Noometry

Model comparison

GPT-4 vs Qwen3.6 35B-A3B

Qwen3.6 35B-A3B is the stronger model overall, scoring 37.6 to 29.1 on the Noometry Index.

Last verified . 8 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Qwen3.6 35B-A3B Alibaba (Qwen)

37.6

Rank #201 Confirmed

Summary

  • They share 8 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Qwen3.6 35B-A3B in 4 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3.6 35B-A3B leads 51.3 to 18.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 86.7% for Qwen3.6 35B-A3B.
  • Qwen3.6 35B-A3B is cheaper at $0.25 / $1.49 per million input/output tokens, against $30 / $60 for GPT-4.
  • Qwen3.6 35B-A3B accepts more context: 262K tokens versus 8K.
  • Qwen3.6 35B-A3B has downloadable open weights; the other is API-only.

Side by side

GPT-4Qwen3.6 35B-A3B
ProviderOpenAIAlibaba (Qwen)
Noometry Index29.137.6
Released2023-03-142026-04-01
WeightsProprietaryOpen
Context window8K262K
Max output8K66K
Input $ / M tokens$30$0.25
Output $ / M tokens$60$1.49
Results tracked3814

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

Category by category

Coding Qwen3.6 35B-A3B leads

GPT-4: 31.6 (#283), Qwen3.6 35B-A3B: 37.2 (#196)

BenchmarkGPT-4Qwen3.6 35B-A3B
WeirdML12.4%34.5%
SciCode—35.8%
BigCodeBench Instruct46%—
LMArena Coding1254—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Qwen3.6 35B-A3B: 22.1 (#134)

BenchmarkGPT-4Qwen3.6 35B-A3B
Terminal-Bench—23%
METR Time Horizons36.1%—

Reasoning Qwen3.6 35B-A3B leads

GPT-4: 17.8 (#289), Qwen3.6 35B-A3B: 28.0 (#109)

BenchmarkGPT-4Qwen3.6 35B-A3B
Chess Puzzles4%26%
Mystery Game Puzzles12%22%
DTBench62.7%73.9%
LMCA17.1%29.7%
Epoch Capabilities Index125.89143.93
NYT Connections (extended)—41.6%
CritPt—0.3%
LMArena Hard Prompts1241—
Surface Evolver Bench—44.4%
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Qwen3.6 35B-A3B leads

GPT-4: 10.8 (#309), Qwen3.6 35B-A3B: 38.9 (#121)

BenchmarkGPT-4Qwen3.6 35B-A3B
OTIS Mock AIME 2024-20251.1%86.7%
FrontierMath (Tiers 1-3)—20.4%
LMArena Math1269—
MATH Level 523%—
GSM8K92%—

Knowledge Qwen3.6 35B-A3B leads

GPT-4: 18.4 (#282), Qwen3.6 35B-A3B: 51.3 (#68)

BenchmarkGPT-4Qwen3.6 35B-A3B
GPQA Diamond35.7%84.8%
LMArena Expert1211—
MMLU86.4%—
TriviaQA84.8%—

Multilingual Not comparable

GPT-4: 40.6 (#215), Qwen3.6 35B-A3B: —

BenchmarkGPT-4Qwen3.6 35B-A3B
LMArena Non-English1246—
LMArena Chinese1242—
LMArena French1283—
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—
LMArena Russian1251—
LMArena Spanish1261—

Instruction Following Not comparable

GPT-4: 65.3 (#222), Qwen3.6 35B-A3B: —

BenchmarkGPT-4Qwen3.6 35B-A3B
LMArena Instruction Following1241—

Long Context Not comparable

GPT-4: 37.7 (#212), Qwen3.6 35B-A3B: —

BenchmarkGPT-4Qwen3.6 35B-A3B
LMArena Longer Query1244—

Writing & Preference Not comparable

GPT-4: 34.9 (#268), Qwen3.6 35B-A3B: —

BenchmarkGPT-4Qwen3.6 35B-A3B
LMArena Text1263—
LMArena Creative Writing1244—
EQ-Bench Creative Writing752—
LMArena Multi-Turn1257—

Frequently asked questions

Is GPT-4 better than Qwen3.6 35B-A3B?

Qwen3.6 35B-A3B is the stronger model overall, scoring 37.6 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Qwen3.6 35B-A3B?

Qwen3.6 35B-A3B is cheaper. It lists at $0.25 per million input tokens and $1.49 per million output tokens; GPT-4 lists at $30 and $60.

Is GPT-4 or Qwen3.6 35B-A3B better for coding?

Qwen3.6 35B-A3B scores higher on coding benchmarks: 37.2 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Qwen3.6 35B-A3B does, with 262K tokens against 8K.

How many benchmarks do GPT-4 and Qwen3.6 35B-A3B share?

8 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Qwen3.6 35B-A3B has 14.

Related comparisons

Go deeper