Noometry

Model comparison

Claude Sonnet 4.6 vs Qwen2.5-VL 72B Instruct

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 29.9 on the Noometry Index.

Last verified . 2 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Qwen2.5-VL 72B Instruct Alibaba (Qwen)

29.9

Rank #302 Confirmed

Summary

  • They share 2 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 3 categories and Qwen2.5-VL 72B Instruct in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 20.7.
  • The biggest single-benchmark swing is OSWorld: 72.1% for Claude Sonnet 4.6 and 5% for Qwen2.5-VL 72B Instruct.
  • Qwen2.5-VL 72B Instruct is cheaper at $2.80 / $8.40 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 131K.
  • Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Qwen2.5-VL 72B Instruct
ProviderAnthropicAlibaba (Qwen)
Noometry Index50.329.9
Released2026-02-172024-09
WeightsProprietaryOpen
Context window1M131K
Max output128K8K
Input $ / M tokens$3$2.80
Output $ / M tokens$15$8.40
Results tracked576

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

Category by category

Coding Not comparable

Claude Sonnet 4.6: 46.3 (#67), Qwen2.5-VL 72B Instruct: —

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
LMArena WebDev1522—
SciCode46.8%—
WeirdML66.1%—
LMArena Coding1504—
ALE-Bench1,327—

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), Qwen2.5-VL 72B Instruct: 18.6 (#144)

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
OSWorld72.1%5%
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), Qwen2.5-VL 72B Instruct: 20.7 (#233)

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
ARC-AGI-260.4%—
Kagi LLM Benchmark—36%
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
CritPt3.1%—
Chess Puzzles13%—
Thematic Generalization76.3%—
LMArena Hard Prompts1484—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—
Epoch Capabilities Index152.24—
ForecastBench62—

Math Not comparable

Claude Sonnet 4.6: 52.9 (#49), Qwen2.5-VL 72B Instruct: —

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
OTIS Mock AIME 2024-202585.8%—
ProofBench45%—
LMArena Math1462—
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Not comparable

Claude Sonnet 4.6: 51.7 (#65), Qwen2.5-VL 72B Instruct: —

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
GPQA Diamond87.4%—
SimpleQA Verified35.5%—
Vectara Hallucination Rate10.6%—
LMArena Expert1500—

Multimodal Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 38.0 (#68), Qwen2.5-VL 72B Instruct: 33.5 (#97)

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
LMArena Vision12831107
Video-MME—73.5%
GeoBench—62%
Blueprint-Bench 26.7%—
LMArena Document1482—
SpatialViz-Bench—33.3%

Multilingual Not comparable

Claude Sonnet 4.6: 54.4 (#41), Qwen2.5-VL 72B Instruct: —

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
LMArena Non-English1440—
LMArena Chinese1491—
LMArena French1465—
LMArena German1428—
LMArena Japanese1420—
LMArena Korean1411—
LMArena Russian1440—
LMArena Spanish1464—

Instruction Following Not comparable

Claude Sonnet 4.6: 77.4 (#25), Qwen2.5-VL 72B Instruct: —

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
LMArena Instruction Following1475—

Long Context Not comparable

Claude Sonnet 4.6: 45.3 (#44), Qwen2.5-VL 72B Instruct: —

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
LMArena Longer Query1479—

Writing & Preference Not comparable

Claude Sonnet 4.6: 70.2 (#22), Qwen2.5-VL 72B Instruct: —

BenchmarkClaude Sonnet 4.6Qwen2.5-VL 72B Instruct
LMArena Text1458—
LMArena Creative Writing1435—
EQ-Bench Creative Writing1810—
EQ-Bench 41207—
LMArena Multi-Turn1464—

Frequently asked questions

Is Claude Sonnet 4.6 better than Qwen2.5-VL 72B Instruct?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 29.9 on the Noometry Index.

Which is cheaper, Claude Sonnet 4.6 or Qwen2.5-VL 72B Instruct?

Qwen2.5-VL 72B Instruct is cheaper. It lists at $2.80 per million input tokens and $8.40 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 131K.

How many benchmarks do Claude Sonnet 4.6 and Qwen2.5-VL 72B Instruct share?

2 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Qwen2.5-VL 72B Instruct has 6.

Related comparisons

Go deeper