Noometry

Model comparison

Gemini 3.8 Flash vs Llama 4 Maverick

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 30.9 on the Noometry Index. Llama 4 Maverick costs 4.9× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

Last verified . 32 shared benchmarks.

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Llama 4 Maverick Meta

30.9

Rank #282 Confirmed

Summary

  • They share 32 benchmarks with published results for both. Gemini 3.8 Flash 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 3.8 Flash leads 76.9 to 10.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 98.5% for Gemini 3.8 Flash and 4.4% for Llama 4 Maverick.
  • Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
  • Gemini 3.8 Flash accepts more context: 1.05M tokens versus 128K.
  • Llama 4 Maverick has downloadable open weights; the other is API-only.

Side by side

Gemini 3.8 FlashLlama 4 Maverick
ProviderGoogleMeta
Noometry Index61.830.9
Released2026-09-022025-04-05
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$0.75$0.19
Output $ / M tokens$3.75$0.65
Results tracked5054

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

Category by category

Coding Gemini 3.8 Flash leads

Gemini 3.8 Flash: 59.2 (#15), Llama 4 Maverick: 26.6 (#324)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
SciCode56.6%33.1%
WeirdML84.8%24.5%
LMArena Coding15101302
ALE-Bench1,270172.97
DeepSWE73.8%—
FrontierCode41.2%—
SWE-bench Verified (bash only)—21%
Aider Polyglot—15.6%
CursorBench39.6%—
LMArena WebDev1584—
FrontierSWE19.6%—
BigCodeBench Instruct—49.7%
BigCodeBench Complete—61.4%

Agentic & Tool Use Gemini 3.8 Flash leads

Gemini 3.8 Flash: 41.8 (#21), Llama 4 Maverick: 28.2 (#91)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
APEX-Agents64.3%—
Berkeley Function Calling Leaderboard—37.3%
Remote Labor Index5.8%—
GDP.pdf23.4%—
Vending-Bench 25,094—

Reasoning Gemini 3.8 Flash leads

Gemini 3.8 Flash: 76.9 (#5), Llama 4 Maverick: 10.1 (#342)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
ARC-AGI-289.2%0%
NYT Connections (extended)97.4%8%
ARC-AGI-198.5%4.4%
CritPt18.3%0%
LMArena Hard Prompts15081281
DTBench95.7%61.9%
LMCA52.9%15.9%
Epoch Capabilities Index156.71132.2
SimpleBench—27.7%
Kagi LLM Benchmark—55.9%
Chess Puzzles61%—
EnigmaEval—0.6%
Mystery Game Puzzles47%—
Surface Evolver Bench76.9%—
ForecastBench—57.5

Math Gemini 3.8 Flash leads

Gemini 3.8 Flash: 65.3 (#28), Llama 4 Maverick: 26.0 (#262)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
OTIS Mock AIME 2024-202598.9%20.6%
LMArena Math15281299
FrontierMath (Tiers 1-3)68.4%—
FrontierMath Tier 422%—
ProofBench48%—
Omni-MATH—42.2%
MATH Level 5—73%
FrontierMath (Feb 2025 set)—0.7%

Knowledge Gemini 3.8 Flash leads

Gemini 3.8 Flash: 74.8 (#2), Llama 4 Maverick: 33.4 (#204)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
GPQA Diamond95.4%67%
Humanity's Last Exam44.5%5.7%
LMArena Expert15241259
SimpleQA Verified69.7%—
MMLU-Pro—81%
Confabulations—22.6%
Vectara Hallucination Rate—8.2%
GPQA (HELM)—65%

Multimodal Gemini 3.8 Flash leads

Gemini 3.8 Flash: 40.7 (#45), Llama 4 Maverick: 31.6 (#105)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
LMArena Vision13141142
GeoBench—52%
Blueprint-Bench 238.6%—
Furniture Assembly31.7%—
SpatialViz-Bench—31.8%

Multilingual Gemini 3.8 Flash leads

Gemini 3.8 Flash: 58.0 (#5), Llama 4 Maverick: 42.2 (#195)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
LMArena Non-English14911269
LMArena Chinese15541277
LMArena French14981259
LMArena German14931291
LMArena Japanese15021207
LMArena Korean14591203
LMArena Russian15151286
LMArena Spanish14851293

Instruction Following Gemini 3.8 Flash leads

Gemini 3.8 Flash: 78.0 (#13), Llama 4 Maverick: 71.7 (#146)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
LMArena Instruction Following14901267
IFEval—90.8%

Long Context Gemini 3.8 Flash leads

Gemini 3.8 Flash: 46.3 (#24), Llama 4 Maverick: 31.4 (#279)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
LMArena Longer Query15081280
Fiction.LiveBench—46.2%

Writing & Preference Gemini 3.8 Flash leads

Gemini 3.8 Flash: 72.2 (#15), Llama 4 Maverick: 38.8 (#252)

BenchmarkGemini 3.8 FlashLlama 4 Maverick
LMArena Text14991287
LMArena Creative Writing14921267
EQ-Bench Creative Writing1748860
LMArena Multi-Turn15011289
Short-Story Creative Writing—62%
WildBench—80%

Frequently asked questions

Is Gemini 3.8 Flash better than Llama 4 Maverick?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 30.9 on the Noometry Index. Llama 4 Maverick costs 4.9× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.8 Flash 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 3.8 Flash lists at $0.75 and $3.75.

Is Gemini 3.8 Flash or Llama 4 Maverick better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 26.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 3.8 Flash and Llama 4 Maverick share?

32 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Llama 4 Maverick has 54.

Related comparisons

Go deeper