Noometry

Model comparison

Claude Haiku 5.5 vs Qwen3 32B

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 39.2 on the Noometry Index.

Last verified . 2 shared benchmarks.

Claude Haiku 5.5 Anthropic

49.5

Rank #52 Confirmed

Qwen3 32B Alibaba (Qwen)

39.2

Rank #172 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 4 categories and Qwen3 32B in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 39.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.9% for Claude Haiku 5.5 and 66.9% for Qwen3 32B.
  • Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $0.70 / $2.80 for Qwen3 32B.
  • Claude Haiku 5.5 accepts more context: 1M tokens versus 131K.
  • Qwen3 32B has downloadable open weights; the other is API-only.

Side by side

Claude Haiku 5.5Qwen3 32B
ProviderAnthropicAlibaba (Qwen)
Noometry Index49.539.2
Released2026-10-072025-04
WeightsProprietaryOpen
Context window1M131K
Max output128K16K
Input $ / M tokens$0.10$0.70
Output $ / M tokens$0.50$2.80
Results tracked926

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

Category by category

Coding Claude Haiku 5.5 leads

Claude Haiku 5.5: 49.2 (#50), Qwen3 32B: 37.7 (#190)

BenchmarkClaude Haiku 5.5Qwen3 32B
Aider Polyglot—40%
LMArena WebDev1587—
SciCode—35.4%
LMArena Coding—1358

Agentic & Tool Use Not comparable

Claude Haiku 5.5: —, Qwen3 32B: 32.6 (#62)

BenchmarkClaude Haiku 5.5Qwen3 32B
Berkeley Function Calling Leaderboard—48.7%

Reasoning Claude Haiku 5.5 leads

Claude Haiku 5.5: 35.2 (#69), Qwen3 32B: 20.2 (#241)

BenchmarkClaude Haiku 5.5Qwen3 32B
Kagi LLM Benchmark—54.9%
NYT Connections (extended)65.7%—
CritPt—0.3%
Chess Puzzles—5%
LMArena Hard Prompts—1334
Mystery Game Puzzles30%—
DTBench—67.5%
LMCA—17.3%
Epoch Capabilities Index—138.51

Math Claude Haiku 5.5 leads

Claude Haiku 5.5: 73.6 (#18), Qwen3 32B: 39.7 (#99)

BenchmarkClaude Haiku 5.5Qwen3 32B
OTIS Mock AIME 2024-202598.9%66.9%
FrontierMath (Tiers 1-3)75.1%—
FrontierMath Tier 446.3%—
LMArena Math—1399

Knowledge Claude Haiku 5.5 leads

Claude Haiku 5.5: 50.8 (#70), Qwen3 32B: 40.0 (#125)

BenchmarkClaude Haiku 5.5Qwen3 32B
GPQA Diamond89.6%65.7%
SimpleQA Verified23.8%—
Vectara Hallucination Rate—5.9%
LMArena Expert—1362

Multimodal Not comparable

Claude Haiku 5.5: 43.7 (#21), Qwen3 32B: —

BenchmarkClaude Haiku 5.5Qwen3 32B
Furniture Assembly47.5%—

Multilingual Not comparable

Claude Haiku 5.5: —, Qwen3 32B: 45.6 (#167)

BenchmarkClaude Haiku 5.5Qwen3 32B
LMArena Non-English—1317
LMArena Chinese—1357
LMArena German—1341
LMArena Russian—1311

Instruction Following Not comparable

Claude Haiku 5.5: —, Qwen3 32B: 68.9 (#179)

BenchmarkClaude Haiku 5.5Qwen3 32B
LMArena Instruction Following—1305

Long Context Not comparable

Claude Haiku 5.5: —, Qwen3 32B: 43.8 (#87)

BenchmarkClaude Haiku 5.5Qwen3 32B
Fiction.LiveBench—74.2%
LMArena Longer Query—1327

Writing & Preference Not comparable

Claude Haiku 5.5: —, Qwen3 32B: 52.9 (#163)

BenchmarkClaude Haiku 5.5Qwen3 32B
LMArena Text—1340
LMArena Creative Writing—1297
LMArena Multi-Turn—1331

Frequently asked questions

Is Claude Haiku 5.5 better than Qwen3 32B?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 39.2 on the Noometry Index.

Which is cheaper, Claude Haiku 5.5 or Qwen3 32B?

Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Qwen3 32B lists at $0.70 and $2.80.

Is Claude Haiku 5.5 or Qwen3 32B better for coding?

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 37.7 in the Noometry coding category.

Which has the bigger context window?

Claude Haiku 5.5 does, with 1M tokens against 131K.

How many benchmarks do Claude Haiku 5.5 and Qwen3 32B share?

2 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Qwen3 32B has 26.

Related comparisons

Go deeper