Noometry

Model comparison

Llama 4 Maverick vs Qwen1.5-7B

Llama 4 Maverick and Qwen1.5-7B score almost the same on the Noometry Index (30.6 vs 30.8), so choose on price, context window or the category you care about most.

Last verified . 12 shared benchmarks.

Llama 4 Maverick Meta

30.6

Rank #276 Confirmed

Qwen1.5-7B Alibaba (Qwen)

30.8

Rank #270 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Llama 4 Maverick scores higher in 4 categories and Qwen1.5-7B in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in instruction following, where Llama 4 Maverick leads 71.9 to 54.4.

Side by side

Llama 4 MaverickQwen1.5-7B
ProviderMetaAlibaba (Qwen)
Noometry Index30.630.8
Released2025-04-052024-02-04
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.19—
Output $ / M tokens$0.65—
Results tracked5413

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

Category by category

Coding Qwen1.5-7B leads

Llama 4 Maverick: 26.3 (#318), Qwen1.5-7B: 31.6 (#271)

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Coding13021107
SWE-bench Verified (bash only)21%—
Aider Polyglot15.6%—
SciCode33.1%—
WeirdML24.5%—
BigCodeBench Instruct49.7%—
BigCodeBench Complete61.4%—
ALE-Bench172.97—

Agentic & Tool Use Not comparable

Llama 4 Maverick: 27.9 (#86), Qwen1.5-7B: —

BenchmarkLlama 4 MaverickQwen1.5-7B
Berkeley Function Calling Leaderboard37.3%—

Reasoning Qwen1.5-7B leads

Llama 4 Maverick: 10.1 (#337), Qwen1.5-7B: 19.5 (#237)

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Hard Prompts12811066
ARC-AGI-20%—
SimpleBench27.7%—
Kagi LLM Benchmark55.9%—
NYT Connections (extended)8%—
ARC-AGI-14.4%—
CritPt0%—
EnigmaEval0.6%—
DTBench61.9%—
LMCA15.9%—
Epoch Capabilities Index132.2—
ForecastBench57.5—

Math Qwen1.5-7B leads

Llama 4 Maverick: 24.6 (#256), Qwen1.5-7B: 29.0 (#222)

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Math12991080
OTIS Mock AIME 2024-202520.6%—
Omni-MATH42.2%—
MATH Level 573%—
FrontierMath (Feb 2025 set)0.7%—

Knowledge Llama 4 Maverick leads

Llama 4 Maverick: 33.3 (#196), Qwen1.5-7B: 28.2 (#239)

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Expert12591055
GPQA Diamond67%—
Humanity's Last Exam5.7%—
MMLU-Pro81%—
Confabulations22.6%—
Vectara Hallucination Rate8.2%—
GPQA (HELM)65%—
MMLU—62.6%

Multimodal Not comparable

Llama 4 Maverick: 30.9 (#100), Qwen1.5-7B: —

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Vision1141—
GeoBench52%—
SpatialViz-Bench31.8%—

Multilingual Llama 4 Maverick leads

Llama 4 Maverick: 42.4 (#190), Qwen1.5-7B: 28.6 (#266)

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Non-English12691058
LMArena Chinese12771140
LMArena Russian12861006
LMArena French1258—
LMArena German1291—
LMArena Japanese1207—
LMArena Korean1203—
LMArena Spanish1293—

Instruction Following Llama 4 Maverick leads

Llama 4 Maverick: 71.9 (#140), Qwen1.5-7B: 54.4 (#276)

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Instruction Following12671058
IFEval90.8%—

Long Context Qwen1.5-7B leads

Llama 4 Maverick: 31.4 (#274), Qwen1.5-7B: 33.1 (#261)

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Longer Query12801090
Fiction.LiveBench46.2%—

Writing & Preference Llama 4 Maverick leads

Llama 4 Maverick: 39.0 (#247), Qwen1.5-7B: 29.8 (#288)

BenchmarkLlama 4 MaverickQwen1.5-7B
LMArena Text12871084
LMArena Creative Writing12661035
LMArena Multi-Turn12891061
Short-Story Creative Writing62%—
EQ-Bench Creative Writing860—
WildBench80%—

Frequently asked questions

Is Llama 4 Maverick better than Qwen1.5-7B?

Llama 4 Maverick and Qwen1.5-7B score almost the same on the Noometry Index (30.6 vs 30.8), so choose on price, context window or the category you care about most.

Is Llama 4 Maverick or Qwen1.5-7B better for coding?

Qwen1.5-7B scores higher on coding benchmarks: 31.6 versus 26.3 in the Noometry coding category.

How many benchmarks do Llama 4 Maverick and Qwen1.5-7B share?

12 benchmarks have published results for both models. Llama 4 Maverick has 54 scored results on Noometry and Qwen1.5-7B has 13.

Related comparisons

Go deeper