Noometry

Model comparison

GPT-3.5-turbo vs Qwen Plus

Qwen Plus is the stronger model overall, scoring 37.1 to 23.2 on the Noometry Index.

Last verified . 18 shared benchmarks.

GPT-3.5-turbo OpenAI

23.2

Rank #350 Confirmed

Qwen Plus Alibaba (Qwen)

37.1

Rank #210 Confirmed

Summary

  • They share 18 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Qwen Plus leads 52.2 to 25.3.
  • The biggest single-benchmark swing is MATH Level 5: 15.9% for GPT-3.5-turbo and 65.3% for Qwen Plus.
  • Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $0.50 / $1.50 for GPT-3.5-turbo.
  • Qwen Plus accepts more context: 1M tokens versus 16K.

Side by side

GPT-3.5-turboQwen Plus
ProviderOpenAIAlibaba (Qwen)
Noometry Index23.237.1
Released2023-03-012024-01-25
WeightsProprietaryProprietary
Context window16K1M
Max output4K33K
Input $ / M tokens$0.50$0.40
Output $ / M tokens$1.50$1.20
Results tracked4420

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

Category by category

Coding Qwen Plus leads

GPT-3.5-turbo: 23.9 (#331), Qwen Plus: 38.9 (#167)

BenchmarkGPT-3.5-turboQwen Plus
LMArena Coding11361328
WeirdML3.5%—
BigCodeBench Instruct39.1%—
BigCodeBench Complete50.6%—
HumanEval+70.7%—
MBPP+69.7%—

Agentic & Tool Use Not comparable

GPT-3.5-turbo: —, Qwen Plus: —

BenchmarkGPT-3.5-turboQwen Plus
METR Time Horizons21.5%—

Reasoning Qwen Plus leads

GPT-3.5-turbo: 13.8 (#332), Qwen Plus: 28.4 (#107)

BenchmarkGPT-3.5-turboQwen Plus
LMArena Hard Prompts11081317
DTBench48.5%81.1%
LMCA9.7%24%
Kagi LLM Benchmark—63.3%
Chess Puzzles0%—
Mystery Game Puzzles3%—
Adversarial NLI58.1%—
BIG-Bench Hard61.6%—
CommonsenseQA 2.057%—
Epoch Capabilities Index118.55—
ForecastBench50.4—
WinoGrande81.6%—

Math Qwen Plus leads

GPT-3.5-turbo: 6.3 (#327), Qwen Plus: 23.3 (#271)

BenchmarkGPT-3.5-turboQwen Plus
OTIS Mock AIME 2024-20252.2%17.8%
LMArena Math11421326
MATH Level 515.9%65.3%
FrontierMath (Tiers 1-3)0%—
FrontierMath (Feb 2025 set)—1.7%
GSM8K57.8%—

Knowledge Qwen Plus leads

GPT-3.5-turbo: 10.0 (#303), Qwen Plus: 27.4 (#251)

BenchmarkGPT-3.5-turboQwen Plus
GPQA Diamond28%48.1%
LMArena Expert10701328
ARC (AI2) Challenge87.4%—
BoolQ87%—
MMLU71.4%—
OpenBookQA86%—
TriviaQA85.8%—

Multilingual Qwen Plus leads

GPT-3.5-turbo: 31.5 (#258), Qwen Plus: 45.1 (#175)

BenchmarkGPT-3.5-turboQwen Plus
LMArena Non-English11081310
LMArena Chinese10751347
LMArena Japanese10431251
LMArena Russian11231323
LMArena French1118—
LMArena German1090—
LMArena Korean1019—
LMArena Spanish1121—

Instruction Following Qwen Plus leads

GPT-3.5-turbo: 57.9 (#262), Qwen Plus: 68.8 (#181)

BenchmarkGPT-3.5-turboQwen Plus
LMArena Instruction Following11191303

Long Context Qwen Plus leads

GPT-3.5-turbo: 34.0 (#254), Qwen Plus: 40.3 (#158)

BenchmarkGPT-3.5-turboQwen Plus
LMArena Longer Query11211324

Writing & Preference Qwen Plus leads

GPT-3.5-turbo: 25.3 (#305), Qwen Plus: 52.2 (#176)

BenchmarkGPT-3.5-turboQwen Plus
LMArena Text11251326
LMArena Creative Writing10921293
LMArena Multi-Turn11171336
EQ-Bench Creative Writing451—

Frequently asked questions

Is GPT-3.5-turbo better than Qwen Plus?

Qwen Plus is the stronger model overall, scoring 37.1 to 23.2 on the Noometry Index.

Which is cheaper, GPT-3.5-turbo or Qwen Plus?

Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; GPT-3.5-turbo lists at $0.50 and $1.50.

Is GPT-3.5-turbo or Qwen Plus better for coding?

Qwen Plus scores higher on coding benchmarks: 38.9 versus 23.9 in the Noometry coding category.

Which has the bigger context window?

Qwen Plus does, with 1M tokens against 16K.

How many benchmarks do GPT-3.5-turbo and Qwen Plus share?

18 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and Qwen Plus has 20.

Related comparisons

Go deeper