Noometry

Model comparison

Gemini 3 Flash Preview vs Llama 4 Maverick

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 3.7× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Gemini 3 Flash Preview Google

52.3

Rank #40 Confirmed

Llama 4 Maverick Meta

30.9

Rank #282 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Gemini 3 Flash Preview scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Gemini 3 Flash Preview leads 49.2 to 10.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 84.7% for Gemini 3 Flash Preview and 4.4% for Llama 4 Maverick.
  • Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.50 / $3 for Gemini 3 Flash Preview.
  • Gemini 3 Flash Preview accepts more context: 1.05M tokens versus 128K.
  • Llama 4 Maverick has downloadable open weights; the other is API-only.

Side by side

Gemini 3 Flash PreviewLlama 4 Maverick
ProviderGoogleMeta
Noometry Index52.330.9
Released2025-12-172025-04-05
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$0.50$0.19
Output $ / M tokens$3$0.65
Results tracked5954

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 50.9 (#42), Llama 4 Maverick: 26.6 (#324)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
SWE-bench Verified (bash only)75.8%21%
WeirdML61.6%24.5%
LMArena Coding14601302
ALE-Bench1,367172.97
SWE-bench Verified75.4%—
Aider Polyglot—15.6%
LMArena WebDev1439—
SWE-bench Multilingual72.7%—
SciCode—33.1%
GSO9.8%—
BigCodeBench Instruct—49.7%
BigCodeBench Complete—61.4%

Agentic & Tool Use Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 38.7 (#29), Llama 4 Maverick: 28.2 (#91)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
Terminal-Bench64.3%—
Berkeley Function Calling Leaderboard—37.3%
τ²-bench Airline82.5%—
τ²-bench Banking27.3%—
τ²-bench Retail76.8%—
τ²-bench Telecom91.2%—
DeepResearch Bench49.8%—
BALROG48.1%—
GDP.pdf10%—
LMArena Search1198—
Vending-Bench 23,635—

Reasoning Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 49.2 (#37), Llama 4 Maverick: 10.1 (#342)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
ARC-AGI-233.6%0%
SimpleBench61.1%27.7%
NYT Connections (extended)83.1%8%
ARC-AGI-184.7%4.4%
LMArena Hard Prompts14651281
DTBench89.1%61.9%
LMCA43.1%15.9%
Epoch Capabilities Index151.8132.2
ForecastBench58.557.5
Kagi LLM Benchmark—55.9%
CritPt—0%
Chess Puzzles40%—
EnigmaEval—0.6%
Mystery Game Puzzles26%—

Math Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 51.7 (#55), Llama 4 Maverick: 26.0 (#262)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
OTIS Mock AIME 2024-202595.6%20.6%
LMArena Math14731299
FrontierMath (Feb 2025 set)35.6%0.7%
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 417.1%—
MathArena Final-Answer Competitions67.6%—
ProofBench15%—
Omni-MATH—42.2%
MATH Level 5—73%
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 58.8 (#33), Llama 4 Maverick: 33.4 (#204)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
GPQA Diamond89.4%67%
Vectara Hallucination Rate13.5%8.2%
LMArena Expert14621259
Humanity's Last Exam—5.7%
SimpleQA Verified66.8%—
MMLU-Pro—81%
Confabulations—22.6%
GPQA (HELM)—65%

Multimodal Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 45.5 (#16), Llama 4 Maverick: 31.6 (#105)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
LMArena Vision12851142
GeoBench88%52%
VPCT72.6%—
Blueprint-Bench 20%—
LMArena Document1413—
SpatialViz-Bench—31.8%

Multilingual Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 55.7 (#27), Llama 4 Maverick: 42.2 (#195)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
LMArena Non-English14581269
LMArena Chinese15111277
LMArena French14771259
LMArena German14971291
LMArena Japanese14891207
LMArena Korean14431203
LMArena Russian14801286
LMArena Spanish14691293

Instruction Following Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 75.7 (#56), Llama 4 Maverick: 71.7 (#146)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
LMArena Instruction Following14371267
IFEval—90.8%

Long Context Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 44.4 (#67), Llama 4 Maverick: 31.4 (#279)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
LMArena Longer Query14521280
Fiction.LiveBench—46.2%

Writing & Preference Gemini 3 Flash Preview leads

Gemini 3 Flash Preview: 65.5 (#45), Llama 4 Maverick: 38.8 (#252)

BenchmarkGemini 3 Flash PreviewLlama 4 Maverick
LMArena Text14661287
LMArena Creative Writing14571267
LMArena Multi-Turn14711289
Short-Story Creative Writing—62%
EQ-Bench Creative Writing—860
WildBench—80%

Frequently asked questions

Is Gemini 3 Flash Preview better than Llama 4 Maverick?

Gemini 3 Flash Preview is the stronger model overall, scoring 52.3 to 30.9 on the Noometry Index. Llama 4 Maverick costs 3.7× less per token, which makes it the better buy when Gemini 3 Flash Preview's lead doesn't matter for your workload.

Which is cheaper, Gemini 3 Flash Preview or Llama 4 Maverick?

Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Gemini 3 Flash Preview lists at $0.50 and $3.

Is Gemini 3 Flash Preview or Llama 4 Maverick better for coding?

Gemini 3 Flash Preview scores higher on coding benchmarks: 50.9 versus 26.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 3 Flash Preview does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 3 Flash Preview and Llama 4 Maverick share?

34 benchmarks have published results for both models. Gemini 3 Flash Preview has 59 scored results on Noometry and Llama 4 Maverick has 54.

Related comparisons

Go deeper