Noometry

Model comparison

Claude 3 Haiku vs Qwen3.7 Max

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 25.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Qwen3.7 Max Alibaba (Qwen)

51.5

Rank #42 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.7 Max leads 62.4 to 9.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 95.6% for Qwen3.7 Max.

Side by side

Claude 3 HaikuQwen3.7 Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index25.951.5
Released2024-03-072026-05-19
WeightsProprietaryProprietary
Context window—1M
Max output—131K
Input $ / M tokens—$2.50
Output $ / M tokens—$7.50
Results tracked3733

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

Category by category

Coding Qwen3.7 Max leads

Claude 3 Haiku: 26.4 (#325), Qwen3.7 Max: 50.4 (#45)

BenchmarkClaude 3 HaikuQwen3.7 Max
LMArena Coding11991498
SWE-bench Verified—77.3%
LMArena WebDev—1515
SciCode—48.8%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
ALE-Bench—1,189
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Qwen3.7 Max: 22.1 (#135)

BenchmarkClaude 3 HaikuQwen3.7 Max
GBAEval—0.4%

Reasoning Qwen3.7 Max leads

Claude 3 Haiku: 16.3 (#307), Qwen3.7 Max: 49.2 (#38)

BenchmarkClaude 3 HaikuQwen3.7 Max
LMArena Hard Prompts11741483
DTBench50.1%92.3%
LMCA8.8%44%
Epoch Capabilities Index118.35153.68
SimpleBench—70.4%
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—85.1%
CritPt—13.4%
Chess Puzzles—19%
EBR-Bench—9.5%
Mystery Game Puzzles—32%
ForecastBench53.2—
WinoGrande74.2%—

Math Qwen3.7 Max leads

Claude 3 Haiku: 9.8 (#319), Qwen3.7 Max: 62.4 (#32)

BenchmarkClaude 3 HaikuQwen3.7 Max
OTIS Mock AIME 2024-20251.8%95.6%
LMArena Math11881490
FrontierMath (Tiers 1-3)—64.6%
FrontierMath Tier 4—34.1%
ProofBench—26%
MATH Level 514.9%—

Knowledge Qwen3.7 Max leads

Claude 3 Haiku: 17.3 (#285), Qwen3.7 Max: 61.6 (#28)

BenchmarkClaude 3 HaikuQwen3.7 Max
GPQA Diamond36.3%90.9%
LMArena Expert11481488
SimpleQA Verified—55.8%
Confabulations34.2%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Qwen3.7 Max: —

BenchmarkClaude 3 HaikuQwen3.7 Max
LMArena Vision950—
ScienceQA72%—

Multilingual Qwen3.7 Max leads

Claude 3 Haiku: 36.0 (#243), Qwen3.7 Max: 56.9 (#15)

BenchmarkClaude 3 HaikuQwen3.7 Max
LMArena Non-English11781474
LMArena Chinese11551530
LMArena Russian12041484
LMArena French1195—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—
LMArena Spanish1166—

Instruction Following Qwen3.7 Max leads

Claude 3 Haiku: 61.3 (#247), Qwen3.7 Max: 76.7 (#38)

BenchmarkClaude 3 HaikuQwen3.7 Max
LMArena Instruction Following11731460

Long Context Qwen3.7 Max leads

Claude 3 Haiku: 36.1 (#237), Qwen3.7 Max: 45.4 (#40)

BenchmarkClaude 3 HaikuQwen3.7 Max
LMArena Longer Query11901482

Writing & Preference Qwen3.7 Max leads

Claude 3 Haiku: 29.7 (#291), Qwen3.7 Max: 65.0 (#54)

BenchmarkClaude 3 HaikuQwen3.7 Max
LMArena Text11951476
LMArena Creative Writing11571449
LMArena Multi-Turn11901481
EQ-Bench Creative Writing717—
EQ-Bench 4—1110

Frequently asked questions

Is Claude 3 Haiku better than Qwen3.7 Max?

Qwen3.7 Max is the stronger model overall, scoring 51.5 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Qwen3.7 Max better for coding?

Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Qwen3.7 Max share?

17 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen3.7 Max has 33.

Related comparisons

Go deeper