Noometry

Model comparison

Qwen2-72B vs Qwen3-Next 80B-A3B Instruct

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 30.0 on the Noometry Index.

Last verified . 17 shared benchmarks.

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Qwen3-Next 80B-A3B Instruct Alibaba (Qwen)

43.0

Rank #102 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Qwen2-72B scores higher in 0 categories and Qwen3-Next 80B-A3B Instruct in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3-Next 80B-A3B Instruct leads 41.8 to 21.2.

Side by side

Qwen2-72BQwen3-Next 80B-A3B Instruct
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.043.0
Released2024-06-072025-09
WeightsOpenOpen
Context window—131K
Max output—33K
Input $ / M tokens—$0.50
Output $ / M tokens—$2
Results tracked2625

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

Category by category

Coding Qwen3-Next 80B-A3B Instruct leads

Qwen2-72B: 29.1 (#310), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
LMArena Coding11961440
WeirdML11.3%—
BigCodeBench Instruct38.5%—
BigCodeBench Complete54%—

Agentic & Tool Use Not comparable

Qwen2-72B: 17.0 (#146), Qwen3-Next 80B-A3B Instruct: —

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
TheAgentCompany1.1%—
METR Time Horizons29.9%—

Reasoning Qwen3-Next 80B-A3B Instruct leads

Qwen2-72B: 23.2 (#181), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
LMArena Hard Prompts11911428
Kagi LLM Benchmark—66.7%
Epoch Capabilities Index125.28—

Math Qwen3-Next 80B-A3B Instruct leads

Qwen2-72B: 30.2 (#236), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
LMArena Math12351440
Omni-MATH—46.7%
MATH Level 539.1%—

Knowledge Qwen3-Next 80B-A3B Instruct leads

Qwen2-72B: 21.2 (#275), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
LMArena Expert11711417
GPQA Diamond40.8%—
MMLU-Pro—78.6%
Vectara Hallucination Rate—9.3%
GPQA (HELM)—63%
MMLU82.4%—

Multilingual Qwen3-Next 80B-A3B Instruct leads

Qwen2-72B: 35.9 (#244), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
LMArena Non-English11761407
LMArena Chinese12401460
LMArena French11701413
LMArena German11511417
LMArena Japanese11111395
LMArena Korean10831364
LMArena Russian11691404
LMArena Spanish11691435

Instruction Following Qwen3-Next 80B-A3B Instruct leads

Qwen2-72B: 61.7 (#241), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
LMArena Instruction Following11811389
IFEval—81%

Long Context Too close to call

Qwen2-72B: 36.1 (#235), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
LMArena Longer Query11921403
Fiction.LiveBench—55.6%

Writing & Preference Qwen3-Next 80B-A3B Instruct leads

Qwen2-72B: 40.8 (#241), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)

BenchmarkQwen2-72BQwen3-Next 80B-A3B Instruct
LMArena Text12031417
LMArena Creative Writing11811334
LMArena Multi-Turn11961416
WildBench—80.7%

Frequently asked questions

Is Qwen2-72B better than Qwen3-Next 80B-A3B Instruct?

Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 30.0 on the Noometry Index.

Is Qwen2-72B or Qwen3-Next 80B-A3B Instruct better for coding?

Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 29.1 in the Noometry coding category.

How many benchmarks do Qwen2-72B and Qwen3-Next 80B-A3B Instruct share?

17 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.

Related comparisons

Go deeper