Noometry

Model comparison

Claude 3.5 Haiku vs Qwen Max

Qwen Max is the stronger model overall, scoring 34.4 to 28.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3.5 Haiku Anthropic

28.9

Rank #309 Confirmed

Qwen Max Alibaba (Qwen)

34.4

Rank #226 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Qwen Max in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen Max leads 30.3 to 18.7.
  • The biggest single-benchmark swing is MATH Level 5: 46.4% for Claude 3.5 Haiku and 67.2% for Qwen Max.

Side by side

Claude 3.5 HaikuQwen Max
ProviderAnthropicAlibaba (Qwen)
Noometry Index28.934.4
Released2024-10-222024-04-03
WeightsProprietaryProprietary
Context window—33K
Max output—8K
Input $ / M tokens—$1.60
Output $ / M tokens—$6.40
Results tracked4923

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

Category by category

Coding Claude 3.5 Haiku leads

Claude 3.5 Haiku: 32.6 (#258), Qwen Max: 30.3 (#288)

BenchmarkClaude 3.5 HaikuQwen Max
Aider Polyglot28%21.8%
LMArena Coding12871288
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 27.7 (#90), Qwen Max: —

BenchmarkClaude 3.5 HaikuQwen Max
BALROG19.3%—

Reasoning Qwen Max leads

Claude 3.5 Haiku: 17.1 (#286), Qwen Max: 24.1 (#154)

BenchmarkClaude 3.5 HaikuQwen Max
LMArena Hard Prompts12511270
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Qwen Max leads

Claude 3.5 Haiku: 13.7 (#294), Qwen Max: 21.0 (#272)

BenchmarkClaude 3.5 HaikuQwen Max
OTIS Mock AIME 2024-20254.3%16.1%
LMArena Math12441275
MATH Level 546.4%67.2%
FrontierMath (Feb 2025 set)0.3%1%
Omni-MATH22.4%—
LiveBench Math35.5%—

Knowledge Qwen Max leads

Claude 3.5 Haiku: 18.7 (#276), Qwen Max: 30.3 (#222)

BenchmarkClaude 3.5 HaikuQwen Max
GPQA Diamond38.1%56.1%
LMArena Expert12081248
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Not comparable

Claude 3.5 Haiku: 26.3 (#113), Qwen Max: —

BenchmarkClaude 3.5 HaikuQwen Max
LMArena Vision1092—
GeoBench34%—

Multilingual Qwen Max leads

Claude 3.5 Haiku: 40.2 (#213), Qwen Max: 42.0 (#197)

BenchmarkClaude 3.5 HaikuQwen Max
LMArena Non-English12381263
LMArena Chinese12291254
LMArena French12621329
LMArena German12371254
LMArena Japanese11751205
LMArena Korean11721141
LMArena Russian12531274
LMArena Spanish12611290

Instruction Following Qwen Max leads

Claude 3.5 Haiku: 63.1 (#229), Qwen Max: 66.7 (#203)

BenchmarkClaude 3.5 HaikuQwen Max
LMArena Instruction Following12411262
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Qwen Max leads

Claude 3.5 Haiku: 38.3 (#195), Qwen Max: 39.4 (#175)

BenchmarkClaude 3.5 HaikuQwen Max
LMArena Longer Query12611289
Fiction.LiveBench—66.7%

Writing & Preference Qwen Max leads

Claude 3.5 Haiku: 42.9 (#228), Qwen Max: 48.0 (#200)

BenchmarkClaude 3.5 HaikuQwen Max
LMArena Text12551282
LMArena Creative Writing12331248
LMArena Multi-Turn12651277
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Qwen Max?

Qwen Max is the stronger model overall, scoring 34.4 to 28.9 on the Noometry Index.

Is Claude 3.5 Haiku or Qwen Max better for coding?

Claude 3.5 Haiku scores higher on coding benchmarks: 32.6 versus 30.3 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Qwen Max share?

22 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Qwen Max has 23.

Related comparisons

Go deeper