Noometry

Model comparison

Claude 3 Haiku vs Qwen3.6 Plus

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 25.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Qwen3.6 Plus Alibaba (Qwen)

47.5

Rank #62 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen3.6 Plus in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.6 Plus leads 51.8 to 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 93.3% for Qwen3.6 Plus.

Side by side

Claude 3 HaikuQwen3.6 Plus
ProviderAnthropicAlibaba (Qwen)
Noometry Index25.947.5
Released2024-03-072026-03-31
WeightsProprietaryProprietary
Context window—1M
Max output—66K
Input $ / M tokens—$0.50
Output $ / M tokens—$3
Results tracked3737

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

Category by category

Coding Qwen3.6 Plus leads

Claude 3 Haiku: 26.4 (#325), Qwen3.6 Plus: 40.8 (#130)

BenchmarkClaude 3 HaikuQwen3.6 Plus
LMArena Coding11991467
SWE-bench Verified—57.9%
LMArena WebDev—1461
SciCode—40.7%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—670.15
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Qwen3.6 Plus: —

BenchmarkClaude 3 HaikuQwen3.6 Plus
Vending-Bench 2—5,115

Reasoning Qwen3.6 Plus leads

Claude 3 Haiku: 16.3 (#307), Qwen3.6 Plus: 29.3 (#93)

BenchmarkClaude 3 HaikuQwen3.6 Plus
LMArena Hard Prompts11741449
DTBench50.1%81.9%
LMCA8.8%33.1%
Epoch Capabilities Index118.35147.65
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—60.3%
CritPt—2.9%
Chess Puzzles—17%
Thematic Generalization—59.5%
Mystery Game Puzzles—12%
ForecastBench53.2—
WinoGrande74.2%—

Math Qwen3.6 Plus leads

Claude 3 Haiku: 9.8 (#319), Qwen3.6 Plus: 51.8 (#54)

BenchmarkClaude 3 HaikuQwen3.6 Plus
OTIS Mock AIME 2024-20251.8%93.3%
LMArena Math11881450
FrontierMath (Tiers 1-3)—38.2%
MATH Level 514.9%—
FrontierMath (Feb 2025 set)—26.2%
FrontierMath Tier 4 (v1)—8.3%

Knowledge Qwen3.6 Plus leads

Claude 3 Haiku: 17.3 (#285), Qwen3.6 Plus: 56.1 (#45)

BenchmarkClaude 3 HaikuQwen3.6 Plus
GPQA Diamond36.3%88.4%
LMArena Expert11481454
SimpleQA Verified—44.1%
Confabulations34.2%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Qwen3.6 Plus: —

BenchmarkClaude 3 HaikuQwen3.6 Plus
LMArena Vision950—
ScienceQA72%—

Multilingual Qwen3.6 Plus leads

Claude 3 Haiku: 36.0 (#243), Qwen3.6 Plus: 53.3 (#70)

BenchmarkClaude 3 HaikuQwen3.6 Plus
LMArena Non-English11781424
LMArena Chinese11551477
LMArena French11951455
LMArena German11741452
LMArena Japanese11021389
LMArena Korean11091379
LMArena Russian12041434
LMArena Spanish11661432

Instruction Following Qwen3.6 Plus leads

Claude 3 Haiku: 61.3 (#247), Qwen3.6 Plus: 75.0 (#74)

BenchmarkClaude 3 HaikuQwen3.6 Plus
LMArena Instruction Following11731425

Long Context Qwen3.6 Plus leads

Claude 3 Haiku: 36.1 (#237), Qwen3.6 Plus: 45.2 (#49)

BenchmarkClaude 3 HaikuQwen3.6 Plus
LMArena Longer Query11901439
CL-bench—20.3%

Writing & Preference Qwen3.6 Plus leads

Claude 3 Haiku: 29.7 (#291), Qwen3.6 Plus: 62.2 (#82)

BenchmarkClaude 3 HaikuQwen3.6 Plus
LMArena Text11951437
LMArena Creative Writing11571404
LMArena Multi-Turn11901438
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Qwen3.6 Plus?

Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Qwen3.6 Plus better for coding?

Qwen3.6 Plus scores higher on coding benchmarks: 40.8 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Qwen3.6 Plus share?

22 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen3.6 Plus has 37.

Related comparisons

Go deeper