Noometry

Model comparison

Claude 3 Haiku vs Qwen2.5 7B Instruct

Qwen2.5 7B Instruct is the stronger model overall, scoring 29.0 to 25.9 on the Noometry Index.

Last verified . 8 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Qwen2.5 7B Instruct Alibaba (Qwen)

29.0

Rank #320 Confirmed

Summary

  • They share 8 benchmarks with published results for both. Claude 3 Haiku scores higher in 2 categories and Qwen2.5 7B Instruct in 4 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 29.7.
  • Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.

Side by side

Claude 3 HaikuQwen2.5 7B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index25.929.0
Released2024-03-072024-09
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.17
Output $ / M tokens—$0.70
Results tracked3715

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

Category by category

Coding Qwen2.5 7B Instruct leads

Claude 3 Haiku: 26.4 (#325), Qwen2.5 7B Instruct: 36.5 (#208)

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
BigCodeBench Instruct39.4%37.6%
BigCodeBench Complete50.1%46.1%
WeirdML9.8%—
LMArena Coding1199—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Qwen2.5 7B Instruct: 23.8 (#124)

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
BALROG—7.8%

Reasoning Claude 3 Haiku leads

Claude 3 Haiku: 16.3 (#307), Qwen2.5 7B Instruct: 14.8 (#322)

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
DTBench50.1%47.7%
LMCA8.8%6.4%
Epoch Capabilities Index118.35118.51
Kagi LLM Benchmark34.2%—
Chess Puzzles—0%
LMArena Hard Prompts1174—
ForecastBench53.2—
WinoGrande74.2%—

Math Qwen2.5 7B Instruct leads

Claude 3 Haiku: 9.8 (#319), Qwen2.5 7B Instruct: 12.6 (#306)

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
OTIS Mock AIME 2024-20251.8%2.5%
Omni-MATH—29.4%
LMArena Math1188—
MATH Level 514.9%—

Knowledge Too close to call

Claude 3 Haiku: 17.3 (#285), Qwen2.5 7B Instruct: 17.0 (#286)

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
GPQA Diamond36.3%35.5%
MMLU73.8%72.9%
MMLU-Pro—53.9%
Confabulations34.2%—
GPQA (HELM)—34.1%
LMArena Expert1148—

Multimodal Not comparable

Claude 3 Haiku: 23.6 (#128), Qwen2.5 7B Instruct: —

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
LMArena Vision950—
ScienceQA72%—

Multilingual Not comparable

Claude 3 Haiku: 36.0 (#243), Qwen2.5 7B Instruct: —

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
LMArena Non-English1178—
LMArena Chinese1155—
LMArena French1195—
LMArena German1174—
LMArena Japanese1102—
LMArena Korean1109—
LMArena Russian1204—
LMArena Spanish1166—

Instruction Following Qwen2.5 7B Instruct leads

Claude 3 Haiku: 61.3 (#247), Qwen2.5 7B Instruct: 63.2 (#231)

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
IFEval—74.1%
LMArena Instruction Following1173—

Long Context Not comparable

Claude 3 Haiku: 36.1 (#237), Qwen2.5 7B Instruct: —

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
LMArena Longer Query1190—

Writing & Preference Qwen2.5 7B Instruct leads

Claude 3 Haiku: 29.7 (#291), Qwen2.5 7B Instruct: 48.8 (#195)

BenchmarkClaude 3 HaikuQwen2.5 7B Instruct
LMArena Text1195—
LMArena Creative Writing1157—
EQ-Bench Creative Writing717—
WildBench—73.1%
LMArena Multi-Turn1190—

Frequently asked questions

Is Claude 3 Haiku better than Qwen2.5 7B Instruct?

Qwen2.5 7B Instruct is the stronger model overall, scoring 29.0 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Qwen2.5 7B Instruct better for coding?

Qwen2.5 7B Instruct scores higher on coding benchmarks: 36.5 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Qwen2.5 7B Instruct share?

8 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen2.5 7B Instruct has 15.

Related comparisons

Go deeper