Noometry

Model comparison

Llama 2-70B vs Qwen3 Max

Qwen3 Max is the stronger model overall, scoring 43.7 to 24.4 on the Noometry Index.

Last verified . 22 shared benchmarks.

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Qwen3 Max Alibaba (Qwen)

43.7

Rank #87 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 7.4.
  • The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 97.1% for Qwen3 Max.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Llama 2-70BQwen3 Max
ProviderMetaAlibaba (Qwen)
Noometry Index24.443.7
Released2023-07-182025-09-23
WeightsOpenProprietary
Context window—262K
Max output—66K
Input $ / M tokens—$1.20
Output $ / M tokens—$6
Results tracked3533

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

Category by category

Coding Qwen3 Max leads

Llama 2-70B: 31.4 (#286), Qwen3 Max: 43.0 (#93)

BenchmarkLlama 2-70BQwen3 Max
LMArena Coding10791456
ALE-Bench—370.45

Agentic & Tool Use Not comparable

Llama 2-70B: —, Qwen3 Max: —

BenchmarkLlama 2-70BQwen3 Max
Vending-Bench 2—71.56

Reasoning Qwen3 Max leads

Llama 2-70B: 14.4 (#325), Qwen3 Max: 22.6 (#190)

BenchmarkLlama 2-70BQwen3 Max
LMArena Hard Prompts10731448
DTBench41.6%82.1%
Epoch Capabilities Index113.79142.38
Kagi LLM Benchmark—72.5%
NYT Connections (extended)—30.1%
Chess Puzzles—4%
Mystery Game Puzzles—5%
LMCA—28.3%
BIG-Bench Hard64.9%—
CommonsenseQA 2.050%—
ForecastBench51.4—
HellaSwag85.3%—
LAMBADA78.9%—
PIQA82.8%—
WinoGrande80.2%—

Math Qwen3 Max leads

Llama 2-70B: 8.1 (#326), Qwen3 Max: 38.7 (#131)

BenchmarkLlama 2-70BQwen3 Max
OTIS Mock AIME 2024-20250%73.3%
LMArena Math10911446
MATH Level 53.3%97.1%
FrontierMath (Tiers 1-3)—18.9%
GSM8K69.6%—

Knowledge Qwen3 Max leads

Llama 2-70B: 7.4 (#310), Qwen3 Max: 48.1 (#78)

BenchmarkLlama 2-70BQwen3 Max
GPQA Diamond26.3%72.6%
LMArena Expert10391455
SimpleQA Verified—48.7%
ARC (AI2) Challenge78.3%—
BoolQ88.6%—
MMLU69.9%—
OpenBookQA60.2%—
TriviaQA87.6%—

Multilingual Qwen3 Max leads

Llama 2-70B: 27.7 (#274), Qwen3 Max: 53.7 (#62)

BenchmarkLlama 2-70BQwen3 Max
LMArena Non-English10451429
LMArena Chinese9951478
LMArena French10901449
LMArena German10411463
LMArena Japanese9271397
LMArena Korean9641399
LMArena Russian10831428
LMArena Spanish11431462

Instruction Following Qwen3 Max leads

Llama 2-70B: 54.9 (#278), Qwen3 Max: 74.8 (#87)

BenchmarkLlama 2-70BQwen3 Max
LMArena Instruction Following10711419

Long Context Qwen3 Max leads

Llama 2-70B: 32.3 (#270), Qwen3 Max: 41.6 (#134)

BenchmarkLlama 2-70BQwen3 Max
LMArena Longer Query10621438
Fiction.LiveBench—66.7%
CL-bench—14.5%

Writing & Preference Qwen3 Max leads

Llama 2-70B: 32.3 (#279), Qwen3 Max: 62.4 (#76)

BenchmarkLlama 2-70BQwen3 Max
LMArena Text11151439
LMArena Creative Writing10751402
LMArena Multi-Turn10881446

Frequently asked questions

Is Llama 2-70B better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.7 to 24.4 on the Noometry Index.

Is Llama 2-70B or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 43.0 versus 31.4 in the Noometry coding category.

How many benchmarks do Llama 2-70B and Qwen3 Max share?

22 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Qwen3 Max has 33.

Related comparisons

Go deeper