Noometry

Model comparison

Qwen2.5-VL 72B Instruct vs Qwen3.5-Flash

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 29.9 on the Noometry Index.

Last verified . 0 shared benchmarks.

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

29.9

Rank #302 Confirmed

Qwen3.5-Flash Alibaba (Qwen)

42.5

Rank #112 Confirmed

Summary

  • The widest gap is in reasoning, where Qwen3.5-Flash leads 33.7 to 20.7.
  • Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $2.80 / $8.40 for Qwen2.5-VL 72B Instruct.
  • Qwen3.5-Flash accepts more context: 1M tokens versus 131K.
  • Qwen2.5-VL 72B Instruct has downloadable open weights; the other is API-only.

Side by side

Qwen2.5-VL 72B InstructQwen3.5-Flash
ProviderAlibaba (Qwen)Alibaba (Qwen)
Noometry Index29.942.5
Released2024-092026-02-23
WeightsOpenProprietary
Context window131K1M
Max output8K66K
Input $ / M tokens$2.80$0.10
Output $ / M tokens$8.40$0.40
Results tracked632

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

Category by category

Coding Not comparable

Qwen2.5-VL 72B Instruct: —, Qwen3.5-Flash: 34.2 (#242)

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
LMArena WebDev—1244
LMArena Coding—1412
ALE-Bench—221.8

Agentic & Tool Use Not comparable

Qwen2.5-VL 72B Instruct: 18.6 (#144), Qwen3.5-Flash: —

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
OSWorld5%—
Vending-Bench 2—462.69

Reasoning Qwen3.5-Flash leads

Qwen2.5-VL 72B Instruct: 20.7 (#233), Qwen3.5-Flash: 33.7 (#72)

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
Kagi LLM Benchmark36%—
Chess Puzzles—21%
LMArena Hard Prompts—1403
Mystery Game Puzzles—20%
DTBench—82.9%
LMCA—29.1%
Epoch Capabilities Index—143.98

Math Not comparable

Qwen2.5-VL 72B Instruct: —, Qwen3.5-Flash: 37.4 (#158)

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
FrontierMath (Tiers 1-3)—18.2%
OTIS Mock AIME 2024-2025—84.4%
LMArena Math—1407
FrontierMath (Feb 2025 set)—6.2%
FrontierMath Tier 4 (v1)—0%

Knowledge Not comparable

Qwen2.5-VL 72B Instruct: —, Qwen3.5-Flash: 43.2 (#93)

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
GPQA Diamond—82.3%
SimpleQA Verified—20.3%
Vectara Hallucination Rate—10.5%
LMArena Expert—1407

Multimodal Not comparable

Qwen2.5-VL 72B Instruct: 33.5 (#97), Qwen3.5-Flash: —

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
LMArena Vision1107—
Video-MME73.5%—
GeoBench62%—
SpatialViz-Bench33.3%—

Multilingual Not comparable

Qwen2.5-VL 72B Instruct: —, Qwen3.5-Flash: 50.5 (#121)

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
LMArena Non-English—1385
LMArena Chinese—1446
LMArena French—1412
LMArena German—1390
LMArena Japanese—1368
LMArena Korean—1344
LMArena Russian—1379
LMArena Spanish—1400

Instruction Following Not comparable

Qwen2.5-VL 72B Instruct: —, Qwen3.5-Flash: 72.6 (#139)

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
LMArena Instruction Following—1374

Long Context Not comparable

Qwen2.5-VL 72B Instruct: —, Qwen3.5-Flash: 42.4 (#124)

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
LMArena Longer Query—1392

Writing & Preference Not comparable

Qwen2.5-VL 72B Instruct: —, Qwen3.5-Flash: 57.9 (#122)

BenchmarkQwen2.5-VL 72B InstructQwen3.5-Flash
LMArena Text—1397
LMArena Creative Writing—1343
LMArena Multi-Turn—1393

Frequently asked questions

Is Qwen2.5-VL 72B Instruct better than Qwen3.5-Flash?

Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 29.9 on the Noometry Index.

Which is cheaper, Qwen2.5-VL 72B Instruct or Qwen3.5-Flash?

Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Qwen2.5-VL 72B Instruct lists at $2.80 and $8.40.

Which has the bigger context window?

Qwen3.5-Flash does, with 1M tokens against 131K.

How many benchmarks do Qwen2.5-VL 72B Instruct and Qwen3.5-Flash share?

0 benchmarks have published results for both models. Qwen2.5-VL 72B Instruct has 6 scored results on Noometry and Qwen3.5-Flash has 32.

Related comparisons

Go deeper