Noometry

Model comparison

Claude Haiku 4.5 vs Qwen2-72B

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 30.0 on the Noometry Index.

Last verified . 21 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.5

Rank #165 Confirmed

Qwen2-72B Alibaba (Qwen)

30.0

Rank #300 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 8 categories and Qwen2-72B in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Claude Haiku 4.5 leads 57.9 to 40.8.
  • The biggest single-benchmark swing is MATH Level 5: 96.4% for Claude Haiku 4.5 and 39.1% for Qwen2-72B.
  • Qwen2-72B has downloadable open weights; the other is API-only.

Side by side

Claude Haiku 4.5Qwen2-72B
ProviderAnthropicAlibaba (Qwen)
Noometry Index39.530.0
Released2025-10-152024-06-07
WeightsProprietaryOpen
Context window200K—
Max output64K—
Input $ / M tokens$1—
Output $ / M tokens$5—
Results tracked5326

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), Qwen2-72B: 29.1 (#310)

BenchmarkClaude Haiku 4.5Qwen2-72B
WeirdML45.4%11.3%
LMArena Coding14531196
SWE-bench Verified (bash only)66.6%—
LMArena WebDev1330—
SWE-bench Multilingual64.7%—
SciCode43.3%—
BigCodeBench Instruct—38.5%
BigCodeBench Complete—54%
ALE-Bench653.48—

Agentic & Tool Use Claude Haiku 4.5 leads

Claude Haiku 4.5: 33.6 (#52), Qwen2-72B: 17.0 (#146)

BenchmarkClaude Haiku 4.5Qwen2-72B
Terminal-Bench35.5%—
Berkeley Function Calling Leaderboard68.7%—
TheAgentCompany—1.1%
DeepResearch Bench45.5%—
BALROG31.2%—
ExploitBench13.7%—
METR Time Horizons—29.9%
Vending-Bench 2458.89—

Reasoning Qwen2-72B leads

Claude Haiku 4.5: 15.1 (#320), Qwen2-72B: 23.2 (#181)

BenchmarkClaude Haiku 4.5Qwen2-72B
LMArena Hard Prompts14201191
Epoch Capabilities Index142.41125.28
ARC-AGI-24%—
NYT Connections (extended)14.3%—
ARC-AGI-147.7%—
CritPt0%—
Chess Puzzles8%—
DTBench73.6%—
LMCA30.9%—
ForecastBench61.4—

Math Claude Haiku 4.5 leads

Claude Haiku 4.5: 44.9 (#78), Qwen2-72B: 30.2 (#236)

BenchmarkClaude Haiku 4.5Qwen2-72B
LMArena Math13961235
MATH Level 596.4%39.1%
OTIS Mock AIME 2024-202566.7%—
Omni-MATH56.1%—
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), Qwen2-72B: 21.2 (#275)

BenchmarkClaude Haiku 4.5Qwen2-72B
GPQA Diamond71.2%40.8%
LMArena Expert14421171
SimpleQA Verified13.2%—
MMLU-Pro77.7%—
Vectara Hallucination Rate9.8%—
GPQA (HELM)60.5%—
MMLU—82.4%

Multimodal Not comparable

Claude Haiku 4.5: 26.8 (#118), Qwen2-72B: —

BenchmarkClaude Haiku 4.5Qwen2-72B
Blueprint-Bench 20%—
LMArena Document1420—

Multilingual Claude Haiku 4.5 leads

Claude Haiku 4.5: 49.9 (#129), Qwen2-72B: 35.9 (#244)

BenchmarkClaude Haiku 4.5Qwen2-72B
LMArena Non-English13771176
LMArena Chinese14171240
LMArena French14081170
LMArena German13751151
LMArena Japanese13391111
LMArena Korean13471083
LMArena Russian13811169
LMArena Spanish14201169

Instruction Following Claude Haiku 4.5 leads

Claude Haiku 4.5: 71.4 (#149), Qwen2-72B: 61.7 (#241)

BenchmarkClaude Haiku 4.5Qwen2-72B
LMArena Instruction Following14141181
IFEval80.1%—

Long Context Claude Haiku 4.5 leads

Claude Haiku 4.5: 43.6 (#92), Qwen2-72B: 36.1 (#235)

BenchmarkClaude Haiku 4.5Qwen2-72B
LMArena Longer Query14271192

Writing & Preference Claude Haiku 4.5 leads

Claude Haiku 4.5: 57.9 (#123), Qwen2-72B: 40.8 (#241)

BenchmarkClaude Haiku 4.5Qwen2-72B
LMArena Text13961203
LMArena Creative Writing13721181
LMArena Multi-Turn14091196
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than Qwen2-72B?

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 30.0 on the Noometry Index.

Is Claude Haiku 4.5 or Qwen2-72B better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 29.1 in the Noometry coding category.

How many benchmarks do Claude Haiku 4.5 and Qwen2-72B share?

21 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Qwen2-72B has 26.

Related comparisons

Go deeper