Noometry

Model comparison

Qwen1.5-32B vs Qwen3.5-Flash

Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 30.0 on the Noometry Index.

Last verified . 18 shared benchmarks.

Qwen1.5-32B Alibaba (Qwen)

30.0

Rank #288 Confirmed

Qwen3.5-Flash Alibaba (Qwen)

42.3

Rank #105 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Qwen1.5-32B scores higher in 0 categories and Qwen3.5-Flash in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.5-Flash leads 43.2 to 13.5.
  • The biggest single-benchmark swing is GPQA Diamond: 30.7% for Qwen1.5-32B and 82.3% for Qwen3.5-Flash.
  • Qwen1.5-32B has downloadable open weights; the other is API-only.

Side by side

Qwen1.5-32BQwen3.5-Flash
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index30.042.3
Released2024-02-042026-02-23
WeightsOpenProprietary
Context window—1M
Max output—66K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.40
Results tracked2132

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

Category by category

Coding Qwen3.5-Flash leads

Qwen1.5-32B: 31.1 (#278), Qwen3.5-Flash: 33.9 (#234)

BenchmarkQwen1.5-32BQwen3.5-Flash
LMArena Coding11551412
LMArena WebDev—1243
BigCodeBench Instruct32.3%—
BigCodeBench Complete42%—
ALE-Bench—221.8

Agentic & Tool Use Not comparable

Qwen1.5-32B: —, Qwen3.5-Flash: —

BenchmarkQwen1.5-32BQwen3.5-Flash
Vending-Bench 2—462.69

Reasoning Qwen3.5-Flash leads

Qwen1.5-32B: 20.9 (#210), Qwen3.5-Flash: 32.9 (#63)

BenchmarkQwen1.5-32BQwen3.5-Flash
LMArena Hard Prompts11311404
Chess Puzzles—21%
Mystery Game Puzzles—20%
DTBench—82.9%
LMCA—29.1%
Epoch Capabilities Index—143.98

Math Qwen3.5-Flash leads

Qwen1.5-32B: 30.5 (#207), Qwen3.5-Flash: 36.3 (#117)

BenchmarkQwen1.5-32BQwen3.5-Flash
LMArena Math11551407
FrontierMath (Tiers 1-3)—18.2%
OTIS Mock AIME 2024-2025—84.4%
FrontierMath (Feb 2025 set)—6.2%
FrontierMath Tier 4 (v1)—0%

Knowledge Qwen3.5-Flash leads

Qwen1.5-32B: 13.5 (#291), Qwen3.5-Flash: 43.2 (#84)

BenchmarkQwen1.5-32BQwen3.5-Flash
GPQA Diamond30.7%82.3%
LMArena Expert11261408
SimpleQA Verified—20.3%
Vectara Hallucination Rate—10.5%
MMLU74.4%—

Multilingual Qwen3.5-Flash leads

Qwen1.5-32B: 31.6 (#254), Qwen3.5-Flash: 50.7 (#116)

BenchmarkQwen1.5-32BQwen3.5-Flash
LMArena Non-English11061385
LMArena Chinese11761446
LMArena French11001412
LMArena German10581389
LMArena Japanese10271369
LMArena Korean10071344
LMArena Russian10731379
LMArena Spanish10891399

Instruction Following Qwen3.5-Flash leads

Qwen1.5-32B: 58.0 (#260), Qwen3.5-Flash: 72.8 (#133)

BenchmarkQwen1.5-32BQwen3.5-Flash
LMArena Instruction Following11161374

Long Context Qwen3.5-Flash leads

Qwen1.5-32B: 34.7 (#241), Qwen3.5-Flash: 42.4 (#119)

BenchmarkQwen1.5-32BQwen3.5-Flash
LMArena Longer Query11461392

Writing & Preference Qwen3.5-Flash leads

Qwen1.5-32B: 34.4 (#266), Qwen3.5-Flash: 58.2 (#117)

BenchmarkQwen1.5-32BQwen3.5-Flash
LMArena Text11371397
LMArena Creative Writing10831343
LMArena Multi-Turn11401393

Frequently asked questions

Is Qwen1.5-32B better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.3 to 30.0 on the Noometry Index.

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

Qwen3.5-Flash scores higher on coding benchmarks: 33.9 versus 31.1 in the Noometry coding category.

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

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

Related comparisons

Go deeper