Enter opens the highlighted result. Esc closes.

Gemini 2.5 Flash vs Llama 4 Maverick

Gemini 2.5 Flash leads Llama 4 Maverick on the Artificial Analysis Intelligence Index, 15.5 to 9.3, and Llama 4 Maverick costs 2.5x less per output token ($1.00 vs $2.50 per million). Updated October 22, 2026; 64 benchmarks have a result for both.

Replace Gemini 2.5 Flash Replace Llama 4 Maverick
Gemini 2.5 FlashGoogle
Coding
No data
Overall
34.3
Output $/M
$2.50
64
Llama 4 MaverickMeta Llama
Coding
No data
Overall
21.8
Output $/M
$1.00
0
vs boards won of 64 shared

Gemini 2.5 Flash or Llama 4 Maverick: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Gemini 2.5 Flash for a lower cost per solved task ($0.466 against $1.491) and a larger context window (1.05M against 524K tokens).

Model AGemini 2.5 FlashGoogleNot benchmarkedNo coding benchmark$0.466 per solved taskModel BLlama 4 MaverickMeta LlamaNot benchmarkedNo coding benchmark$1.491 per solved task
Shared results
64
Gemini 2.5 Flash only
9
Llama 4 Maverick only
21
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 2.5 Flash not benchmarked, Llama 4 Maverick not benchmarked.
Widest category
Math, 37.0 points apart on average over 4 shared benchmarks.
Widest single gap
AA Math Index: Gemini 2.5 Flash 73.3 against Llama 4 Maverick 19.3, 54.0 points apart on a 0 to 100 scale.
Output price
Gemini 2.5 Flash $2.50 against Llama 4 Maverick $1.00 per million output tokens, 2.5x apart.
Context window
Gemini 2.5 Flash takes 1.05M tokens, Llama 4 Maverick 524K.

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 2.5 FlashBarsLlama 4 MaverickTies
Coding50
Intelligence20
Agentic work10
Reasoning110
Math40
Knowledge60
Web design60
General290
All shared boards640
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
Coding benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
Aider polyglotNot measured15.6%Only Llama 4 Maverick measured
SWE-bench Verified28.7%21.0%Gemini 2.5 Flash
AA Coding IndexNot measured16.3Only Llama 4 Maverick measured
LiveCodeBench (Vals AI)Not measured47.3%Only Llama 4 Maverick measured
LiveCodeBench (Artificial Analysis run)69.5%39.7%Gemini 2.5 Flash
SciCodeNot measured31.7%Only Llama 4 Maverick measured
Terminal-Bench Hard (Artificial Analysis run)13.6%6.8%Gemini 2.5 Flash
Terminal-Bench17.1%Not measuredOnly Gemini 2.5 Flash measured
WeirdMLNot measured24.5%Only Llama 4 Maverick measured
ALE-BenchNot measured173.0Only Llama 4 Maverick measured
LMArena Text: coding14231301Gemini 2.5 Flash
LMArena Text: software and IT14251299Gemini 2.5 Flash
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
AA Intelligence Index15.59.3Gemini 2.5 Flash
Epoch Capabilities Index142.9132.2Gemini 2.5 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
AA Agentic IndexNot measured0.6Only Llama 4 Maverick measured
τ²-Bench Telecom31.6%17.8%Gemini 2.5 Flash
BALROG33.5%Not measuredOnly Gemini 2.5 Flash measured
Vending-Bench 2$549Not measuredOnly Gemini 2.5 Flash measured
Berkeley Function Calling Leaderboard (BFCL)56.2%Not measuredOnly Gemini 2.5 Flash measured
BrowseComp-Plus39.9%Not measuredOnly Gemini 2.5 Flash measured
Neither model has a result on the other 35 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
Reasoning benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
GPQA DiamondNot measured69.4%Only Llama 4 Maverick measured
MMMU Pro (Vals AI)Not measured71.7%Only Llama 4 Maverick measured
GPQA Diamond (Artificial Analysis run)79.0%67.1%Gemini 2.5 Flash
Humanity's Last Exam (Artificial Analysis run)12.1%4.9%Gemini 2.5 Flash
ARC-AGI33.3%4.4%Gemini 2.5 Flash
ARC-AGI-22.5%0.0%Gemini 2.5 Flash
SimpleBench41.2%27.7%Gemini 2.5 Flash
LMArena Text: hard prompts14221281Gemini 2.5 Flash
LMArena Text: expert14261259Gemini 2.5 Flash
LMArena Text: hard prompts in English14201295Gemini 2.5 Flash
LMArena Vision: diagrams12451134Gemini 2.5 Flash
LMArena Vision: homework12441164Gemini 2.5 Flash
Kagi LLM Benchmark56.8%55.9%Gemini 2.5 Flash
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
AIMENot measured25.2%Only Llama 4 Maverick measured
MATH 500 (Vals AI)Not measured85.2%Only Llama 4 Maverick measured
MGSM (Vals AI)Not measured92.4%Only Llama 4 Maverick measured
AA Math Index73.319.3Gemini 2.5 Flash
AIME 2025 (Artificial Analysis run)73.3%19.3%Gemini 2.5 Flash
LMArena Text: math14111299Gemini 2.5 Flash
LMArena Text: mathematical work14221295Gemini 2.5 Flash
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
MMLU ProNot measured79.4%Only Llama 4 Maverick measured
LegalBench (Vals AI)Not measured77.8%Only Llama 4 Maverick measured
CorpFin (Vals AI)Not measured49.7%Only Llama 4 Maverick measured
TaxEval (Vals AI)Not measured66.6%Only Llama 4 Maverick measured
MortgageTax (Vals AI)Not measured58.5%Only Llama 4 Maverick measured
MedQA (Vals AI)Not measured43.3%Only Llama 4 Maverick measured
MedCode (Vals AI)40.4%36.5%Gemini 2.5 Flash
MMLU Pro (Artificial Analysis run)83.2%80.9%Gemini 2.5 Flash
GeoBenchNot measured52.0%Only Llama 4 Maverick measured
LMArena Text: science14331288Gemini 2.5 Flash
LMArena Text: medicine and healthcare14281275Gemini 2.5 Flash
LMArena Text: legal and government14301286Gemini 2.5 Flash
LMArena Text: business and finance14041260Gemini 2.5 Flash
FACTS Benchmark Suite47.2%Not measuredOnly Gemini 2.5 Flash measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
Design Arena: websites1074871Gemini 2.5 Flash
Design Arena: UI components1002896Gemini 2.5 Flash
Design Arena: game dev1004837Gemini 2.5 Flash
Design Arena: data viz1060882Gemini 2.5 Flash
Design Arena: 3D1020900Gemini 2.5 Flash
Design Arena: all code categories1059879Gemini 2.5 Flash
Design Arena: SVG1020Not measuredOnly Gemini 2.5 Flash measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index290
General benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
SAGE (Vals AI)44.8%35.7%Gemini 2.5 Flash
MedScribe (Vals AI)83.0%54.2%Gemini 2.5 Flash
IFBench50.3%43.0%Gemini 2.5 Flash
Long context reasoning (AA-LCR)65.3%50.0%Gemini 2.5 Flash
DTBench76.5%61.9%Gemini 2.5 Flash
LMCA27.5%15.9%Gemini 2.5 Flash
Fiction.LiveBenchNot measured46.2%Only Llama 4 Maverick measured
Creative writing (Lech Mazur)Not measured62.0%Only Llama 4 Maverick measured
LMArena Text14171287Gemini 2.5 Flash
LMArena Text: instruction following14051267Gemini 2.5 Flash
LMArena Text: creative writing14001266Gemini 2.5 Flash
LMArena Vision12351142Gemini 2.5 Flash
LMArena Text: English14181303Gemini 2.5 Flash
LMArena Text: non-English14091269Gemini 2.5 Flash
LMArena Text: Chinese14491277Gemini 2.5 Flash
LMArena Text: German14171291Gemini 2.5 Flash
LMArena Text: Japanese13961206Gemini 2.5 Flash
LMArena Text: Korean13851203Gemini 2.5 Flash
LMArena Text: French14321259Gemini 2.5 Flash
LMArena Text: Spanish14221293Gemini 2.5 Flash
LMArena Text: Russian14151286Gemini 2.5 Flash
LMArena Text: Polish14131275Gemini 2.5 Flash
LMArena Text: multi-turn14081289Gemini 2.5 Flash
LMArena Text: longer queries14191280Gemini 2.5 Flash
LMArena Text: writing and language14051277Gemini 2.5 Flash
LMArena Text: entertainment and media13931250Gemini 2.5 Flash
LMArena Vision: English12391150Gemini 2.5 Flash
LMArena Vision: Chinese12841141Gemini 2.5 Flash
LMArena Vision: reading text12371143Gemini 2.5 Flash
LMArena Vision: humor12251100Gemini 2.5 Flash
LMArena Vision: captioning1277Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: recognizing things1252Not measuredOnly Gemini 2.5 Flash measured
LMArena Vision: creative writing12411099Gemini 2.5 Flash
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 2.5 Flash and Llama 4 Maverick
BenchmarkGemini 2.5 FlashLlama 4 MaverickLeader
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 Flash$0.0015Fits in one request
Llama 4 Maverick$0.0008Fits in one request

Llama 4 Maverick costs less

Repository review

50K input + 3K output tokens

Gemini 2.5 Flash$0.022Fits in one request
Llama 4 Maverick$0.021Fits in one request

Llama 4 Maverick costs less

Agent loop

200K input + 10K output tokens

Gemini 2.5 Flash$0.085Fits in one request
Llama 4 Maverick$0.080Fits in one request

Llama 4 Maverick 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 2.5 Flash and Llama 4 Maverick
SpecificationGoogle Gemini 2.5 FlashMeta Llama 4 Maverick
MakerGoogleMeta Llama
WeightsNo public weights listedOpen weights
ReleasedJune 17, 2025April 5, 2025
Context window1.05M524K
Input $/Mtok$0.30$0.35
Output $/Mtok$2.50$1.00
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved task$0.466$1.491
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 2.5 Flash better than Llama 4 Maverick for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemini 2.5 Flash for a lower cost per solved task ($0.466 against $1.491) and a larger context window (1.05M against 524K tokens).

Which is cheaper, Gemini 2.5 Flash or Llama 4 Maverick?

Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens; Llama 4 Maverick costs $0.35 and $1.00. Per solved SWE-bench Verified task, Gemini 2.5 Flash costs $0.466 and Llama 4 Maverick $1.491.

Which has the bigger context window, Gemini 2.5 Flash or Llama 4 Maverick?

Gemini 2.5 Flash, with 1.05M tokens against 524K.

How many benchmarks is the Gemini 2.5 Flash vs Llama 4 Maverick comparison based on?

64 benchmarks have a result for both models as of October 22, 2026. Gemini 2.5 Flash's coding index rests on 0 independent benchmarks and Llama 4 Maverick's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next