Noometry

Model comparison

Claude 3 Haiku vs Qwen2.5-Max

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 25.9 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Qwen2.5-Max Alibaba (Qwen)

40.7

Rank #146 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen2.5-Max leads 36.9 to 9.8.
  • The biggest single-benchmark swing is Confabulations: 34.2% for Claude 3 Haiku and 21.8% for Qwen2.5-Max.

Side by side

Claude 3 HaikuQwen2.5-Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index25.940.7
Released2024-03-072025-01-25
WeightsProprietaryProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3727

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

Category by category

Coding Qwen2.5-Max leads

Claude 3 Haiku: 26.4 (#325), Qwen2.5-Max: 41.8 (#117)

BenchmarkClaude 3 HaikuQwen2.5-Max
LMArena Coding11991359
WeirdML9.8%—
BigCodeBench Instruct39.4%—
LiveBench Coding—64.4%
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Qwen2.5-Max leads

Claude 3 Haiku: 16.3 (#307), Qwen2.5-Max: 25.6 (#147)

BenchmarkClaude 3 HaikuQwen2.5-Max
LMArena Hard Prompts11741360
Epoch Capabilities Index118.35132.53
Kagi LLM Benchmark34.2%—
LiveBench Reasoning—51.4%
DTBench50.1%—
LiveBench Data Analysis—67.9%
LMCA8.8%—
ForecastBench53.2—
LiveBench—62.3%
WinoGrande74.2%—

Math Qwen2.5-Max leads

Claude 3 Haiku: 9.8 (#319), Qwen2.5-Max: 36.9 (#162)

BenchmarkClaude 3 HaikuQwen2.5-Max
LMArena Math11881369
OTIS Mock AIME 2024-20251.8%—
LiveBench Math—58.4%
MATH Level 514.9%—

Knowledge Qwen2.5-Max leads

Claude 3 Haiku: 17.3 (#285), Qwen2.5-Max: 35.3 (#186)

BenchmarkClaude 3 HaikuQwen2.5-Max
Confabulations34.2%21.8%
LMArena Expert11481337
GPQA Diamond36.3%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Qwen2.5-Max: —

BenchmarkClaude 3 HaikuQwen2.5-Max
LMArena Vision950—
ScienceQA72%—

Multilingual Qwen2.5-Max leads

Claude 3 Haiku: 36.0 (#243), Qwen2.5-Max: 48.1 (#146)

BenchmarkClaude 3 HaikuQwen2.5-Max
LMArena Non-English11781352
LMArena Chinese11551382
LMArena French11951396
LMArena German11741350
LMArena Japanese11021300
LMArena Korean11091304
LMArena Russian12041353
LMArena Spanish11661377

Instruction Following Qwen2.5-Max leads

Claude 3 Haiku: 61.3 (#247), Qwen2.5-Max: 71.3 (#152)

BenchmarkClaude 3 HaikuQwen2.5-Max
LMArena Instruction Following11731335
LiveBench Instruction Following—75.3%

Long Context Qwen2.5-Max leads

Claude 3 Haiku: 36.1 (#237), Qwen2.5-Max: 41.4 (#142)

BenchmarkClaude 3 HaikuQwen2.5-Max
LMArena Longer Query11901358

Writing & Preference Qwen2.5-Max leads

Claude 3 Haiku: 29.7 (#291), Qwen2.5-Max: 55.4 (#146)

BenchmarkClaude 3 HaikuQwen2.5-Max
LMArena Text11951367
LMArena Creative Writing11571339
LMArena Multi-Turn11901364
Short-Story Creative Writing—72.9%
EQ-Bench Creative Writing717—
LiveBench Language—56.3%

Frequently asked questions

Is Claude 3 Haiku better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.7 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Qwen2.5-Max share?

19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen2.5-Max has 27.

Related comparisons

Go deeper