Noometry

Model comparison

Gemini 2.5 Pro vs Llama 4 Maverick

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 30.9 on the Noometry Index. Llama 4 Maverick costs 11× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Last verified . 50 shared benchmarks.

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Llama 4 Maverick Meta

30.9

Rank #282 Confirmed

Summary

  • They share 50 benchmarks with published results for both. Gemini 2.5 Pro scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 31.4.
  • The biggest single-benchmark swing is Aider Polyglot: 83.1% for Gemini 2.5 Pro and 15.6% for Llama 4 Maverick.
  • Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 128K.
  • Llama 4 Maverick has downloadable open weights; the other is API-only.

Side by side

Gemini 2.5 ProLlama 4 Maverick
ProviderGoogleMeta
Noometry Index45.030.9
Released2025-03-252025-04-05
WeightsProprietaryOpen
Context window1.05M128K
Max output66K4K
Input $ / M tokens$1.25$0.19
Output $ / M tokens$10$0.65
Results tracked7854

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

Category by category

Coding Gemini 2.5 Pro leads

Gemini 2.5 Pro: 42.4 (#101), Llama 4 Maverick: 26.6 (#324)

BenchmarkGemini 2.5 ProLlama 4 Maverick
SWE-bench Verified (bash only)53.6%21%
Aider Polyglot83.1%15.6%
SciCode42.8%33.1%
WeirdML54%24.5%
LMArena Coding14521302
ALE-Bench785.52172.97
SWE-bench Verified57.6%—
LMArena WebDev1227—
GSO3.9%—
BigCodeBench Instruct—49.7%
LiveBench Coding85.9%—
BigCodeBench Complete—61.4%
CadEval64%—
AlgoTune1.51—

Agentic & Tool Use Gemini 2.5 Pro leads

Gemini 2.5 Pro: 29.2 (#88), Llama 4 Maverick: 28.2 (#91)

BenchmarkGemini 2.5 ProLlama 4 Maverick
Terminal-Bench32.6%—
Berkeley Function Calling Leaderboard—37.3%
GDPval23.3%—
Remote Labor Index0.8%—
TheAgentCompany30.3%—
τ²-bench Banking13.7%—
DeepResearch Bench42.8%—
BALROG43.3%—
LMArena Search1142—
METR Time Horizons55.4%—
Vending-Bench 2573.64—

Reasoning Gemini 2.5 Pro leads

Gemini 2.5 Pro: 28.8 (#99), Llama 4 Maverick: 10.1 (#342)

BenchmarkGemini 2.5 ProLlama 4 Maverick
ARC-AGI-24.9%0%
SimpleBench62.4%27.7%
Kagi LLM Benchmark70.3%55.9%
ARC-AGI-141%4.4%
CritPt2%0%
EnigmaEval5.6%0.6%
LMArena Hard Prompts14551281
DTBench82.4%61.9%
LMCA34.8%15.9%
Epoch Capabilities Index145.32132.2
ForecastBench61.357.5
NYT Connections (extended)—8%
Chess Puzzles20%—
LiveBench Reasoning89.8%—
LiveBench Data Analysis79.9%—
LiveBench82.3%—

Math Gemini 2.5 Pro leads

Gemini 2.5 Pro: 32.5 (#213), Llama 4 Maverick: 26.0 (#262)

BenchmarkGemini 2.5 ProLlama 4 Maverick
OTIS Mock AIME 2024-202584.7%20.6%
Omni-MATH41.6%42.2%
LMArena Math14501299
MATH Level 595.9%73%
FrontierMath (Feb 2025 set)14.1%0.7%
FrontierMath (Tiers 1-3)24.6%—
FrontierMath Tier 40%—
LiveBench Math90.2%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Gemini 2.5 Pro leads

Gemini 2.5 Pro: 56.0 (#46), Llama 4 Maverick: 33.4 (#204)

BenchmarkGemini 2.5 ProLlama 4 Maverick
GPQA Diamond85.3%67%
Humanity's Last Exam21.6%5.7%
MMLU-Pro86.3%81%
Confabulations10.6%22.6%
Vectara Hallucination Rate7%8.2%
GPQA (HELM)74.9%65%
LMArena Expert14521259

Multimodal Gemini 2.5 Pro leads

Gemini 2.5 Pro: 45.2 (#18), Llama 4 Maverick: 31.6 (#105)

BenchmarkGemini 2.5 ProLlama 4 Maverick
LMArena Vision12631142
GeoBench86%52%
SpatialViz-Bench44.7%31.8%
VPCT48%—
LMArena Document1421—

Multilingual Gemini 2.5 Pro leads

Gemini 2.5 Pro: 55.3 (#31), Llama 4 Maverick: 42.2 (#195)

BenchmarkGemini 2.5 ProLlama 4 Maverick
LMArena Non-English14511269
LMArena Chinese15071277
LMArena French14721259
LMArena German14871291
LMArena Japanese14611207
LMArena Korean14341203
LMArena Russian14611286
LMArena Spanish14731293

Instruction Following Gemini 2.5 Pro leads

Gemini 2.5 Pro: 75.0 (#75), Llama 4 Maverick: 71.7 (#146)

BenchmarkGemini 2.5 ProLlama 4 Maverick
IFEval84%90.8%
LMArena Instruction Following14371267
LiveBench Instruction Following80.6%—

Long Context Gemini 2.5 Pro leads

Gemini 2.5 Pro: 59.8 (#5), Llama 4 Maverick: 31.4 (#279)

BenchmarkGemini 2.5 ProLlama 4 Maverick
Fiction.LiveBench91.7%46.2%
LMArena Longer Query14491280

Writing & Preference Gemini 2.5 Pro leads

Gemini 2.5 Pro: 63.7 (#62), Llama 4 Maverick: 38.8 (#252)

BenchmarkGemini 2.5 ProLlama 4 Maverick
LMArena Text14581287
LMArena Creative Writing14541267
Short-Story Creative Writing83.8%62%
EQ-Bench Creative Writing1421860
WildBench85.7%80%
LMArena Multi-Turn14531289
LiveBench Language67.8%—

Frequently asked questions

Is Gemini 2.5 Pro better than Llama 4 Maverick?

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 30.9 on the Noometry Index. Llama 4 Maverick costs 11× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Which is cheaper, Gemini 2.5 Pro 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 2.5 Pro lists at $1.25 and $10.

Is Gemini 2.5 Pro or Llama 4 Maverick better for coding?

Gemini 2.5 Pro scores higher on coding benchmarks: 42.4 versus 26.6 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 128K.

How many benchmarks do Gemini 2.5 Pro and Llama 4 Maverick share?

50 benchmarks have published results for both models. Gemini 2.5 Pro has 78 scored results on Noometry and Llama 4 Maverick has 54.

Related comparisons

Go deeper