Noometry

Model comparison

Llama 4 Scout vs Qwen1.5-72B

Qwen1.5-72B is the stronger model overall, scoring 30.3 to 27.4 on the Noometry Index.

Last verified . 19 shared benchmarks.

Llama 4 Scout Meta

27.4

Rank #323 Confirmed

Qwen1.5-72B Alibaba (Qwen)

30.3

Rank #282 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Llama 4 Scout scores higher in 3 categories and Qwen1.5-72B in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Llama 4 Scout leads 31.8 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 51.8% for Llama 4 Scout and 28.8% for Qwen1.5-72B.

Side by side

Llama 4 ScoutQwen1.5-72B
ProviderMetaAlibaba (Qwen)
Noometry Index27.430.3
Released2025-04-052024-02-04
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.30—
Results tracked4322

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

Category by category

Coding Qwen1.5-72B leads

Llama 4 Scout: 19.9 (#334), Qwen1.5-72B: 31.4 (#272)

BenchmarkLlama 4 ScoutQwen1.5-72B
LMArena Coding12861166
BigCodeBench Complete43.1%40.3%
SWE-bench Verified (bash only)9.1%—
SciCode17%—
BigCodeBench Instruct—33.2%
HumanEval+—59.1%
MBPP+—61.6%

Agentic & Tool Use Not comparable

Llama 4 Scout: 24.4 (#109), Qwen1.5-72B: —

BenchmarkLlama 4 ScoutQwen1.5-72B
Berkeley Function Calling Leaderboard28.1%—

Reasoning Qwen1.5-72B leads

Llama 4 Scout: 9.2 (#339), Qwen1.5-72B: 21.2 (#201)

BenchmarkLlama 4 ScoutQwen1.5-72B
LMArena Hard Prompts12661148
ARC-AGI-20%—
Kagi LLM Benchmark36.9%—
ARC-AGI-10.5%—
CritPt0%—
DTBench57.9%—
LMCA12%—
Epoch Capabilities Index129.64—
ForecastBench57.5—

Math Qwen1.5-72B leads

Llama 4 Scout: 18.4 (#280), Qwen1.5-72B: 30.7 (#205)

BenchmarkLlama 4 ScoutQwen1.5-72B
LMArena Math12861164
OTIS Mock AIME 2024-20257.8%—
Omni-MATH37.3%—
MATH Level 562.3%—
FrontierMath (Feb 2025 set)0%—

Knowledge Llama 4 Scout leads

Llama 4 Scout: 31.8 (#208), Qwen1.5-72B: 11.5 (#295)

BenchmarkLlama 4 ScoutQwen1.5-72B
GPQA Diamond51.8%28.8%
LMArena Expert12361136
MMLU-Pro74.2%—
Vectara Hallucination Rate7.7%—
GPQA (HELM)50.7%—

Multimodal Not comparable

Llama 4 Scout: 31.6 (#98), Qwen1.5-72B: —

BenchmarkLlama 4 ScoutQwen1.5-72B
LMArena Vision1118—
SpatialViz-Bench34.2%—

Multilingual Llama 4 Scout leads

Llama 4 Scout: 41.3 (#207), Qwen1.5-72B: 33.4 (#248)

BenchmarkLlama 4 ScoutQwen1.5-72B
LMArena Non-English12531135
LMArena Chinese12561186
LMArena French12831158
LMArena German12741084
LMArena Japanese12091061
LMArena Korean12071049
LMArena Russian12631104
LMArena Spanish12771110

Instruction Following Llama 4 Scout leads

Llama 4 Scout: 66.0 (#212), Qwen1.5-72B: 59.6 (#251)

BenchmarkLlama 4 ScoutQwen1.5-72B
LMArena Instruction Following12481142
IFEval81.8%—

Long Context Qwen1.5-72B leads

Llama 4 Scout: 27.5 (#289), Qwen1.5-72B: 35.0 (#238)

BenchmarkLlama 4 ScoutQwen1.5-72B
LMArena Longer Query12651157
Fiction.LiveBench36%—

Writing & Preference Too close to call

Llama 4 Scout: 37.1 (#256), Qwen1.5-72B: 37.4 (#253)

BenchmarkLlama 4 ScoutQwen1.5-72B
LMArena Text12791166
LMArena Creative Writing12491137
LMArena Multi-Turn12811160
EQ-Bench Creative Writing783—
WildBench78%—

Frequently asked questions

Is Llama 4 Scout better than Qwen1.5-72B?

Qwen1.5-72B is the stronger model overall, scoring 30.3 to 27.4 on the Noometry Index.

Is Llama 4 Scout or Qwen1.5-72B better for coding?

Qwen1.5-72B scores higher on coding benchmarks: 31.4 versus 19.9 in the Noometry coding category.

How many benchmarks do Llama 4 Scout and Qwen1.5-72B share?

19 benchmarks have published results for both models. Llama 4 Scout has 43 scored results on Noometry and Qwen1.5-72B has 22.

Related comparisons

Go deeper