Noometry

Model comparison

Llama 3.1-70B vs Qwen3 8B

Qwen3 8B is the stronger model overall, scoring 33.3 to 29.4 on the Noometry Index.

Last verified . 5 shared benchmarks.

Llama 3.1-70B Meta

29.4

Rank #299 Confirmed

Qwen3 8B Alibaba (Qwen)

33.3

Rank #237 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Llama 3.1-70B scores higher in 1 category and Qwen3 8B in 5 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3 8B leads 33.3 to 12.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 3.6% for Llama 3.1-70B and 56.1% for Qwen3 8B.
  • Qwen3 8B is cheaper at $0.18 / $0.70 per million input/output tokens, against $0.40 / $0.40 for Llama 3.1-70B.
  • Qwen3 8B accepts more context: 131K tokens versus 128K.

Side by side

Llama 3.1-70BQwen3 8B
ProviderMetaAlibaba (Qwen)
Noometry Index29.433.3
Released2024-07-232025-04
WeightsOpenOpen
Context window128K131K
Max output4K8K
Input $ / M tokens$0.40$0.18
Output $ / M tokens$0.40$0.70
Results tracked3511

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

Category by category

Coding Qwen3 8B leads

Llama 3.1-70B: 29.8 (#292), Qwen3 8B: 33.4 (#245)

BenchmarkLlama 3.1-70BQwen3 8B
SciCode—22.6%
WeirdML9%—
BigCodeBench Instruct46.1%—
LMArena Coding1260—
BigCodeBench Complete54.8%—

Agentic & Tool Use Qwen3 8B leads

Llama 3.1-70B: 24.9 (#104), Qwen3 8B: 29.9 (#71)

BenchmarkLlama 3.1-70BQwen3 8B
Berkeley Function Calling Leaderboard—42.6%
TheAgentCompany6.9%—
BALROG27.9%—

Reasoning Llama 3.1-70B leads

Llama 3.1-70B: 20.8 (#215), Qwen3 8B: 16.1 (#299)

BenchmarkLlama 3.1-70BQwen3 8B
DTBench60%59.7%
LMCA14.8%8.8%
Epoch Capabilities Index125.91136.17
CritPt—0%
Chess Puzzles—5%
LMArena Hard Prompts1241—

Math Qwen3 8B leads

Llama 3.1-70B: 12.7 (#298), Qwen3 8B: 33.3 (#176)

BenchmarkLlama 3.1-70BQwen3 8B
OTIS Mock AIME 2024-20253.6%56.1%
Omni-MATH21%—
LMArena Math1252—
MATH Level 536.7%—

Knowledge Qwen3 8B leads

Llama 3.1-70B: 24.1 (#264), Qwen3 8B: 36.1 (#164)

BenchmarkLlama 3.1-70BQwen3 8B
GPQA Diamond44.2%56.8%
MMLU-Pro65.3%—
Vectara Hallucination Rate—4.8%
GPQA (HELM)42.6%—
LMArena Expert1209—
MMLU80.1%—

Multilingual Not comparable

Llama 3.1-70B: 38.9 (#220), Qwen3 8B: —

BenchmarkLlama 3.1-70BQwen3 8B
LMArena Non-English1219—
LMArena Chinese1215—
LMArena French1260—
LMArena German1222—
LMArena Japanese1132—
LMArena Korean1140—
LMArena Russian1234—
LMArena Spanish1253—

Instruction Following Not comparable

Llama 3.1-70B: 65.5 (#218), Qwen3 8B: —

BenchmarkLlama 3.1-70BQwen3 8B
IFEval82.1%—
LMArena Instruction Following1231—

Long Context Too close to call

Llama 3.1-70B: 37.6 (#208), Qwen3 8B: 37.8 (#205)

BenchmarkLlama 3.1-70BQwen3 8B
Fiction.LiveBench—62.1%
LMArena Longer Query1241—

Writing & Preference Not comparable

Llama 3.1-70B: 35.6 (#262), Qwen3 8B: —

BenchmarkLlama 3.1-70BQwen3 8B
LMArena Text1261—
LMArena Creative Writing1232—
EQ-Bench Creative Writing784—
WildBench75.8%—
LMArena Multi-Turn1256—

Frequently asked questions

Is Llama 3.1-70B better than Qwen3 8B?

Qwen3 8B is the stronger model overall, scoring 33.3 to 29.4 on the Noometry Index.

Which is cheaper, Llama 3.1-70B or Qwen3 8B?

Qwen3 8B is cheaper. It lists at $0.18 per million input tokens and $0.70 per million output tokens; Llama 3.1-70B lists at $0.40 and $0.40.

Is Llama 3.1-70B or Qwen3 8B better for coding?

Qwen3 8B scores higher on coding benchmarks: 33.4 versus 29.8 in the Noometry coding category.

Which has the bigger context window?

Qwen3 8B does, with 131K tokens against 128K.

How many benchmarks do Llama 3.1-70B and Qwen3 8B share?

5 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Qwen3 8B has 11.

Related comparisons

Go deeper