Noometry

Model comparison

GPT-4.5 vs Qwen3 14B

GPT-4.5 is the stronger model overall, scoring 37.2 to 35.5 on the Noometry Index.

Last verified . 4 shared benchmarks.

GPT-4.5 OpenAI

37.2

Rank #208 Confirmed

Qwen3 14B Alibaba (Qwen)

35.5

Rank #225 Confirmed

Summary

  • They share 4 benchmarks with published results for both. GPT-4.5 scores higher in 2 categories and Qwen3 14B in 4 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Qwen3 14B leads 39.3 to 32.5.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 66.4% for Qwen3 14B.
  • Qwen3 14B has downloadable open weights; the other is API-only.

Side by side

GPT-4.5Qwen3 14B
ProviderOpenAIAlibaba (Qwen)
Noometry Index37.235.5
Released2025-02-272025-04
WeightsProprietaryOpen
Context window—131K
Max output—8K
Input $ / M tokens—$0.35
Output $ / M tokens—$1.40
Results tracked4212

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

Category by category

Coding GPT-4.5 leads

GPT-4.5: 42.2 (#109), Qwen3 14B: 37.3 (#195)

BenchmarkGPT-4.5Qwen3 14B
Aider Polyglot44.9%—
SciCode—31.6%
WeirdML39.4%—
LiveBench Coding75.2%—
LMArena Coding1396—

Agentic & Tool Use Qwen3 14B leads

GPT-4.5: 27.9 (#97), Qwen3 14B: 29.6 (#83)

BenchmarkGPT-4.5Qwen3 14B
Berkeley Function Calling Leaderboard—41%
Cybench17.5%—

Reasoning Qwen3 14B leads

GPT-4.5: 13.9 (#330), Qwen3 14B: 18.5 (#280)

BenchmarkGPT-4.5Qwen3 14B
Epoch Capabilities Index136.74138.23
ARC-AGI-20.8%—
SimpleBench34.5%—
Kagi LLM Benchmark—49.1%
ARC-AGI-110.3%—
CritPt—0%
Chess Puzzles—4%
EnigmaEval3.2%—
LiveBench Reasoning71.1%—
LMArena Hard Prompts1403—
DTBench—64%
LiveBench Data Analysis64.3%—
LMCA—18.2%
ForecastBench61.7—
LiveBench69%—

Math Qwen3 14B leads

GPT-4.5: 32.6 (#211), Qwen3 14B: 38.6 (#133)

BenchmarkGPT-4.5Qwen3 14B
OTIS Mock AIME 2024-202537.8%66.4%
LiveBench Math69.3%—
LMArena Math1412—
MATH Level 578.6%—

Knowledge Qwen3 14B leads

GPT-4.5: 32.5 (#211), Qwen3 14B: 39.3 (#134)

BenchmarkGPT-4.5Qwen3 14B
GPQA Diamond68.7%63.8%
Humanity's Last Exam5.4%—
Confabulations13.6%—
Vectara Hallucination Rate—5.4%
LMArena Expert1394—

Multimodal Not comparable

GPT-4.5: 37.6 (#71), Qwen3 14B: —

BenchmarkGPT-4.5Qwen3 14B
LMArena Vision1195—
VPCT45%—

Multilingual Not comparable

GPT-4.5: 52.5 (#83), Qwen3 14B: —

BenchmarkGPT-4.5Qwen3 14B
LMArena Non-English1413—
LMArena Chinese1421—
LMArena French1418—
LMArena German1457—
LMArena Japanese1416—
LMArena Korean1392—
LMArena Russian1419—

Instruction Following Not comparable

GPT-4.5: 72.6 (#134), Qwen3 14B: —

BenchmarkGPT-4.5Qwen3 14B
LiveBench Instruction Following72.3%—
LMArena Instruction Following1404—

Long Context GPT-4.5 leads

GPT-4.5: 40.4 (#155), Qwen3 14B: 38.1 (#204)

BenchmarkGPT-4.5Qwen3 14B
Fiction.LiveBench63.9%62.5%
LMArena Longer Query1406—

Writing & Preference Not comparable

GPT-4.5: 56.9 (#134), Qwen3 14B: —

BenchmarkGPT-4.5Qwen3 14B
LMArena Text1417—
LMArena Creative Writing1394—
Short-Story Creative Writing75.6%—
EQ-Bench Creative Writing1258—
LMArena Multi-Turn1444—
LiveBench Language61.5%—

Frequently asked questions

Is GPT-4.5 better than Qwen3 14B?

GPT-4.5 is the stronger model overall, scoring 37.2 to 35.5 on the Noometry Index.

Is GPT-4.5 or Qwen3 14B better for coding?

GPT-4.5 scores higher on coding benchmarks: 42.2 versus 37.3 in the Noometry coding category.

How many benchmarks do GPT-4.5 and Qwen3 14B share?

4 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen3 14B has 12.

Related comparisons

Go deeper