LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 2.5 Pro vs Llama 4 Scout

Updated October 21, 2026. 68 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 2.5 Pro Replace Llama 4 Scout
Gemini 2.5 ProGoogle
Coding
37.0
Overall
16.1
Output $/M
$10.00
68
Llama 4 ScoutMeta Llama
Coding
9.1
Overall
6.5
Output $/M
$0.30
0
vs boards won of 68 shared

Decision reading

Pick Gemini 2.5 Pro for coding: it scores 37.0 on the Vibe Coding Index against 9.1 for Llama 4 Scout.

Pick Llama 4 Scout when output tokens cost 33.3x less, or when the context window is larger, 1.31M against 1.05M tokens.

Model AGemini 2.5 ProGoogle37.0/1002 independent benchmarks$0.64 per solved taskModel BLlama 4 ScoutMeta Llama9.1/1001 independent benchmark$1.276 per solved task
Shared results
68
Gemini 2.5 Pro only
19
Llama 4 Scout only
12
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.

At a glance

Coding index
Gemini 2.5 Pro 37.0 from 2 benchmarks, Llama 4 Scout 9.1 from 1 benchmark.
Widest category
Math, 55.9 points apart on average over 5 shared benchmarks.
Widest single gap
OTIS Mock AIME: Gemini 2.5 Pro 84.7% against Llama 4 Scout 7.8%, 76.9 points apart on a 0 to 100 scale.
Output price
Gemini 2.5 Pro $10.00 against Llama 4 Scout $0.30 per million output tokens, 33.3x apart.
Context window
Gemini 2.5 Pro takes 1.05M tokens, Llama 4 Scout 1.31M.

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 ProBarsLlama 4 ScoutTies
Coding70
Intelligence20
Agentic work20
Reasoning100
Math50
Knowledge80
Web design50
General290
All shared boards680
CodingLike-for-likeFour of these boards feed the Vibe Coding Index70
Coding benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
SWE-bench Verified53.6%9.1%Gemini 2.5 Pro
LMArena WebDev1226Not measuredOnly Gemini 2.5 Pro measured
AA Coding Index33.38.2Gemini 2.5 Pro
LiveCodeBench (Vals AI)Not measured38.5%Only Llama 4 Scout measured
SWE-bench Verified (Vals AI)54.4%Not measuredOnly Gemini 2.5 Pro measured
Vibe Code Bench (Vals AI)0.4%Not measuredOnly Gemini 2.5 Pro measured
LiveCodeBench (Artificial Analysis run)80.1%29.9%Gemini 2.5 Pro
SciCode46.3%21.3%Gemini 2.5 Pro
Terminal-Bench Hard (Artificial Analysis run)26.5%1.5%Gemini 2.5 Pro
Terminal-Bench32.6%Not measuredOnly Gemini 2.5 Pro measured
GSO-Bench3.9%Not measuredOnly Gemini 2.5 Pro measured
WeirdML54.0%Not measuredOnly Gemini 2.5 Pro measured
LMArena Text: coding14521286Gemini 2.5 Pro
LMArena Text: software and IT14591286Gemini 2.5 Pro
LMArena WebDev: HTML1235Not measuredOnly Gemini 2.5 Pro measured
LMArena WebDev: from an image1285Not measuredOnly Gemini 2.5 Pro measured
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
AA Intelligence Index16.16.5Gemini 2.5 Pro
Epoch Capabilities Index145.1129.6Gemini 2.5 Pro
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
AA Agentic Index1.60.5Gemini 2.5 Pro
τ²-Bench Telecom54.1%15.5%Gemini 2.5 Pro
GDPval23.3%Not measuredOnly Gemini 2.5 Pro measured
DeepResearch Bench41.5%Not measuredOnly Gemini 2.5 Pro measured
Vending-Bench 2$574Not measuredOnly Gemini 2.5 Pro measured
Neither model has a result on the other 34 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
Reasoning benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
GPQA DiamondNot measured47.0%Only Llama 4 Scout measured
MMMU Pro (Vals AI)Not measured58.8%Only Llama 4 Scout measured
GPQA Diamond (Artificial Analysis run)84.4%58.7%Gemini 2.5 Pro
Humanity's Last Exam (Artificial Analysis run)22.5%3.8%Gemini 2.5 Pro
GPQA Diamond (Epoch AI run)85.3%51.8%Gemini 2.5 Pro
ARC-AGI41.0%0.5%Gemini 2.5 Pro
ARC-AGI-24.9%0.0%Gemini 2.5 Pro
LMArena Text: hard prompts14551266Gemini 2.5 Pro
LMArena Text: expert14521235Gemini 2.5 Pro
LMArena Text: hard prompts in English14531293Gemini 2.5 Pro
LMArena Vision: diagrams12741125Gemini 2.5 Pro
LMArena Vision: homework12811148Gemini 2.5 Pro
Neither model has a result on the other 9 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
AIMENot measured19.0%Only Llama 4 Scout measured
MATH 500 (Vals AI)Not measured79.2%Only Llama 4 Scout measured
MGSM (Vals AI)Not measured88.0%Only Llama 4 Scout measured
AA Math Index87.714.0Gemini 2.5 Pro
AIME 2025 (Artificial Analysis run)87.7%14.0%Gemini 2.5 Pro
OTIS Mock AIME84.7%7.8%Gemini 2.5 Pro
FrontierMath, tiers 1 to 324.6%Not measuredOnly Gemini 2.5 Pro measured
FrontierMath, tier 40.0%Not measuredOnly Gemini 2.5 Pro measured
MATH level 5Not measured62.3%Only Llama 4 Scout measured
LMArena Text: math14501287Gemini 2.5 Pro
LMArena Text: mathematical work14541286Gemini 2.5 Pro
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index80
Knowledge benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
MMLU ProNot measured69.6%Only Llama 4 Scout measured
LegalBench (Vals AI)Not measured72.0%Only Llama 4 Scout measured
CaseLaw (Vals AI)63.9%Not measuredOnly Gemini 2.5 Pro measured
CorpFin (Vals AI)60.8%46.8%Gemini 2.5 Pro
TaxEval (Vals AI)Not measured55.2%Only Llama 4 Scout measured
MortgageTax (Vals AI)68.9%57.8%Gemini 2.5 Pro
MedQA (Vals AI)Not measured50.9%Only Llama 4 Scout measured
MedCode (Vals AI)50.6%23.3%Gemini 2.5 Pro
MMLU Pro (Artificial Analysis run)86.2%75.2%Gemini 2.5 Pro
LMArena Text: science14801278Gemini 2.5 Pro
LMArena Text: medicine and healthcare14761275Gemini 2.5 Pro
LMArena Text: legal and government14801285Gemini 2.5 Pro
LMArena Text: business and finance14391257Gemini 2.5 Pro
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index50
Web design benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
Design Arena: websites1167750Gemini 2.5 Pro
Design Arena: UI components1139767Gemini 2.5 Pro
Design Arena: game dev1112773Gemini 2.5 Pro
Design Arena: data viz1222896Gemini 2.5 Pro
Design Arena: 3D1080Not measuredOnly Gemini 2.5 Pro measured
Design Arena: all code categories1152790Gemini 2.5 Pro
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index290
General benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
SAGE (Vals AI)41.9%34.8%Gemini 2.5 Pro
MedScribe (Vals AI)73.5%50.6%Gemini 2.5 Pro
IFBench48.7%39.5%Gemini 2.5 Pro
Long context reasoning (AA-LCR)69.0%27.7%Gemini 2.5 Pro
DTBench82.4%57.9%Gemini 2.5 Pro
LMCA34.8%12.0%Gemini 2.5 Pro
Fiction.LiveBenchNot measured36.0%Only Llama 4 Scout measured
Creative writing (Lech Mazur)83.8%Not measuredOnly Gemini 2.5 Pro measured
LMArena Text14581279Gemini 2.5 Pro
LMArena Text: instruction following14371248Gemini 2.5 Pro
LMArena Text: creative writing14541249Gemini 2.5 Pro
LMArena Vision12631118Gemini 2.5 Pro
LMArena Text: English14581304Gemini 2.5 Pro
LMArena Text: non-English14521252Gemini 2.5 Pro
LMArena Text: Chinese15071255Gemini 2.5 Pro
LMArena Text: German14871273Gemini 2.5 Pro
LMArena Text: Japanese14611206Gemini 2.5 Pro
LMArena Text: Korean14341207Gemini 2.5 Pro
LMArena Text: French14731283Gemini 2.5 Pro
LMArena Text: Spanish14741278Gemini 2.5 Pro
LMArena Text: Russian14611263Gemini 2.5 Pro
LMArena Text: Polish14791265Gemini 2.5 Pro
LMArena Text: multi-turn14531280Gemini 2.5 Pro
LMArena Text: longer queries14491265Gemini 2.5 Pro
LMArena Text: writing and language14541269Gemini 2.5 Pro
LMArena Text: entertainment and media14411242Gemini 2.5 Pro
LMArena Vision: English12611143Gemini 2.5 Pro
LMArena Vision: Chinese13001106Gemini 2.5 Pro
LMArena Vision: reading text12701117Gemini 2.5 Pro
LMArena Vision: humor12621102Gemini 2.5 Pro
LMArena Vision: captioning1304Not measuredOnly Gemini 2.5 Pro measured
LMArena Vision: recognizing things1283Not measuredOnly Gemini 2.5 Pro measured
LMArena Vision: creative writing12651126Gemini 2.5 Pro
LMArena Document1421Not measuredOnly Gemini 2.5 Pro measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 2.5 Pro and Llama 4 Scout
BenchmarkGemini 2.5 ProLlama 4 ScoutLeader
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 Pro$0.0063Fits in one request
Llama 4 Scout$0.0003Fits in one request

Llama 4 Scout costs less

Repository review

50K input + 3K output tokens

Gemini 2.5 Pro$0.092Fits in one request
Llama 4 Scout$0.0059Fits in one request

Llama 4 Scout costs less

Agent loop

200K input + 10K output tokens

Gemini 2.5 Pro$0.350Fits in one request
Llama 4 Scout$0.023Fits in one request

Llama 4 Scout 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 Pro and Llama 4 Scout
SpecificationGoogle Gemini 2.5 ProMeta Llama 4 Scout
MakerGoogleMeta Llama
WeightsNo public weights listedOpen weights
ReleasedJune 17, 2025April 5, 2025
Context window1.05M1.31M
Input $/Mtok$1.25$0.10
Output $/Mtok$10.00$0.30
Coding index37.09.1
Independent measurements behind it21
Cost per solved task$0.64$1.276
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 2.5 Pro better than Llama 4 Scout for coding?

Pick Gemini 2.5 Pro for coding: it scores 37.0 on the Vibe Coding Index against 9.1 for Llama 4 Scout. Pick Llama 4 Scout when output tokens cost 33.3x less, or when the context window is larger, 1.31M against 1.05M tokens.

Which is cheaper, Gemini 2.5 Pro or Llama 4 Scout?

Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens; Llama 4 Scout costs $0.10 and $0.30. Per solved SWE-bench Verified task, Gemini 2.5 Pro costs $0.64 and Llama 4 Scout $1.276.

Which has the bigger context window, Gemini 2.5 Pro or Llama 4 Scout?

Llama 4 Scout, with 1.31M tokens against 1.05M.

How many benchmarks is the Gemini 2.5 Pro vs Llama 4 Scout comparison based on?

68 benchmarks have a result for both models as of October 21, 2026. Gemini 2.5 Pro's coding index rests on 2 independent benchmarks and Llama 4 Scout's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next