Noometry

Model comparison

GPT-5.4 mini vs Qwen3.5 122B-A10B

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 42.1 on the Noometry Index. Qwen3.5 122B-A10B costs 1.5× 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

Qwen3.5 122B-A10B Alibaba (Qwen)

42.1

Rank #119 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Qwen3.5 122B-A10B in 1 category; 5 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 38.8.
  • The biggest single-benchmark swing is SciCode: 49.9% for GPT-5.4 mini and 35.6% for Qwen3.5 122B-A10B.
  • Qwen3.5 122B-A10B is cheaper at $0.40 / $3.20 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 262K.
  • Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniQwen3.5 122B-A10B
ProviderOpenAIAlibaba (Qwen)
Noometry Index45.042.1
Released2026-03-172026-02-23
WeightsProprietaryOpen
Context window400K262K
Max output128K66K
Input $ / M tokens$0.75$0.40
Output $ / M tokens$4.50$3.20
Results tracked4627

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), Qwen3.5 122B-A10B: 39.1 (#162)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
LMArena WebDev13971360
SciCode49.9%35.6%
LMArena Coding14381436
FrontierCode27%—
WeirdML60.3%—
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.9 (#81), Qwen3.5 122B-A10B: —

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), Qwen3.5 122B-A10B: 27.2 (#123)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
NYT Connections (extended)61.8%51.7%
CritPt10%0.9%
Thematic Generalization61.7%51.2%
LMArena Hard Prompts14241421
Mystery Game Puzzles11%17%
DTBench80%84.3%
LMCA40.8%32.2%
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
ARC-AGI-163.7%—
Chess Puzzles24%—
Epoch Capabilities Index148.84—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.5 (#75), Qwen3.5 122B-A10B: 39.1 (#112)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
LMArena Math14191432
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
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), Qwen3.5 122B-A10B: 38.8 (#142)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
Vectara Hallucination Rate5.5%11.2%
LMArena Expert14351432
GPQA Diamond86.9%—
SimpleQA Verified29.4%—

Multimodal Too close to call

GPT-5.4 mini: 39.7 (#56), Qwen3.5 122B-A10B: 39.6 (#57)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
LMArena Vision12451245

Multilingual Too close to call

GPT-5.4 mini: 51.9 (#96), Qwen3.5 122B-A10B: 51.6 (#107)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
LMArena Non-English14051400
LMArena Chinese14461462
LMArena French14401442
LMArena German14091426
LMArena Japanese13741367
LMArena Korean13681352
LMArena Russian14171400
LMArena Spanish14051424

Instruction Following Too close to call

GPT-5.4 mini: 74.1 (#102), Qwen3.5 122B-A10B: 73.8 (#115)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
LMArena Instruction Following14051399

Long Context Too close to call

GPT-5.4 mini: 43.0 (#112), Qwen3.5 122B-A10B: 43.0 (#109)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
LMArena Longer Query14071410

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.0 (#58), Qwen3.5 122B-A10B: 60.0 (#105)

BenchmarkGPT-5.4 miniQwen3.5 122B-A10B
LMArena Text14121417
LMArena Creative Writing13701368
LMArena Multi-Turn14291416
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Qwen3.5 122B-A10B?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 42.1 on the Noometry Index. Qwen3.5 122B-A10B costs 1.5× 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 Qwen3.5 122B-A10B?

Qwen3.5 122B-A10B is cheaper. It lists at $0.40 per million input tokens and $3.20 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

Is GPT-5.4 mini or Qwen3.5 122B-A10B better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 262K.

How many benchmarks do GPT-5.4 mini and Qwen3.5 122B-A10B share?

27 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen3.5 122B-A10B has 27.

Related comparisons

Go deeper