Noometry

Model comparison

Llama 4 Maverick vs Mercury 2.5

Llama 4 Maverick has enough public results to be ranked (#276); Mercury 2.5 does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Llama 4 Maverick Meta

30.6

Rank #276 Confirmed

Mercury 2.5 Inception

30.2

Unranked Sparse

Summary

  • They share 1 benchmark with published results for both. Llama 4 Maverick scores higher in 1 category and Mercury 2.5 in 0 categories; one gap is clear of the uncertainty.
  • Mercury 2.5 is cheaper at $0.04 / $0.15 per million input/output tokens, against $0.19 / $0.65 for Llama 4 Maverick.
  • Mercury 2.5 accepts more context: 260K tokens versus 128K.
  • Llama 4 Maverick has downloadable open weights; the other is API-only.

Side by side

Llama 4 MaverickMercury 2.5
ProviderMetaInception
Noometry Index30.630.2
Released2025-04-052026-09-08
WeightsOpenProprietary
Context window128K260K
Max output4K66K
Input $ / M tokens$0.19$0.04
Output $ / M tokens$0.65$0.15
Results tracked542

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

Category by category

Coding Not comparable

Llama 4 Maverick: 26.3 (#318), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
ALE-Bench172.97301.65
SWE-bench Verified (bash only)21%—
Aider Polyglot15.6%—
SciCode33.1%—
WeirdML24.5%—
BigCodeBench Instruct49.7%—
LMArena Coding1302—
BigCodeBench Complete61.4%—

Agentic & Tool Use Not comparable

Llama 4 Maverick: 27.9 (#86), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
Berkeley Function Calling Leaderboard37.3%—

Reasoning Not comparable

Llama 4 Maverick: 10.1 (#337), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
ARC-AGI-20%—
SimpleBench27.7%—
Kagi LLM Benchmark55.9%—
NYT Connections (extended)8%—
ARC-AGI-14.4%—
CritPt0%—
EnigmaEval0.6%—
LMArena Hard Prompts1281—
DTBench61.9%—
LMCA15.9%—
Epoch Capabilities Index132.2—
ForecastBench57.5—

Math Llama 4 Maverick leads

Llama 4 Maverick: 24.6 (#256), Mercury 2.5: 22.4

BenchmarkLlama 4 MaverickMercury 2.5
OTIS Mock AIME 2024-202520.6%—
ProofBench—3%
Omni-MATH42.2%—
LMArena Math1299—
MATH Level 573%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Not comparable

Llama 4 Maverick: 33.3 (#196), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
GPQA Diamond67%—
Humanity's Last Exam5.7%—
MMLU-Pro81%—
Confabulations22.6%—
Vectara Hallucination Rate8.2%—
GPQA (HELM)65%—
LMArena Expert1259—

Multimodal Not comparable

Llama 4 Maverick: 30.9 (#100), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
LMArena Vision1141—
GeoBench52%—
SpatialViz-Bench31.8%—

Multilingual Not comparable

Llama 4 Maverick: 42.4 (#190), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
LMArena Non-English1269—
LMArena Chinese1277—
LMArena French1258—
LMArena German1291—
LMArena Japanese1207—
LMArena Korean1203—
LMArena Russian1286—
LMArena Spanish1293—

Instruction Following Not comparable

Llama 4 Maverick: 71.9 (#140), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
IFEval90.8%—
LMArena Instruction Following1267—

Long Context Not comparable

Llama 4 Maverick: 31.4 (#274), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
Fiction.LiveBench46.2%—
LMArena Longer Query1280—

Writing & Preference Not comparable

Llama 4 Maverick: 39.0 (#247), Mercury 2.5: —

BenchmarkLlama 4 MaverickMercury 2.5
LMArena Text1287—
LMArena Creative Writing1266—
Short-Story Creative Writing62%—
EQ-Bench Creative Writing860—
WildBench80%—
LMArena Multi-Turn1289—

Frequently asked questions

Is Llama 4 Maverick better than Mercury 2.5?

Llama 4 Maverick has enough public results to be ranked (#276); Mercury 2.5 does not yet, so treat this comparison as directional.

Which is cheaper, Llama 4 Maverick or Mercury 2.5?

Mercury 2.5 is cheaper. It lists at $0.04 per million input tokens and $0.15 per million output tokens; Llama 4 Maverick lists at $0.19 and $0.65.

Which has the bigger context window?

Mercury 2.5 does, with 260K tokens against 128K.

How many benchmarks do Llama 4 Maverick and Mercury 2.5 share?

1 benchmark has published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Mercury 2.5 has 2.

Related comparisons

Go deeper