Noometry

Model comparison

Llama-3.3-70B-Instruct vs Qwen1.5-32B

Llama-3.3-70B-Instruct and Qwen1.5-32B score almost the same on the Noometry Index (30.6 vs 30.5), so choose on price, context window or the category you care about most.

Last verified . 21 shared benchmarks.

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Qwen1.5-32B in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen1.5-32B leads 33.0 to 15.3.
  • The biggest single-benchmark swing is GPQA Diamond: 47.4% for Llama-3.3-70B-Instruct and 30.7% for Qwen1.5-32B.

Side by side

Llama-3.3-70B-InstructQwen1.5-32B
ProviderMetaAlibaba (Qwen)
Noometry Index30.630.5
Released2024-12-062024-02-04
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.32—
Results tracked4321

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

Category by category

Coding Too close to call

Llama-3.3-70B-Instruct: 31.0 (#290), Qwen1.5-32B: 31.7 (#282)

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
BigCodeBench Instruct46.9%32.3%
LMArena Coding12681155
BigCodeBench Complete57.5%42%
SciCode26%—
WeirdML14.4%—
LiveBench Coding36.6%—

Agentic & Tool Use Not comparable

Llama-3.3-70B-Instruct: 25.8 (#105), Qwen1.5-32B: —

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
Berkeley Function Calling Leaderboard31.9%—
BALROG23%—

Reasoning Qwen1.5-32B leads

Llama-3.3-70B-Instruct: 14.1 (#327), Qwen1.5-32B: 21.8 (#212)

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
LMArena Hard Prompts12571130
SimpleBench19.9%—
CritPt0%—
LiveBench Reasoning50.8%—
DTBench59.5%—
LiveBench Data Analysis49.5%—
LMCA17.5%—
Epoch Capabilities Index127.33—
ForecastBench58.6—
LiveBench50.2%—

Math Qwen1.5-32B leads

Llama-3.3-70B-Instruct: 15.3 (#298), Qwen1.5-32B: 33.0 (#207)

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
LMArena Math12671155
OTIS Mock AIME 2024-20255.1%—
LiveBench Math42.2%—
MATH Level 541.6%—

Knowledge Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 30.6 (#226), Qwen1.5-32B: 13.5 (#296)

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
GPQA Diamond47.4%30.7%
LMArena Expert12251126
MMLU86.3%74.4%
Confabulations22.8%—
Vectara Hallucination Rate4.1%—

Multilingual Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 39.9 (#220), Qwen1.5-32B: 31.4 (#259)

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
LMArena Non-English12361106
LMArena Chinese12171177
LMArena French12811101
LMArena German12511058
LMArena Japanese11501027
LMArena Korean11431008
LMArena Russian12521073
LMArena Spanish12701089

Instruction Following Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 71.1 (#157), Qwen1.5-32B: 57.7 (#265)

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
LMArena Instruction Following12421116
LiveBench Instruction Following82.7%—

Long Context Qwen1.5-32B leads

Llama-3.3-70B-Instruct: 26.4 (#295), Qwen1.5-32B: 34.7 (#246)

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
LMArena Longer Query12561146
Fiction.LiveBench33.3%—

Writing & Preference Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 47.6 (#207), Qwen1.5-32B: 34.2 (#271)

BenchmarkLlama-3.3-70B-InstructQwen1.5-32B
LMArena Text12741137
LMArena Creative Writing12501083
LMArena Multi-Turn12801140
LiveBench Language39.2%—

Frequently asked questions

Is Llama-3.3-70B-Instruct better than Qwen1.5-32B?

Llama-3.3-70B-Instruct and Qwen1.5-32B score almost the same on the Noometry Index (30.6 vs 30.5), so choose on price, context window or the category you care about most.

Is Llama-3.3-70B-Instruct or Qwen1.5-32B better for coding?

They score almost the same on coding (31.0 vs 31.7); test both on your own repository before choosing.

How many benchmarks do Llama-3.3-70B-Instruct and Qwen1.5-32B share?

21 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Qwen1.5-32B has 21.

Related comparisons

Go deeper