Noometry

Model comparison

Llama-3.3-70B-Instruct vs Qwen1.5 4b Chat

Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 28.8 on the Noometry Index.

Last verified . 13 shared benchmarks.

Llama-3.3-70B-Instruct Meta

30.6

Rank #291 Confirmed

Qwen1.5 4b Chat Alibaba (Qwen)

28.8

Rank #322 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 5 categories and Qwen1.5 4b Chat in 3 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Llama-3.3-70B-Instruct leads 47.6 to 23.8.

Side by side

Llama-3.3-70B-InstructQwen1.5 4b Chat
ProviderMetaAlibaba (Qwen)
Noometry Index30.628.8
Released2024-12-06—
WeightsOpenOpen
Context window128K—
Max output4K—
Input $ / M tokens$0.10—
Output $ / M tokens$0.32—
Results tracked4313

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

Category by category

Coding Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 31.0 (#290), Qwen1.5 4b Chat: 29.1 (#308)

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
LMArena Coding1268999
SciCode26%—
WeirdML14.4%—
BigCodeBench Instruct46.9%—
LiveBench Coding36.6%—
BigCodeBench Complete57.5%—

Agentic & Tool Use Not comparable

Llama-3.3-70B-Instruct: 25.8 (#105), Qwen1.5 4b Chat: —

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
Berkeley Function Calling Leaderboard31.9%—
BALROG23%—

Reasoning Qwen1.5 4b Chat leads

Llama-3.3-70B-Instruct: 14.1 (#327), Qwen1.5 4b Chat: 18.5 (#279)

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
LMArena Hard Prompts1257976
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 4b Chat leads

Llama-3.3-70B-Instruct: 15.3 (#298), Qwen1.5 4b Chat: 30.4 (#234)

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
LMArena Math12671026
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 4b Chat: 26.7 (#255)

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
LMArena Expert1225980
GPQA Diamond47.4%—
Confabulations22.8%—
Vectara Hallucination Rate4.1%—
MMLU86.3%—

Multilingual Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 39.9 (#220), Qwen1.5 4b Chat: 24.1 (#290)

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
LMArena Non-English1236979
LMArena Chinese12171024
LMArena German1251902
LMArena Russian1252952
LMArena French1281—
LMArena Japanese1150—
LMArena Korean1143—
LMArena Spanish1270—

Instruction Following Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 71.1 (#157), Qwen1.5 4b Chat: 49.0 (#300)

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
LMArena Instruction Following1242978
LiveBench Instruction Following82.7%—

Long Context Qwen1.5 4b Chat leads

Llama-3.3-70B-Instruct: 26.4 (#295), Qwen1.5 4b Chat: 30.1 (#290)

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
LMArena Longer Query1256988
Fiction.LiveBench33.3%—

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

Llama-3.3-70B-Instruct: 47.6 (#207), Qwen1.5 4b Chat: 23.8 (#309)

BenchmarkLlama-3.3-70B-InstructQwen1.5 4b Chat
LMArena Text1274997
LMArena Creative Writing1250969
LMArena Multi-Turn1280977
LiveBench Language39.2%—

Frequently asked questions

Is Llama-3.3-70B-Instruct better than Qwen1.5 4b Chat?

Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 28.8 on the Noometry Index.

Is Llama-3.3-70B-Instruct or Qwen1.5 4b Chat better for coding?

Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 29.1 in the Noometry coding category.

How many benchmarks do Llama-3.3-70B-Instruct and Qwen1.5 4b Chat share?

13 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Qwen1.5 4b Chat has 13.

Related comparisons

Go deeper