Noometry

Model comparison

GPT-4 vs Qwen3-VL 235B-A22B

Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 29.1 on the Noometry Index.

Last verified . 17 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Qwen3-VL 235B-A22B Alibaba (Qwen)

43.2

Rank #95 Confirmed

Summary

  • They share 17 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen3-VL 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3-VL 235B-A22B leads 39.0 to 10.8.
  • Qwen3-VL 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen3-VL 235B-A22B accepts more context: 131K tokens versus 8K.
  • Qwen3-VL 235B-A22B has downloadable open weights; the other is API-only.

Side by side

GPT-4Qwen3-VL 235B-A22B
ProviderOpenAIAlibaba (Qwen)
Noometry Index29.143.2
Released2023-03-142025-04
WeightsProprietaryOpen
Context window8K131K
Max output8K33K
Input $ / M tokens$30$0.70
Output $ / M tokens$60$2.80
Results tracked3818

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

Category by category

Coding Qwen3-VL 235B-A22B leads

GPT-4: 31.6 (#283), Qwen3-VL 235B-A22B: 42.4 (#100)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Coding12541439
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen3-VL 235B-A22B: —

BenchmarkGPT-4Qwen3-VL 235B-A22B
METR Time Horizons36.1%—

Reasoning Qwen3-VL 235B-A22B leads

GPT-4: 17.8 (#289), Qwen3-VL 235B-A22B: 29.3 (#92)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Hard Prompts12411428
Chess Puzzles4%—
Mystery Game Puzzles12%—
DTBench62.7%—
LMCA17.1%—
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.89—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Qwen3-VL 235B-A22B leads

GPT-4: 10.8 (#309), Qwen3-VL 235B-A22B: 39.0 (#118)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Math12691426
OTIS Mock AIME 2024-20251.1%—
MATH Level 523%—
GSM8K92%—

Knowledge Qwen3-VL 235B-A22B leads

GPT-4: 18.4 (#282), Qwen3-VL 235B-A22B: 40.3 (#121)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Expert12111442
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Qwen3-VL 235B-A22B: 39.8 (#55)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Vision—1247

Multilingual Qwen3-VL 235B-A22B leads

GPT-4: 40.6 (#215), Qwen3-VL 235B-A22B: 51.9 (#97)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Non-English12461405
LMArena Chinese12421463
LMArena French12831452
LMArena German12511424
LMArena Japanese12091385
LMArena Korean11841394
LMArena Russian12511408
LMArena Spanish12611428

Instruction Following Qwen3-VL 235B-A22B leads

GPT-4: 65.3 (#222), Qwen3-VL 235B-A22B: 74.2 (#101)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Instruction Following12411406

Long Context Qwen3-VL 235B-A22B leads

GPT-4: 37.7 (#212), Qwen3-VL 235B-A22B: 43.4 (#98)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Longer Query12441420

Writing & Preference Qwen3-VL 235B-A22B leads

GPT-4: 34.9 (#268), Qwen3-VL 235B-A22B: 60.2 (#99)

BenchmarkGPT-4Qwen3-VL 235B-A22B
LMArena Text12631420
LMArena Creative Writing12441366
LMArena Multi-Turn12571428
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Qwen3-VL 235B-A22B?

Qwen3-VL 235B-A22B is the stronger model overall, scoring 43.2 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Qwen3-VL 235B-A22B?

Qwen3-VL 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Qwen3-VL 235B-A22B better for coding?

Qwen3-VL 235B-A22B scores higher on coding benchmarks: 42.4 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Qwen3-VL 235B-A22B does, with 131K tokens against 8K.

How many benchmarks do GPT-4 and Qwen3-VL 235B-A22B share?

17 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen3-VL 235B-A22B has 18.

Related comparisons

Go deeper