Enter opens the highlighted result. Esc closes.

Gemini 4 Neon vs Mistral Large 4

Gemini 4 Neon leads Mistral Large 4 on coding, 86.9 to 61.1 on the Vibe Coding Index, and Mistral Large 4 costs 7.1x less per output token ($2.10 vs $15.00 per million). Updated November 22, 2026; 63 benchmarks have a result for both.

Gemini 4 NeonGoogle
Coding
86.9
Overall
89.1
Output $/M
$15.00
63
Mistral Large 4Mistral AI
Coding
61.1
Overall
57.9
Output $/M
$2.10
0
vs boards won of 63 shared

Gemini 4 Neon or Mistral Large 4: which to pick

Pick Gemini 4 Neon for coding: it scores 86.9 on the Vibe Coding Index against 61.1 for Mistral Large 4, though on 4 benchmarks against 5.

Pick Mistral Large 4 for output tokens 7.1x cheaper ($2.10 vs $15.00 per million).

Shared results
63
Gemini 4 Neon only
6
Mistral Large 4 only
28
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.

At a glance

Coding index
Gemini 4 Neon 86.9 from 4 benchmarks, Mistral Large 4 61.1 from 5 benchmarks.
Widest category
Intelligence, 35.3 points apart on average over 1 shared benchmark.
Widest single gap
LiveBench browser: Gemini 4 Neon 95.6% against Mistral Large 4 17.4%, 78.2 points apart on a 0 to 100 scale.
Output price
Gemini 4 Neon $15.00 against Mistral Large 4 $2.10 per million output tokens, 7.1x 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.

Boards won, where both have a result
CategoryGemini 4 NeonBarsMistral Large 4Ties
Coding110
Intelligence10
Agentic work80
Reasoning100
Math50
Knowledge60
Web design60
General160
All shared boards630
CodingLike-for-likeSix of these boards feed the Vibe Coding Index110
Coding benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
LiveBench coding89.7%79.4%Gemini 4 Neon
LMArena WebDev17651573Gemini 4 Neon
Terminal-Bench 4 (Vals AI)61.6%27.8%Gemini 4 Neon
Vibe Code Bench (Vals AI)93.7%81.6%Gemini 4 Neon
Code migration (Vals AI)Not measured30.6%Only Mistral Large 4 measured
IOI (Vals AI)Not measured45.3%Only Mistral Large 4 measured
SWE-bench Multimodal (Vals AI)Not measured33.1%Only Mistral Large 4 measured
Vibe Code Bench 1-100 (Vals AI)Not measured14.3%Only Mistral Large 4 measured
Terminal-Bench 4.0 (Artificial Analysis run)63.6%24.7%Gemini 4 Neon
FrontierCode 2.044.4%15.0%Gemini 4 Neon
FrontierCodeNot measured39.4%Only Mistral Large 4 measured
MirrorCodeNot measured40.0%Only Mistral Large 4 measured
ALE-BenchNot measured1213.2Only Mistral Large 4 measured
LMArena Text: coding15551459Gemini 4 Neon
LMArena Text: software and IT15421459Gemini 4 Neon
LMArena WebDev: React17871582Gemini 4 Neon
LMArena WebDev: HTML18031560Gemini 4 Neon
GameBench 298.057.9Gemini 4 Neon
Terminal-Bench 4.0Not measured27.9%Only Mistral Large 4 measured
CursorBench 4.065.4%Not measuredOnly Gemini 4 Neon measured
Neither model has a result on the other 32 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
AA Intelligence Index61.426.1Gemini 4 Neon
Epoch Capabilities IndexNot measured154.6Only Mistral Large 4 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index80
Agentic work benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
LiveBench research94.5%80.3%Gemini 4 Neon
LiveBench browser95.6%17.4%Gemini 4 Neon
LiveBench long agentic82.6%24.7%Gemini 4 Neon
Finance Agent (Vals AI)Not measured54.7%Only Mistral Large 4 measured
Tax Agent Bench (Vals AI)54.9%30.7%Gemini 4 Neon
Legal Research Bench (Vals AI)56.3%35.6%Gemini 4 Neon
Harvey's Legal Agent Benchmark (Vals AI)19.6%17.5%Gemini 4 Neon
Excel Modeling Benchmark (Vals AI)Not measured56.2%Only Mistral Large 4 measured
BioMysteryBench (Vals AI)80.0%67.0%Gemini 4 Neon
Terminal-Bench-Science (Vals AI)62.9%Not measuredOnly Gemini 4 Neon measured
Vals Science Index62.6%Not measuredOnly Gemini 4 Neon measured
APEX-Agents82.9%51.6%Gemini 4 Neon
Vending-Bench 2$16,843Not measuredOnly Gemini 4 Neon measured
Neither model has a result on the other 31 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
Reasoning benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
LiveBench reasoning89.6%85.2%Gemini 4 Neon
MysteryMechanism (Vals AI)45.0%12.2%Gemini 4 Neon
HLE-Diamond (Artificial Analysis run)71.3%17.3%Gemini 4 Neon
CritPt v2, hard subset (Artificial Analysis run)61.5%27.0%Gemini 4 Neon
GPQA Diamond (Epoch AI run)96.3%88.1%Gemini 4 Neon
SimpleBench94.4%Not measuredOnly Gemini 4 Neon measured
Chess puzzles83.0%33.0%Gemini 4 Neon
Mystery game puzzles85.0%17.0%Gemini 4 Neon
EBR-bench98.1%Not measuredOnly Gemini 4 Neon measured
LMArena Text: hard prompts15471436Gemini 4 Neon
LMArena Text: expert15601450Gemini 4 Neon
LMArena Text: hard prompts in English15241442Gemini 4 Neon
LMArena Vision: diagramsNot measured1273Only Mistral Large 4 measured
LMArena Vision: homeworkNot measured1266Only Mistral Large 4 measured
Neither model has a result on the other 12 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
OTIS Mock AIME100.0%98.3%Gemini 4 Neon
FrontierMath, tiers 1 to 391.2%58.6%Gemini 4 Neon
FrontierMath, tier 497.6%26.8%Gemini 4 Neon
ProofBenchNot measured10.0%Only Mistral Large 4 measured
LMArena Text: math15481445Gemini 4 Neon
LMArena Text: mathematical work15661456Gemini 4 Neon
MathArenaNot measured20.7%Only Mistral Large 4 measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
MedCode (Vals AI)Not measured40.7%Only Mistral Large 4 measured
AA-Omniscience54.85.1Gemini 4 Neon
SimpleQA Verified75.2%20.0%Gemini 4 Neon
LMArena Text: science15491434Gemini 4 Neon
LMArena Text: medicine and healthcare15341403Gemini 4 Neon
LMArena Text: legal and government15181427Gemini 4 Neon
LMArena Text: business and finance14931430Gemini 4 Neon
Neither model has a result on the other 14 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
Design Arena: websites13471253Gemini 4 Neon
Design Arena: UI components13491272Gemini 4 Neon
Design Arena: game dev13941190Gemini 4 Neon
Design Arena: data vizNot measured1271Only Mistral Large 4 measured
Design Arena: 3D14901225Gemini 4 Neon
Design Arena: all code categories13911247Gemini 4 Neon
Design Arena: SVGNot measured1216Only Mistral Large 4 measured
Design Arena: ASCII artNot measured1196Only Mistral Large 4 measured
LiveBench design81.5%76.3%Gemini 4 Neon
GeneralLike-for-likePublic boards, shown as published, kept out of the index160
General benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
Vals Index70.9%56.5%Gemini 4 Neon
LiveBench data analysis85.3%76.6%Gemini 4 Neon
MedScribe (Vals AI)Not measured80.4%Only Mistral Large 4 measured
DTBenchNot measured88.2%Only Mistral Large 4 measured
LMCANot measured35.8%Only Mistral Large 4 measured
Surface Evolver BenchNot measured28.1%Only Mistral Large 4 measured
Furniture assembly89.2%20.8%Gemini 4 Neon
LMArena Text15241413Gemini 4 Neon
LMArena Text: instruction following15351414Gemini 4 Neon
LMArena Text: creative writing15191341Gemini 4 Neon
LMArena VisionNot measured1246Only Mistral Large 4 measured
LMArena Text: English15111423Gemini 4 Neon
LMArena Text: non-English15241400Gemini 4 Neon
LMArena Text: Chinese15981466Gemini 4 Neon
LMArena Text: French15631443Gemini 4 Neon
LMArena Text: Spanish15051456Gemini 4 Neon
LMArena Text: Russian15541415Gemini 4 Neon
LMArena Text: multi-turn15251423Gemini 4 Neon
LMArena Text: longer queries15331409Gemini 4 Neon
LMArena Text: writing and language15171367Gemini 4 Neon
LMArena Text: entertainment and media14951358Gemini 4 Neon
LMArena Vision: EnglishNot measured1258Only Mistral Large 4 measured
LMArena Vision: ChineseNot measured1331Only Mistral Large 4 measured
LMArena Vision: reading textNot measured1261Only Mistral Large 4 measured
LMArena Vision: creative writingNot measured1213Only Mistral Large 4 measured
Neither model has a result on the other 24 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 4 Neon and Mistral Large 4
BenchmarkGemini 4 NeonMistral Large 4Leader
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 4 Neon$0.011Fits in one request
Mistral Large 4$0.0018Fits in one request

Mistral Large 4 costs less

Repository review

50K input + 3K output tokens

Gemini 4 Neon$0.195Fits in one request
Mistral Large 4$0.041Fits in one request

Mistral Large 4 costs less

Agent loop

200K input + 10K output tokens

Gemini 4 Neon$0.750Fits in one request
Mistral Large 4$0.161Fits in one request

Mistral Large 4 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 4 Neon and Mistral Large 4
SpecificationGoogle Gemini 4 NeonMistral Large 4
MakerGoogleMistral AI
WeightsNo public weights listedOpen weights
ReleasedNovember 18, 2026October 6, 2026
Context window1.05M1.05M
Input $/Mtok$3.00$0.70
Output $/Mtok$15.00$2.10
Coding index86.961.1
Independent measurements behind it45
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 4 Neon better than Mistral Large 4 for coding?

Pick Gemini 4 Neon for coding: it scores 86.9 on the Vibe Coding Index against 61.1 for Mistral Large 4, though on 4 benchmarks against 5. Pick Mistral Large 4 for output tokens 7.1x cheaper ($2.10 vs $15.00 per million).

Which is cheaper, Gemini 4 Neon or Mistral Large 4?

Gemini 4 Neon costs $3.00 per million input tokens and $15.00 per million output tokens; Mistral Large 4 costs $0.70 and $2.10. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemini 4 Neon or Mistral Large 4?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 4 Neon vs Mistral Large 4 comparison based on?

63 benchmarks have a result for both models as of November 22, 2026. Gemini 4 Neon's coding index rests on 4 independent benchmarks and Mistral Large 4's on 5. 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-4-neon-vs-mistral-large-4-0" title="Gemini 4 Neon vs Mistral Large 4, 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-4-neon-vs-mistral-large-4-0">LLMBenchmark.ai, Gemini 4 Neon vs Mistral Large 4</a></p>