Noometry

Model comparison

GPT-4 vs Qwen3.5 122B-A10B

Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 28.9 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-4 OpenAI

28.9

Rank #308 Confirmed

Qwen3.5 122B-A10B Alibaba (Qwen)

41.6

Rank #120 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen3.5 122B-A10B in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Qwen3.5 122B-A10B leads 36.4 to 10.1.
  • The biggest single-benchmark swing is DTBench: 62.7% for GPT-4 and 84.3% for Qwen3.5 122B-A10B.
  • Qwen3.5 122B-A10B is cheaper at $0.40 / $3.20 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen3.5 122B-A10B accepts more context: 262K tokens versus 8K.
  • Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.

Side by side

GPT-4Qwen3.5 122B-A10B
ProviderOpenAIAlibaba (Qwen)
Noometry Index28.941.6
Released2023-03-142026-02-23
WeightsProprietaryOpen
Context window8K262K
Max output8K66K
Input $ / M tokens$30$0.40
Output $ / M tokens$60$3.20
Results tracked3827

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

Category by category

Coding Qwen3.5 122B-A10B leads

GPT-4: 31.2 (#277), Qwen3.5 122B-A10B: 38.8 (#155)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Coding12541436
LMArena WebDev—1360
SciCode—35.6%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen3.5 122B-A10B: —

BenchmarkGPT-4Qwen3.5 122B-A10B
METR Time Horizons36.1%—

Reasoning Qwen3.5 122B-A10B leads

GPT-4: 17.3 (#285), Qwen3.5 122B-A10B: 26.4 (#121)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Hard Prompts12411421
Mystery Game Puzzles12%17%
DTBench62.7%84.3%
LMCA17.1%32.2%
NYT Connections (extended)—51.7%
CritPt—0.9%
Chess Puzzles4%—
Thematic Generalization—51.2%
BIG-Bench Hard75.1%—
Epoch Capabilities Index125.88—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Qwen3.5 122B-A10B leads

GPT-4: 10.1 (#304), Qwen3.5 122B-A10B: 36.4 (#114)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Math12691432
OTIS Mock AIME 2024-20251.1%—
MATH Level 523%—
GSM8K92%—

Knowledge Qwen3.5 122B-A10B leads

GPT-4: 18.4 (#277), Qwen3.5 122B-A10B: 38.2 (#138)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Expert12111431
GPQA Diamond35.7%—
Vectara Hallucination Rate—11.2%
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Qwen3.5 122B-A10B: 39.0 (#52)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Vision—1245

Multilingual Qwen3.5 122B-A10B leads

GPT-4: 40.8 (#210), Qwen3.5 122B-A10B: 51.8 (#101)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Non-English12461400
LMArena Chinese12421462
LMArena French12821442
LMArena German12511425
LMArena Japanese12091364
LMArena Korean11841353
LMArena Russian12511400
LMArena Spanish12611423

Instruction Following Qwen3.5 122B-A10B leads

GPT-4: 65.5 (#217), Qwen3.5 122B-A10B: 74.0 (#109)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Instruction Following12411399

Long Context Qwen3.5 122B-A10B leads

GPT-4: 37.7 (#207), Qwen3.5 122B-A10B: 43.0 (#105)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Longer Query12441410

Writing & Preference Qwen3.5 122B-A10B leads

GPT-4: 35.0 (#263), Qwen3.5 122B-A10B: 60.2 (#98)

BenchmarkGPT-4Qwen3.5 122B-A10B
LMArena Text12631417
LMArena Creative Writing12441369
LMArena Multi-Turn12571416
EQ-Bench Creative Writing752—

Frequently asked questions

Is GPT-4 better than Qwen3.5 122B-A10B?

Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 28.9 on the Noometry Index.

Which is cheaper, GPT-4 or Qwen3.5 122B-A10B?

Qwen3.5 122B-A10B is cheaper. It lists at $0.40 per million input tokens and $3.20 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Qwen3.5 122B-A10B better for coding?

Qwen3.5 122B-A10B scores higher on coding benchmarks: 38.8 versus 31.2 in the Noometry coding category.

Which has the bigger context window?

Qwen3.5 122B-A10B does, with 262K tokens against 8K.

How many benchmarks do GPT-4 and Qwen3.5 122B-A10B share?

20 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen3.5 122B-A10B has 27.

Related comparisons

Go deeper