Noometry

Model comparison

Gemini 3.7 Flash vs Llama 4 Maverick

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 30.6 on the Noometry Index. Llama 4 Maverick costs 4.9× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

Last verified . 30 shared benchmarks.

Gemini 3.7 Flash Google

59.8

Rank #11 Confirmed

Llama 4 Maverick Meta

30.6

Rank #276 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Gemini 3.7 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 3.7 Flash leads 70.1 to 10.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 95.5% for Gemini 3.7 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 3.7 Flash.
  • Gemini 3.7 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 3.7 FlashLlama 4 Maverick
ProviderGoogleMeta
Noometry Index59.830.6
Released2026-08-132025-04-05
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$0.75$0.19
Output $ / M tokens$3.75$0.65
Results tracked4454

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

Category by category

Coding Gemini 3.7 Flash leads

Gemini 3.7 Flash: 55.7 (#19), Llama 4 Maverick: 26.3 (#318)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
SciCode59.8%33.1%
LMArena Coding14991302
ALE-Bench904.3172.97
DeepSWE65.5%—
FrontierCode43.6%—
SWE-bench Verified (bash only)—21%
Aider Polyglot—15.6%
LMArena WebDev1593—
FrontierSWE20.3%—
WeirdML—24.5%
BigCodeBench Instruct—49.7%
BigCodeBench Complete—61.4%

Agentic & Tool Use Gemini 3.7 Flash leads

Gemini 3.7 Flash: 42.2 (#18), Llama 4 Maverick: 27.9 (#86)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
APEX-Agents67.8%—
Berkeley Function Calling Leaderboard—37.3%
Remote Labor Index5%—
GDP.pdf23.8%—

Reasoning Gemini 3.7 Flash leads

Gemini 3.7 Flash: 70.1 (#12), Llama 4 Maverick: 10.1 (#337)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
ARC-AGI-284.6%0%
NYT Connections (extended)94%8%
ARC-AGI-195.5%4.4%
CritPt14.3%0%
LMArena Hard Prompts14971281
DTBench96.8%61.9%
LMCA50.4%15.9%
Epoch Capabilities Index157.72132.2
SimpleBench—27.7%
Kagi LLM Benchmark—55.9%
Chess Puzzles47%—
EnigmaEval—0.6%
Mystery Game Puzzles37%—
ForecastBench—57.5

Math Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.5 (#18), Llama 4 Maverick: 24.6 (#256)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
OTIS Mock AIME 2024-202597.2%20.6%
LMArena Math15111299
FrontierMath (Tiers 1-3)71.6%—
FrontierMath Tier 436.6%—
ProofBench58%—
Omni-MATH—42.2%
MATH Level 5—73%
FrontierMath (Feb 2025 set)—0.7%

Knowledge Gemini 3.7 Flash leads

Gemini 3.7 Flash: 69.8 (#4), Llama 4 Maverick: 33.3 (#196)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
GPQA Diamond94.8%67%
LMArena Expert15081259
Humanity's Last Exam—5.7%
SimpleQA Verified69.2%—
MMLU-Pro—81%
Confabulations—22.6%
Vectara Hallucination Rate—8.2%
GPQA (HELM)—65%

Multimodal Gemini 3.7 Flash leads

Gemini 3.7 Flash: 36.9 (#69), Llama 4 Maverick: 30.9 (#100)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
LMArena Vision13141141
GeoBench—52%
Furniture Assembly26.7%—
SpatialViz-Bench—31.8%

Multilingual Gemini 3.7 Flash leads

Gemini 3.7 Flash: 57.8 (#7), Llama 4 Maverick: 42.4 (#190)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
LMArena Non-English14851269
LMArena Chinese15531277
LMArena French15121258
LMArena German14851291
LMArena Japanese15061207
LMArena Korean14861203
LMArena Russian15191286
LMArena Spanish15071293

Instruction Following Gemini 3.7 Flash leads

Gemini 3.7 Flash: 78.0 (#12), Llama 4 Maverick: 71.9 (#140)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
LMArena Instruction Following14861267
IFEval—90.8%

Long Context Gemini 3.7 Flash leads

Gemini 3.7 Flash: 45.8 (#28), Llama 4 Maverick: 31.4 (#274)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
LMArena Longer Query14931280
Fiction.LiveBench—46.2%

Writing & Preference Gemini 3.7 Flash leads

Gemini 3.7 Flash: 71.4 (#19), Llama 4 Maverick: 39.0 (#247)

BenchmarkGemini 3.7 FlashLlama 4 Maverick
LMArena Text14871287
LMArena Creative Writing14901266
EQ-Bench Creative Writing1723860
LMArena Multi-Turn14951289
Short-Story Creative Writing—62%
WildBench—80%

Frequently asked questions

Is Gemini 3.7 Flash better than Llama 4 Maverick?

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 30.6 on the Noometry Index. Llama 4 Maverick costs 4.9× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

Which is cheaper, Gemini 3.7 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 3.7 Flash lists at $0.75 and $3.75.

Is Gemini 3.7 Flash or Llama 4 Maverick better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 26.3 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 3.7 Flash and Llama 4 Maverick share?

30 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Llama 4 Maverick has 54.

Related comparisons

Go deeper