Noometry

Model comparison

Qwen1.5-72B vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 30.8 on the Noometry Index.

Last verified . 18 shared benchmarks.

Qwen1.5-72B Alibaba (Qwen)

30.8

Rank #285 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Qwen1.5-72B scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 235B-A22B leads 49.6 to 11.5.
  • The biggest single-benchmark swing is GPQA Diamond: 28.8% for Qwen1.5-72B and 80.1% for Qwen3 235B-A22B.

Side by side

Qwen1.5-72BQwen3 235B-A22B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.843.5
Released2024-02-042025-04
WeightsOpenOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked2249

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

Category by category

Coding Qwen3 235B-A22B leads

Qwen1.5-72B: 31.9 (#277), Qwen3 235B-A22B: 44.3 (#75)

BenchmarkQwen1.5-72BQwen3 235B-A22B
LMArena Coding11651445
Aider Polyglot—59.6%
SciCode—42.4%
WeirdML—41%
BigCodeBench Instruct33.2%—
BigCodeBench Complete40.3%—
HumanEval+59.1%—
MBPP+61.6%—

Agentic & Tool Use Not comparable

Qwen1.5-72B: —, Qwen3 235B-A22B: 33.9 (#51)

BenchmarkQwen1.5-72BQwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
Vending-Bench 2—-11.34

Reasoning Qwen1.5-72B leads

Qwen1.5-72B: 22.2 (#203), Qwen3 235B-A22B: 15.7 (#311)

BenchmarkQwen1.5-72BQwen3 235B-A22B
LMArena Hard Prompts11481433
ARC-AGI-2—1.3%
SimpleBench—31%
Kagi LLM Benchmark—69.4%
ARC-AGI-1—11%
CritPt—0%
Chess Puzzles—12%
Mystery Game Puzzles—9%
DTBench—80.3%
LMCA—29.3%
Epoch Capabilities Index—143.85
ForecastBench—59.7

Math Qwen3 235B-A22B leads

Qwen1.5-72B: 33.2 (#205), Qwen3 235B-A22B: 50.4 (#57)

BenchmarkQwen1.5-72BQwen3 235B-A22B
LMArena Math11641432
OTIS Mock AIME 2024-2025—86.7%
Omni-MATH—71.8%
MATH Level 5—68.9%
FrontierMath (Feb 2025 set)—8.5%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3 235B-A22B leads

Qwen1.5-72B: 11.5 (#300), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkQwen1.5-72BQwen3 235B-A22B
GPQA Diamond28.8%80.1%
LMArena Expert11361463
SimpleQA Verified—40.4%
MMLU-Pro—84.4%
Confabulations—15.6%
Vectara Hallucination Rate—9.3%
GPQA (HELM)—72.7%

Multilingual Qwen3 235B-A22B leads

Qwen1.5-72B: 33.2 (#253), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkQwen1.5-72BQwen3 235B-A22B
LMArena Non-English11351409
LMArena Chinese11861481
LMArena French11591445
LMArena German10841433
LMArena Japanese10611399
LMArena Korean10501391
LMArena Russian11041411
LMArena Spanish11101430

Instruction Following Qwen3 235B-A22B leads

Qwen1.5-72B: 59.3 (#256), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkQwen1.5-72BQwen3 235B-A22B
LMArena Instruction Following11411408
IFEval—83.5%

Long Context Qwen3 235B-A22B leads

Qwen1.5-72B: 35.1 (#243), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkQwen1.5-72BQwen3 235B-A22B
LMArena Longer Query11571426
Fiction.LiveBench—75%

Writing & Preference Qwen3 235B-A22B leads

Qwen1.5-72B: 37.3 (#258), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkQwen1.5-72BQwen3 235B-A22B
LMArena Text11661419
LMArena Creative Writing11371384
LMArena Multi-Turn11601432
Short-Story Creative Writing—83%
EQ-Bench Creative Writing—1366
WildBench—86.6%

Frequently asked questions

Is Qwen1.5-72B better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 30.8 on the Noometry Index.

Is Qwen1.5-72B or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 31.9 in the Noometry coding category.

How many benchmarks do Qwen1.5-72B and Qwen3 235B-A22B share?

18 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper