Noometry

Model comparison

Claude 3 Haiku vs QwQ-32B

QwQ-32B is the stronger model overall, scoring 39.4 to 25.7 on the Noometry Index.

Last verified . 25 shared benchmarks.

Claude 3 Haiku Anthropic

25.7

Rank #333 Confirmed

QwQ-32B Alibaba (Qwen)

39.4

Rank #153 Confirmed

Summary

  • They share 25 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and QwQ-32B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where QwQ-32B leads 36.2 to 9.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.8% for Claude 3 Haiku and 59.2% for QwQ-32B.
  • QwQ-32B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuQwQ-32B
ProviderAnthropicAlibaba (Qwen)
Noometry Index25.739.4
Released2024-03-072024-11-28
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3736

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

Category by category

Coding QwQ-32B leads

Claude 3 Haiku: 26.1 (#320), QwQ-32B: 34.9 (#220)

BenchmarkClaude 3 HaikuQwQ-32B
BigCodeBench Instruct39.4%44.6%
LMArena Coding11991333
BigCodeBench Complete50.1%54.4%
Aider Polyglot—20.9%
WeirdML9.8%—
LiveBench Coding—72.2%
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning QwQ-32B leads

Claude 3 Haiku: 15.7 (#303), QwQ-32B: 22.9 (#171)

BenchmarkClaude 3 HaikuQwQ-32B
LMArena Hard Prompts11741326
Epoch Capabilities Index118.3137.6
ForecastBench53.258.3
Kagi LLM Benchmark34.2%—
Chess Puzzles—5%
LiveBench Reasoning—83.5%
DTBench50.1%—
LiveBench Data Analysis—65%
LMCA8.8%—
LiveBench—72%
WinoGrande74.2%—

Math QwQ-32B leads

Claude 3 Haiku: 9.2 (#313), QwQ-32B: 36.2 (#123)

BenchmarkClaude 3 HaikuQwQ-32B
OTIS Mock AIME 2024-20251.8%59.2%
LMArena Math11881359
LiveBench Math—77.8%
MATH Level 514.9%—

Knowledge QwQ-32B leads

Claude 3 Haiku: 17.3 (#280), QwQ-32B: 37.2 (#150)

BenchmarkClaude 3 HaikuQwQ-32B
GPQA Diamond36.3%65.3%
Confabulations34.2%15.6%
LMArena Expert11481323
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.1 (#123), QwQ-32B: —

BenchmarkClaude 3 HaikuQwQ-32B
LMArena Vision950—
ScienceQA72%—

Multilingual QwQ-32B leads

Claude 3 Haiku: 36.1 (#238), QwQ-32B: 45.0 (#171)

BenchmarkClaude 3 HaikuQwQ-32B
LMArena Non-English11781306
LMArena Chinese11551378
LMArena French11941337
LMArena German11741313
LMArena Japanese11021263
LMArena Korean11081278
LMArena Russian12041297
LMArena Spanish11651353

Instruction Following QwQ-32B leads

Claude 3 Haiku: 61.5 (#242), QwQ-32B: 72.8 (#131)

BenchmarkClaude 3 HaikuQwQ-32B
LMArena Instruction Following11741297
LiveBench Instruction Following—81.8%

Long Context QwQ-32B leads

Claude 3 Haiku: 36.1 (#232), QwQ-32B: 49.0 (#11)

BenchmarkClaude 3 HaikuQwQ-32B
LMArena Longer Query11911308
Fiction.LiveBench—83.3%

Writing & Preference QwQ-32B leads

Claude 3 Haiku: 29.8 (#286), QwQ-32B: 50.9 (#175)

BenchmarkClaude 3 HaikuQwQ-32B
LMArena Text11951329
LMArena Creative Writing11571288
EQ-Bench Creative Writing7171257
LMArena Multi-Turn11901314
Short-Story Creative Writing—80.2%
LiveBench Language—51.4%

Frequently asked questions

Is Claude 3 Haiku better than QwQ-32B?

QwQ-32B is the stronger model overall, scoring 39.4 to 25.7 on the Noometry Index.

Is Claude 3 Haiku or QwQ-32B better for coding?

QwQ-32B scores higher on coding benchmarks: 34.9 versus 26.1 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and QwQ-32B share?

25 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and QwQ-32B has 36.

Related comparisons

Go deeper