Noometry

Model comparison

Claude 3 Haiku vs Qwen3.5 Plus

Qwen3.5 Plus is the stronger model overall, scoring 42.9 to 25.9 on the Noometry Index.

Last verified . 5 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Qwen3.5 Plus Alibaba (Qwen)

42.9

Rank #106 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen3.5 Plus in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.5 Plus leads 49.6 to 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 86.7% for Qwen3.5 Plus.

Side by side

Claude 3 HaikuQwen3.5 Plus
ProviderAnthropicAlibaba (Qwen)
Noometry Index25.942.9
Released2024-03-072026-02-16
WeightsProprietaryProprietary
Context window—1M
Max output—66K
Input $ / M tokens—$0.40
Output $ / M tokens—$2.40
Results tracked3715

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

Category by category

Coding Not comparable

Claude 3 Haiku: 26.4 (#325), Qwen3.5 Plus: —

BenchmarkClaude 3 HaikuQwen3.5 Plus
WeirdML9.8%—
BigCodeBench Instruct39.4%—
LMArena Coding1199—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—621.92
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Qwen3.5 Plus: —

BenchmarkClaude 3 HaikuQwen3.5 Plus
Vending-Bench 2—0.54

Reasoning Qwen3.5 Plus leads

Claude 3 Haiku: 16.3 (#307), Qwen3.5 Plus: 32.8 (#74)

BenchmarkClaude 3 HaikuQwen3.5 Plus
DTBench50.1%80.5%
LMCA8.8%36.4%
Epoch Capabilities Index118.35146.78
Kagi LLM Benchmark34.2%—
Chess Puzzles—22%
LMArena Hard Prompts1174—
Mystery Game Puzzles—17%
ForecastBench53.2—
WinoGrande74.2%—

Math Qwen3.5 Plus leads

Claude 3 Haiku: 9.8 (#319), Qwen3.5 Plus: 49.6 (#61)

BenchmarkClaude 3 HaikuQwen3.5 Plus
OTIS Mock AIME 2024-20251.8%86.7%
LMArena Math1188—
MATH Level 514.9%—
FrontierMath (Feb 2025 set)—21%
FrontierMath Tier 4 (v1)—2.1%

Knowledge Qwen3.5 Plus leads

Claude 3 Haiku: 17.3 (#285), Qwen3.5 Plus: 46.0 (#83)

BenchmarkClaude 3 HaikuQwen3.5 Plus
GPQA Diamond36.3%84.8%
SimpleQA Verified—25.4%
Confabulations34.2%—
Vectara Hallucination Rate—10.7%
LMArena Expert1148—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Qwen3.5 Plus: —

BenchmarkClaude 3 HaikuQwen3.5 Plus
LMArena Vision950—
ScienceQA72%—

Multilingual Not comparable

Claude 3 Haiku: 36.0 (#243), Qwen3.5 Plus: —

BenchmarkClaude 3 HaikuQwen3.5 Plus
LMArena Non-English1178—
LMArena Chinese1155—
LMArena French1195—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—
LMArena Russian1204—
LMArena Spanish1166—

Instruction Following Not comparable

Claude 3 Haiku: 61.3 (#247), Qwen3.5 Plus: —

BenchmarkClaude 3 HaikuQwen3.5 Plus
LMArena Instruction Following1173—

Long Context Qwen3.5 Plus leads

Claude 3 Haiku: 36.1 (#237), Qwen3.5 Plus: 43.0 (#113)

BenchmarkClaude 3 HaikuQwen3.5 Plus
CL-bench—19.8%
CL-bench Life—12.4%
LMArena Longer Query1190—

Writing & Preference Not comparable

Claude 3 Haiku: 29.7 (#291), Qwen3.5 Plus: —

BenchmarkClaude 3 HaikuQwen3.5 Plus
LMArena Text1195—
LMArena Creative Writing1157—
EQ-Bench Creative Writing717—
LMArena Multi-Turn1190—

Frequently asked questions

Is Claude 3 Haiku better than Qwen3.5 Plus?

Qwen3.5 Plus is the stronger model overall, scoring 42.9 to 25.9 on the Noometry Index.

How many benchmarks do Claude 3 Haiku and Qwen3.5 Plus share?

5 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen3.5 Plus has 15.

Related comparisons

Go deeper