Noometry

Model comparison

Llama-3.3-70B-Instruct vs Qwen1.5-7B

Llama-3.3-70B-Instruct and Qwen1.5-7B score almost the same on the Noometry Index (30.3 vs 30.8), so choose on price, context window or the category you care about most.

Last verified . 13 shared benchmarks.

Llama-3.3-70B-Instruct Meta

30.3

Rank #283 Confirmed

Qwen1.5-7B Alibaba (Qwen)

30.8

Rank #270 Confirmed

Summary

  • They share 13 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 4 categories and Qwen1.5-7B in 4 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Llama-3.3-70B-Instruct leads 47.8 to 29.8.

Side by side

Llama-3.3-70B-InstructQwen1.5-7B
ProviderMetaAlibaba (Qwen)
Noometry Index30.330.8
Released2024-12-062024-02-04
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 Qwen1.5-7B leads

Llama-3.3-70B-Instruct: 30.6 (#284), Qwen1.5-7B: 31.6 (#271)

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
LMArena Coding12681107
SciCode26%—
WeirdML14.4%—
BigCodeBench Instruct46.9%—
LiveBench Coding36.6%—
BigCodeBench Complete57.5%—

Agentic & Tool Use Not comparable

Llama-3.3-70B-Instruct: 25.6 (#100), Qwen1.5-7B: —

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
Berkeley Function Calling Leaderboard31.9%—
BALROG23%—

Reasoning Qwen1.5-7B leads

Llama-3.3-70B-Instruct: 13.7 (#325), Qwen1.5-7B: 19.5 (#237)

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
LMArena Hard Prompts12571066
SimpleBench19.9%—
CritPt0%—
LiveBench Reasoning50.8%—
DTBench59.5%—
LiveBench Data Analysis49.5%—
LMCA17.5%—
Epoch Capabilities Index127.32—
ForecastBench58.6—
LiveBench50.2%—

Math Qwen1.5-7B leads

Llama-3.3-70B-Instruct: 14.3 (#292), Qwen1.5-7B: 29.0 (#222)

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
LMArena Math12681080
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: 30.5 (#220), Qwen1.5-7B: 28.2 (#239)

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
LMArena Expert12251055
MMLU86.3%62.6%
GPQA Diamond47.4%—
Confabulations22.8%—
Vectara Hallucination Rate4.1%—

Multilingual Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 40.1 (#215), Qwen1.5-7B: 28.6 (#266)

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
LMArena Non-English12361058
LMArena Chinese12171140
LMArena Russian12521006
LMArena French1280—
LMArena German1251—
LMArena Japanese1149—
LMArena Korean1142—
LMArena Spanish1269—

Instruction Following Llama-3.3-70B-Instruct leads

Llama-3.3-70B-Instruct: 71.3 (#152), Qwen1.5-7B: 54.4 (#276)

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
LMArena Instruction Following12421058
LiveBench Instruction Following82.7%—

Long Context Qwen1.5-7B leads

Llama-3.3-70B-Instruct: 26.4 (#290), Qwen1.5-7B: 33.1 (#261)

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
LMArena Longer Query12561090
Fiction.LiveBench33.3%—

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

Llama-3.3-70B-Instruct: 47.8 (#203), Qwen1.5-7B: 29.8 (#288)

BenchmarkLlama-3.3-70B-InstructQwen1.5-7B
LMArena Text12741084
LMArena Creative Writing12501035
LMArena Multi-Turn12791061
LiveBench Language39.2%—

Frequently asked questions

Is Llama-3.3-70B-Instruct better than Qwen1.5-7B?

Llama-3.3-70B-Instruct and Qwen1.5-7B score almost the same on the Noometry Index (30.3 vs 30.8), so choose on price, context window or the category you care about most.

Is Llama-3.3-70B-Instruct or Qwen1.5-7B better for coding?

Qwen1.5-7B scores higher on coding benchmarks: 31.6 versus 30.6 in the Noometry coding category.

How many benchmarks do Llama-3.3-70B-Instruct and Qwen1.5-7B share?

13 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Qwen1.5-7B has 13.

Related comparisons

Go deeper