Noometry

Model comparison

Claude 3 Haiku vs Qwen1.5-110B

Qwen1.5-110B is the stronger model overall, scoring 34.2 to 25.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Qwen1.5-110B Alibaba (Qwen)

34.2

Rank #234 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Claude 3 Haiku scores higher in 3 categories and Qwen1.5-110B in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen1.5-110B leads 33.7 to 9.8.
  • The biggest single-benchmark swing is BigCodeBench Complete: 50.1% for Claude 3 Haiku and 44.4% for Qwen1.5-110B.
  • Qwen1.5-110B has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuQwen1.5-110B
ProviderAnthropicAlibaba (Qwen)
Noometry Index25.934.2
Released2024-03-072024-04-25
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked3720

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

Category by category

Coding Qwen1.5-110B leads

Claude 3 Haiku: 26.4 (#325), Qwen1.5-110B: 33.0 (#264)

BenchmarkClaude 3 HaikuQwen1.5-110B
BigCodeBench Instruct39.4%35%
LMArena Coding11991184
BigCodeBench Complete50.1%44.4%
WeirdML9.8%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Reasoning Qwen1.5-110B leads

Claude 3 Haiku: 16.3 (#307), Qwen1.5-110B: 22.7 (#189)

BenchmarkClaude 3 HaikuQwen1.5-110B
LMArena Hard Prompts11741168
ForecastBench53.257.7
Kagi LLM Benchmark34.2%—
DTBench50.1%—
LMCA8.8%—
Epoch Capabilities Index118.35—
WinoGrande74.2%—

Math Qwen1.5-110B leads

Claude 3 Haiku: 9.8 (#319), Qwen1.5-110B: 33.7 (#201)

BenchmarkClaude 3 HaikuQwen1.5-110B
LMArena Math11881185
OTIS Mock AIME 2024-20251.8%—
MATH Level 514.9%—

Knowledge Qwen1.5-110B leads

Claude 3 Haiku: 17.3 (#285), Qwen1.5-110B: 31.2 (#219)

BenchmarkClaude 3 HaikuQwen1.5-110B
LMArena Expert11481144
GPQA Diamond36.3%—
Confabulations34.2%—
MMLU73.8%—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Qwen1.5-110B: —

BenchmarkClaude 3 HaikuQwen1.5-110B
LMArena Vision950—
ScienceQA72%—

Multilingual Claude 3 Haiku leads

Claude 3 Haiku: 36.0 (#243), Qwen1.5-110B: 33.6 (#250)

BenchmarkClaude 3 HaikuQwen1.5-110B
LMArena Non-English11781142
LMArena Chinese11551206
LMArena French11951151
LMArena German11741123
LMArena Japanese11021074
LMArena Korean11091044
LMArena Russian12041118
LMArena Spanish11661142

Instruction Following Too close to call

Claude 3 Haiku: 61.3 (#247), Qwen1.5-110B: 60.3 (#252)

BenchmarkClaude 3 HaikuQwen1.5-110B
LMArena Instruction Following11731158

Long Context Claude 3 Haiku leads

Claude 3 Haiku: 36.1 (#237), Qwen1.5-110B: 35.1 (#242)

BenchmarkClaude 3 HaikuQwen1.5-110B
LMArena Longer Query11901157

Writing & Preference Qwen1.5-110B leads

Claude 3 Haiku: 29.7 (#291), Qwen1.5-110B: 38.0 (#255)

BenchmarkClaude 3 HaikuQwen1.5-110B
LMArena Text11951175
LMArena Creative Writing11571148
LMArena Multi-Turn11901160
EQ-Bench Creative Writing717—

Frequently asked questions

Is Claude 3 Haiku better than Qwen1.5-110B?

Qwen1.5-110B is the stronger model overall, scoring 34.2 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Qwen1.5-110B better for coding?

Qwen1.5-110B scores higher on coding benchmarks: 33.0 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Qwen1.5-110B share?

20 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen1.5-110B has 20.

Related comparisons

Go deeper