Noometry

Model comparison

GPT-5.4 mini vs Qwen3-30B-A3B

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 7.8× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

Last verified . 27 shared benchmarks.

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Qwen3-30B-A3B Alibaba (Qwen)

38.9

Rank #179 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-5.4 mini scores higher in 9 categories and Qwen3-30B-A3B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in long context, where GPT-5.4 mini leads 43.0 to 31.0.
  • The biggest single-benchmark swing is WeirdML: 60.3% for GPT-5.4 mini and 29.8% for Qwen3-30B-A3B.
  • Qwen3-30B-A3B is cheaper at $0.12 / $0.50 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
  • GPT-5.4 mini accepts more context: 400K tokens versus 41K.
  • Qwen3-30B-A3B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniQwen3-30B-A3B
ProviderOpenAIAlibaba (Qwen)
Noometry Index45.038.9
Released2026-03-172025-04-28
WeightsProprietaryOpen
Context window400K41K
Max output128K16K
Input $ / M tokens$0.75$0.12
Output $ / M tokens$4.50$0.50
Results tracked4632

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

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.2 (#72), Qwen3-30B-A3B: 37.5 (#194)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
SciCode49.9%33.3%
WeirdML60.3%29.8%
LMArena Coding14381416
FrontierCode27%—
LMArena WebDev1397—
ALE-Bench1,189—

Agentic & Tool Use Too close to call

GPT-5.4 mini: 29.9 (#81), Qwen3-30B-A3B: 29.8 (#82)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
Berkeley Function Calling Leaderboard—41.4%
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), Qwen3-30B-A3B: 22.2 (#204)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
Kagi LLM Benchmark37.9%54.9%
CritPt10%0.3%
Chess Puzzles24%8%
LMArena Hard Prompts14241398
DTBench80%69.3%
LMCA40.8%22.4%
Epoch Capabilities Index148.84139.63
ARC-AGI-218.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
Thematic Generalization61.7%—
Mystery Game Puzzles11%—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.5 (#75), Qwen3-30B-A3B: 37.4 (#157)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
OTIS Mock AIME 2024-202588.9%70.3%
LMArena Math14191394
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
MathArena Final-Answer Competitions—47.8%
ProofBench21%—
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), Qwen3-30B-A3B: 41.8 (#105)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
GPQA Diamond86.9%70.1%
LMArena Expert14351396
SimpleQA Verified29.4%—
Confabulations—12.3%
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

GPT-5.4 mini: 39.7 (#56), Qwen3-30B-A3B: —

BenchmarkGPT-5.4 miniQwen3-30B-A3B
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 51.9 (#96), Qwen3-30B-A3B: 49.5 (#132)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
LMArena Non-English14051372
LMArena Chinese14461433
LMArena French14401418
LMArena German14091380
LMArena Japanese13741337
LMArena Korean13681331
LMArena Russian14171370
LMArena Spanish14051404

Instruction Following GPT-5.4 mini leads

GPT-5.4 mini: 74.1 (#102), Qwen3-30B-A3B: 72.0 (#142)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
LMArena Instruction Following14051363

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 43.0 (#112), Qwen3-30B-A3B: 31.0 (#283)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
LMArena Longer Query14071379
Fiction.LiveBench—40.6%

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.0 (#58), Qwen3-30B-A3B: 55.6 (#143)

BenchmarkGPT-5.4 miniQwen3-30B-A3B
LMArena Text14121384
LMArena Creative Writing13701317
LMArena Multi-Turn14291378
Short-Story Creative Writing—75.3%
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Qwen3-30B-A3B?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 38.9 on the Noometry Index. Qwen3-30B-A3B costs 7.8× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

Which is cheaper, GPT-5.4 mini or Qwen3-30B-A3B?

Qwen3-30B-A3B is cheaper. It lists at $0.12 per million input tokens and $0.50 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

Is GPT-5.4 mini or Qwen3-30B-A3B better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 37.5 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 41K.

How many benchmarks do GPT-5.4 mini and Qwen3-30B-A3B share?

27 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen3-30B-A3B has 32.

Related comparisons

Go deeper