGE (Vals AI)	48.7%	38.2%	Gemini 3.1 Pro Preview
MedScribe (Vals AI)	76.1%	63.4%	Gemini 3.1 Pro Preview
Vals Multimodal Index	56.1%	39.1%	Gemini 3.1 Pro Preview
IFBench	77.1%	81.2%	Grok 4.20
Long context reasoning (AA-LCR)	82.0%	69.0%	Gemini 3.1 Pro Preview
DTBench	97.1%	90.1%	Gemini 3.1 Pro Preview
LMCA	53.8%	38.7%	Gemini 3.1 Pro Preview
CL-bench	20.8%	22.2%	Grok 4.20
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%	11.9%	Gemini 3.1 Pro Preview
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

Image generation benchmarks for Gemini 3.1 Pro Preview and Grok 4.20
Benchmark	Gemini 3.1 Pro Preview	Grok 4.20	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

Grok 4.20$0.0025Fits in one request

Grok 4.20 costs less

Repository review

50K input + 3K output tokens

Gemini 3.1 Pro Preview$0.136Fits in one request

Grok 4.20$0.070Fits in one request

Grok 4.20 costs less

Agent loop

200K input + 10K output tokens

Gemini 3.1 Pro Preview$0.520Fits in one request

Grok 4.20$0.275Fits in one request

Grok 4.20 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 Grok 4.20
Specification	Google Gemini 3.1 Pro Preview	SpaceXAI Grok 4.20
Maker	Google	xAI
Weights	No public weights listed	No public weights listed
Released	February 19, 2026	March 31, 2026
Context window	1.05M	2M
Input $/Mtok	$2.00	$1.25
Output $/Mtok	$12.00	$2.50
Coding index	32.3	33.3
Independent measurements behind it	4	2
Cost per solved task	$0.99	$0.72
Source	OpenRouter listing	OpenRouter listing

Questions

Is Gemini 3.1 Pro Preview better than Grok 4.20 for coding?

Gemini 3.1 Pro Preview and Grok 4.20 are level for coding, 32.3 against 33.3 on the Vibe Coding Index, so price and context decide. Pick Gemini 3.1 Pro Preview for work measured by LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads. Pick Grok 4.20 for output tokens 4.8x cheaper ($2.50 vs $12.00 per million) and a lower cost per solved task ($0.72 against $0.99).

Which is cheaper, Gemini 3.1 Pro Preview or Grok 4.20?

Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Per solved SWE-bench Verified task, Gemini 3.1 Pro Preview costs $0.99 and Grok 4.20 $0.72.

Which has the bigger context window, Gemini 3.1 Pro Preview or Grok 4.20?

Grok 4.20, with 2M tokens against 1.05M.

How many benchmarks is the Gemini 3.1 Pro Preview vs Grok 4.20 comparison based on?

53 benchmarks have a result for both models as of October 21, 2026. Gemini 3.1 Pro Preview's coding index rests on 4 independent benchmarks and Grok 4.20's on 2. 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-grok-4-20" title="Gemini 3.1 Pro Preview vs Grok 4.20, 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-grok-4-20">LLMBenchmark.ai, Gemini 3.1 Pro Preview vs Grok 4.20</a></p>

Gemini 3.1 Pro Preview or Grok 4.20: which to pick

Which one for your work

Coding

Intelligence

Agentic work

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next