Noometry

Model comparison

Claude Haiku 4.5 vs Qwen1.5-14B

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 32.7 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.5

Rank #165 Confirmed

Qwen1.5-14B Alibaba (Qwen)

32.7

Rank #253 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Qwen1.5-14B in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude Haiku 4.5 leads 57.9 to 33.6.
  • Qwen1.5-14B has downloadable open weights; the other is API-only.

Side by side

Claude Haiku 4.5Qwen1.5-14B
ProviderAnthropicAlibaba (Qwen)
Noometry Index39.532.7
Released2025-10-152024-02-04
WeightsProprietaryOpen
Context window200K—
Max output64K—
Input $ / M tokens$1—
Output $ / M tokens$5—
Results tracked5317

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

Category by category

Coding Claude Haiku 4.5 leads

Claude Haiku 4.5: 44.0 (#78), Qwen1.5-14B: 33.1 (#263)

BenchmarkClaude Haiku 4.5Qwen1.5-14B
LMArena Coding14531138
SWE-bench Verified (bash only)66.6%—
LMArena WebDev1330—
SWE-bench Multilingual64.7%—
SciCode43.3%—
WeirdML45.4%—
ALE-Bench653.48—

Agentic & Tool Use Not comparable

Claude Haiku 4.5: 33.6 (#52), Qwen1.5-14B: —

BenchmarkClaude Haiku 4.5Qwen1.5-14B
Terminal-Bench35.5%—
Berkeley Function Calling Leaderboard68.7%—
DeepResearch Bench45.5%—
BALROG31.2%—
ExploitBench13.7%—
Vending-Bench 2458.89—

Reasoning Qwen1.5-14B leads

Claude Haiku 4.5: 15.1 (#320), Qwen1.5-14B: 21.4 (#223)

BenchmarkClaude Haiku 4.5Qwen1.5-14B
LMArena Hard Prompts14201113
ARC-AGI-24%—
NYT Connections (extended)14.3%—
ARC-AGI-147.7%—
CritPt0%—
Chess Puzzles8%—
DTBench73.6%—
LMCA30.9%—
Epoch Capabilities Index142.41—
ForecastBench61.4—

Math Claude Haiku 4.5 leads

Claude Haiku 4.5: 44.9 (#78), Qwen1.5-14B: 32.4 (#215)

BenchmarkClaude Haiku 4.5Qwen1.5-14B
LMArena Math13961125
OTIS Mock AIME 2024-202566.7%—
Omni-MATH56.1%—
MATH Level 596.4%—
FrontierMath (Feb 2025 set)5.9%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Claude Haiku 4.5 leads

Claude Haiku 4.5: 37.7 (#153), Qwen1.5-14B: 29.8 (#232)

BenchmarkClaude Haiku 4.5Qwen1.5-14B
LMArena Expert14421094
GPQA Diamond71.2%—
SimpleQA Verified13.2%—
MMLU-Pro77.7%—
Vectara Hallucination Rate9.8%—
GPQA (HELM)60.5%—
MMLU—68.6%

Multimodal Not comparable

Claude Haiku 4.5: 26.8 (#118), Qwen1.5-14B: —

BenchmarkClaude Haiku 4.5Qwen1.5-14B
Blueprint-Bench 20%—
LMArena Document1420—

Multilingual Claude Haiku 4.5 leads

Claude Haiku 4.5: 49.9 (#129), Qwen1.5-14B: 30.7 (#262)

BenchmarkClaude Haiku 4.5Qwen1.5-14B
LMArena Non-English13771095
LMArena Chinese14171147
LMArena French14081116
LMArena German13751043
LMArena Japanese13391019
LMArena Russian13811046
LMArena Spanish14201085
LMArena Korean1347—

Instruction Following Claude Haiku 4.5 leads

Claude Haiku 4.5: 71.4 (#149), Qwen1.5-14B: 56.8 (#271)

BenchmarkClaude Haiku 4.5Qwen1.5-14B
LMArena Instruction Following14141102
IFEval80.1%—

Long Context Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.6 (#92), Qwen1.5-14B: 33.7 (#257)

BenchmarkClaude Haiku 4.5Qwen1.5-14B
LMArena Longer Query14271113

Writing & Preference Claude Haiku 4.5 leads

Claude Haiku 4.5: 57.9 (#123), Qwen1.5-14B: 33.6 (#276)

BenchmarkClaude Haiku 4.5Qwen1.5-14B
LMArena Text13961128
LMArena Creative Writing13721091
LMArena Multi-Turn14091110
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than Qwen1.5-14B?

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 32.7 on the Noometry Index.

Is Claude Haiku 4.5 or Qwen1.5-14B better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 33.1 in the Noometry coding category.

How many benchmarks do Claude Haiku 4.5 and Qwen1.5-14B share?

16 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Qwen1.5-14B has 17.

Related comparisons

Go deeper