Noometry

Model comparison

Qwen1.5-32B vs Qwen3 235B-A22B

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 30.5 on the Noometry Index.

Last verified . 18 shared benchmarks.

Qwen1.5-32B Alibaba (Qwen)

30.5

Rank #293 Confirmed

Qwen3 235B-A22B Alibaba (Qwen)

43.5

Rank #91 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Qwen1.5-32B 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 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 30.7% for Qwen1.5-32B and 80.1% for Qwen3 235B-A22B.

Side by side

Qwen1.5-32BQwen3 235B-A22B
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.543.5
Released2024-02-042025-04
WeightsOpenOpen
Context window—131K
Max output—16K
Input $ / M tokens—$0.70
Output $ / M tokens—$2.80
Results tracked2149

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

Category by category

Coding Qwen3 235B-A22B leads

Qwen1.5-32B: 31.7 (#282), Qwen3 235B-A22B: 44.3 (#75)

BenchmarkQwen1.5-32BQwen3 235B-A22B
LMArena Coding11551445
Aider Polyglot—59.6%
SciCode—42.4%
WeirdML—41%
BigCodeBench Instruct32.3%—
BigCodeBench Complete42%—

Agentic & Tool Use Not comparable

Qwen1.5-32B: —, Qwen3 235B-A22B: 33.9 (#51)

BenchmarkQwen1.5-32BQwen3 235B-A22B
Berkeley Function Calling Leaderboard—52.1%
Vending-Bench 2—-11.34

Reasoning Qwen1.5-32B leads

Qwen1.5-32B: 21.8 (#212), Qwen3 235B-A22B: 15.7 (#311)

BenchmarkQwen1.5-32BQwen3 235B-A22B
LMArena Hard Prompts11301433
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

Qwen1.5-32B: 33.0 (#207), Qwen3 235B-A22B: 50.4 (#57)

BenchmarkQwen1.5-32BQwen3 235B-A22B
LMArena Math11551432
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

Qwen1.5-32B: 13.5 (#296), Qwen3 235B-A22B: 49.6 (#73)

BenchmarkQwen1.5-32BQwen3 235B-A22B
GPQA Diamond30.7%80.1%
LMArena Expert11261463
SimpleQA Verified—40.4%
MMLU-Pro—84.4%
Confabulations—15.6%
Vectara Hallucination Rate—9.3%
GPQA (HELM)—72.7%
MMLU74.4%—

Multilingual Qwen3 235B-A22B leads

Qwen1.5-32B: 31.4 (#259), Qwen3 235B-A22B: 52.3 (#89)

BenchmarkQwen1.5-32BQwen3 235B-A22B
LMArena Non-English11061409
LMArena Chinese11771481
LMArena French11011445
LMArena German10581433
LMArena Japanese10271399
LMArena Korean10081391
LMArena Russian10731411
LMArena Spanish10891430

Instruction Following Qwen3 235B-A22B leads

Qwen1.5-32B: 57.7 (#265), Qwen3 235B-A22B: 72.6 (#136)

BenchmarkQwen1.5-32BQwen3 235B-A22B
LMArena Instruction Following11161408
IFEval—83.5%

Long Context Qwen3 235B-A22B leads

Qwen1.5-32B: 34.7 (#246), Qwen3 235B-A22B: 46.1 (#26)

BenchmarkQwen1.5-32BQwen3 235B-A22B
LMArena Longer Query11461426
Fiction.LiveBench—75%

Writing & Preference Qwen3 235B-A22B leads

Qwen1.5-32B: 34.2 (#271), Qwen3 235B-A22B: 59.6 (#108)

BenchmarkQwen1.5-32BQwen3 235B-A22B
LMArena Text11371419
LMArena Creative Writing10831384
LMArena Multi-Turn11401432
Short-Story Creative Writing—83%
EQ-Bench Creative Writing—1366
WildBench—86.6%

Frequently asked questions

Is Qwen1.5-32B better than Qwen3 235B-A22B?

Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 30.5 on the Noometry Index.

Is Qwen1.5-32B or Qwen3 235B-A22B better for coding?

Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 31.7 in the Noometry coding category.

How many benchmarks do Qwen1.5-32B and Qwen3 235B-A22B share?

18 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Qwen3 235B-A22B has 49.

Related comparisons

Go deeper