Noometry

Model comparison

GPT-4 Turbo vs GPT-5.4 mini

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 30.5 on the Noometry Index.

Last verified . 27 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and GPT-5.4 mini in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5.4 mini leads 45.5 to 9.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 88.9% for GPT-5.4 mini.
  • GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • GPT-5.4 mini accepts more context: 400K tokens versus 128K.

Side by side

GPT-4 TurboGPT-5.4 mini
ProviderOpenAIOpenAI
Noometry Index30.545.0
Released2023-11-062026-03-17
WeightsProprietaryProprietary
Context window128K400K
Max output4K128K
Input $ / M tokens$10$0.75
Output $ / M tokens$30$4.50
Results tracked3646

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

Category by category

Coding GPT-5.4 mini leads

GPT-4 Turbo: 33.8 (#249), GPT-5.4 mini: 45.2 (#72)

BenchmarkGPT-4 TurboGPT-5.4 mini
WeirdML18%60.3%
LMArena Coding12681438
FrontierCode—27%
LMArena WebDev—1397
SciCode—49.9%
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
ALE-Bench—1,189
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, GPT-5.4 mini: 29.9 (#81)

BenchmarkGPT-4 TurboGPT-5.4 mini
DeepResearch Bench—36.3%
METR Time Horizons36.7%—

Reasoning GPT-5.4 mini leads

GPT-4 Turbo: 15.3 (#317), GPT-5.4 mini: 30.4 (#85)

BenchmarkGPT-4 TurboGPT-5.4 mini
Chess Puzzles6%24%
LMArena Hard Prompts12511424
DTBench61.6%80%
LMCA9.8%40.8%
Epoch Capabilities Index127.25148.84
ForecastBench59.457
ARC-AGI-2—18.9%
SimpleBench25.1%—
Kagi LLM Benchmark—37.9%
NYT Connections (extended)—61.8%
ARC-AGI-1—63.7%
CritPt—10%
Thematic Generalization—61.7%
Mystery Game Puzzles—11%

Math GPT-5.4 mini leads

GPT-4 Turbo: 9.0 (#322), GPT-5.4 mini: 45.5 (#75)

BenchmarkGPT-4 TurboGPT-5.4 mini
FrontierMath (Tiers 1-3)0.7%51.2%
OTIS Mock AIME 2024-20256.7%88.9%
LMArena Math12721419
FrontierMath Tier 4—9.8%
ProofBench—21%
MATH Level 546.7%—
FrontierMath (Feb 2025 set)—28.3%
FrontierMath Tier 4 (v1)—2.1%

Knowledge GPT-5.4 mini leads

GPT-4 Turbo: 24.3 (#268), GPT-5.4 mini: 51.5 (#67)

BenchmarkGPT-4 TurboGPT-5.4 mini
GPQA Diamond46.6%86.9%
LMArena Expert12231435
SimpleQA Verified—29.4%
Confabulations28.4%—
Vectara Hallucination Rate—5.5%
MMLU81.3%—

Multimodal GPT-5.4 mini leads

GPT-4 Turbo: 30.6 (#110), GPT-5.4 mini: 39.7 (#56)

BenchmarkGPT-4 TurboGPT-5.4 mini
LMArena Vision10901245

Multilingual GPT-5.4 mini leads

GPT-4 Turbo: 40.5 (#216), GPT-5.4 mini: 51.9 (#96)

BenchmarkGPT-4 TurboGPT-5.4 mini
LMArena Non-English12451405
LMArena Chinese12421446
LMArena French12761440
LMArena German12591409
LMArena Japanese11941374
LMArena Korean11871368
LMArena Russian12591417
LMArena Spanish12601405

Instruction Following GPT-5.4 mini leads

GPT-4 Turbo: 65.8 (#216), GPT-5.4 mini: 74.1 (#102)

BenchmarkGPT-4 TurboGPT-5.4 mini
LMArena Instruction Following12491405

Long Context GPT-5.4 mini leads

GPT-4 Turbo: 38.0 (#206), GPT-5.4 mini: 43.0 (#112)

BenchmarkGPT-4 TurboGPT-5.4 mini
LMArena Longer Query12541407

Writing & Preference GPT-5.4 mini leads

GPT-4 Turbo: 47.7 (#206), GPT-5.4 mini: 64.0 (#58)

BenchmarkGPT-4 TurboGPT-5.4 mini
LMArena Text12721412
LMArena Creative Writing12691370
LMArena Multi-Turn12671429
EQ-Bench Creative Writing—1665

Frequently asked questions

Is GPT-4 Turbo better than GPT-5.4 mini?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo or GPT-5.4 mini?

GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; GPT-4 Turbo lists at $10 and $30.

Is GPT-4 Turbo or GPT-5.4 mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 128K.

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

27 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and GPT-5.4 mini has 46.

Related comparisons

Go deeper