Noometry

Model comparison

Llama 3-70B vs Qwen3-30B-A3B

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 28.8 on the Noometry Index.

Last verified . 22 shared benchmarks.

Llama 3-70B Meta

28.8

Rank #323 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.9

Rank #179 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Llama 3-70B scores higher in 1 category and Qwen3-30B-A3B in 8 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3-30B-A3B leads 37.4 to 12.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 4.3% for Llama 3-70B and 70.3% for Qwen3-30B-A3B.

Side by side

Llama 3-70BQwen3-30B-A3B
ProviderMetaAlibaba (Qwen)
Noometry Index28.838.9
Released2024-04-182025-04-28
WeightsOpenOpen
Context window—41K
Max output—16K
Input $ / M tokens—$0.12
Output $ / M tokens—$0.50
Results tracked3132

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

Category by category

Coding Qwen3-30B-A3B leads

Llama 3-70B: 35.8 (#218), Qwen3-30B-A3B: 37.5 (#194)

BenchmarkLlama 3-70BQwen3-30B-A3B
LMArena Coding12061416
SciCode—33.3%
WeirdML—29.8%
BigCodeBench Instruct43.6%—
BigCodeBench Complete54.5%—
HumanEval+72%—
MBPP+69%—

Agentic & Tool Use Qwen3-30B-A3B leads

Llama 3-70B: 21.1 (#139), Qwen3-30B-A3B: 29.8 (#82)

BenchmarkLlama 3-70BQwen3-30B-A3B
Berkeley Function Calling Leaderboard—41.4%
Cybench5%—

Reasoning Qwen3-30B-A3B leads

Llama 3-70B: 18.0 (#288), Qwen3-30B-A3B: 22.2 (#204)

BenchmarkLlama 3-70BQwen3-30B-A3B
Kagi LLM Benchmark35.1%54.9%
LMArena Hard Prompts11951398
DTBench54.2%69.3%
Epoch Capabilities Index122.93139.63
CritPt—0.3%
Chess Puzzles—8%
LMCA—22.4%
ForecastBench57.1—
WinoGrande83.5%—

Math Qwen3-30B-A3B leads

Llama 3-70B: 12.8 (#305), Qwen3-30B-A3B: 37.4 (#157)

BenchmarkLlama 3-70BQwen3-30B-A3B
OTIS Mock AIME 2024-20254.3%70.3%
LMArena Math12181394
MathArena Final-Answer Competitions—47.8%
MATH Level 522.6%—

Knowledge Qwen3-30B-A3B leads

Llama 3-70B: 20.8 (#277), Qwen3-30B-A3B: 41.8 (#105)

BenchmarkLlama 3-70BQwen3-30B-A3B
GPQA Diamond40.6%70.1%
LMArena Expert11491396
Confabulations—12.3%
MMLU79.3%—

Multilingual Qwen3-30B-A3B leads

Llama 3-70B: 33.6 (#251), Qwen3-30B-A3B: 49.5 (#132)

BenchmarkLlama 3-70BQwen3-30B-A3B
LMArena Non-English11421372
LMArena Chinese11141433
LMArena French12321418
LMArena German11691380
LMArena Japanese10171337
LMArena Korean10171331
LMArena Russian11591370
LMArena Spanish12411404

Instruction Following Qwen3-30B-A3B leads

Llama 3-70B: 62.5 (#238), Qwen3-30B-A3B: 72.0 (#142)

BenchmarkLlama 3-70BQwen3-30B-A3B
LMArena Instruction Following11941363

Long Context Llama 3-70B leads

Llama 3-70B: 35.6 (#240), Qwen3-30B-A3B: 31.0 (#283)

BenchmarkLlama 3-70BQwen3-30B-A3B
LMArena Longer Query11741379
Fiction.LiveBench—40.6%

Writing & Preference Qwen3-30B-A3B leads

Llama 3-70B: 42.8 (#231), Qwen3-30B-A3B: 55.6 (#143)

BenchmarkLlama 3-70BQwen3-30B-A3B
LMArena Text12211384
LMArena Creative Writing12101317
LMArena Multi-Turn12231378
Short-Story Creative Writing—75.3%

Frequently asked questions

Is Llama 3-70B better than Qwen3-30B-A3B?

Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 28.8 on the Noometry Index.

Is Llama 3-70B or Qwen3-30B-A3B better for coding?

Qwen3-30B-A3B scores higher on coding benchmarks: 37.5 versus 35.8 in the Noometry coding category.

How many benchmarks do Llama 3-70B and Qwen3-30B-A3B share?

22 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper