Noometry

Model comparison

GPT-5.4 mini vs Qwen3-4B

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 31.9 on the Noometry Index.

Last verified . 4 shared benchmarks.

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Qwen3-4B Alibaba (Qwen)

31.9

Rank #264 Confirmed

Summary

  • They share 4 benchmarks with published results for both. GPT-5.4 mini scores higher in 4 categories and Qwen3-4B in 0 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 33.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for GPT-5.4 mini and 52.2% for Qwen3-4B.
  • Qwen3-4B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniQwen3-4B
ProviderOpenAIAlibaba (Qwen)
Noometry Index45.031.9
Released2026-03-172025-04-29
WeightsProprietaryOpen
Context window400K—
Max output128K—
Input $ / M tokens$0.75—
Output $ / M tokens$4.50—
Results tracked466

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

Category by category

Coding Not comparable

GPT-5.4 mini: 45.2 (#72), Qwen3-4B: —

BenchmarkGPT-5.4 miniQwen3-4B
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
LMArena Coding1438—
ALE-Bench1,189—

Agentic & Tool Use GPT-5.4 mini leads

GPT-5.4 mini: 29.9 (#81), Qwen3-4B: 27.6 (#100)

BenchmarkGPT-5.4 miniQwen3-4B
Berkeley Function Calling Leaderboard—35.7%
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), Qwen3-4B: 19.2 (#268)

BenchmarkGPT-5.4 miniQwen3-4B
Chess Puzzles24%4%
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
CritPt10%—
Thematic Generalization61.7%—
LMArena Hard Prompts1424—
Mystery Game Puzzles11%—
DTBench80%—
LMCA40.8%—
Epoch Capabilities Index148.84—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.5 (#75), Qwen3-4B: 29.7 (#240)

BenchmarkGPT-5.4 miniQwen3-4B
OTIS Mock AIME 2024-202588.9%52.2%
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
MathArena Final-Answer Competitions—38.5%
ProofBench21%—
LMArena Math1419—
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.5 (#67), Qwen3-4B: 33.0 (#208)

BenchmarkGPT-5.4 miniQwen3-4B
GPQA Diamond86.9%52.3%
Vectara Hallucination Rate5.5%5.7%
SimpleQA Verified29.4%—
LMArena Expert1435—

Multimodal Not comparable

GPT-5.4 mini: 39.7 (#56), Qwen3-4B: —

BenchmarkGPT-5.4 miniQwen3-4B
LMArena Vision1245—

Multilingual Not comparable

GPT-5.4 mini: 51.9 (#96), Qwen3-4B: —

BenchmarkGPT-5.4 miniQwen3-4B
LMArena Non-English1405—
LMArena Chinese1446—
LMArena French1440—
LMArena German1409—
LMArena Japanese1374—
LMArena Korean1368—
LMArena Russian1417—
LMArena Spanish1405—

Instruction Following Not comparable

GPT-5.4 mini: 74.1 (#102), Qwen3-4B: —

BenchmarkGPT-5.4 miniQwen3-4B
LMArena Instruction Following1405—

Long Context Not comparable

GPT-5.4 mini: 43.0 (#112), Qwen3-4B: —

BenchmarkGPT-5.4 miniQwen3-4B
LMArena Longer Query1407—

Writing & Preference Not comparable

GPT-5.4 mini: 64.0 (#58), Qwen3-4B: —

BenchmarkGPT-5.4 miniQwen3-4B
LMArena Text1412—
LMArena Creative Writing1370—
EQ-Bench Creative Writing1665—
LMArena Multi-Turn1429—

Frequently asked questions

Is GPT-5.4 mini better than Qwen3-4B?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 31.9 on the Noometry Index.

How many benchmarks do GPT-5.4 mini and Qwen3-4B share?

4 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen3-4B has 6.

Related comparisons

Go deeper