Model comparison

GPT-4V vs GPT-5.4

GPT-5.4 has enough public results to be ranked (#14); GPT-4V does not yet, so treat this comparison as directional.

Last verified October 10, 2026. 0 shared benchmarks.

GPT-4V OpenAI

35.8

Unranked Sparse

GPT-5.4 OpenAI

59.5

Rank #14 Confirmed

Summary

The widest gap is in multimodal, where GPT-5.4 leads 43.8 to 32.5.

Side by side

GPT-4V and GPT-5.4 specifications
	GPT-4V	GPT-5.4
Provider	OpenAI	OpenAI
Noometry Index	35.8	59.5
Released	2023-11-06	2026-03-05
Weights	Proprietary	Proprietary
Context window	—	1.05M
Max output	—	128K
Input $ / M tokens	—	$2.50
Output $ / M tokens	—	$15
Results tracked	1	68

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

Category by category

Coding Not comparable

GPT-4V: —, GPT-5.4: 52.8 (#28)

Coding benchmarks
Benchmark	GPT-4V	GPT-5.4
SWE-bench Verified	—	76.9%
DeepSWE	—	51.8%
LMArena WebDev	—	1465
SciCode	—	56.6%
GSO	—	31.4%
WeirdML	—	77.7%
LMArena Coding	—	1497
MirrorCode	—	15.6%
ALE-Bench	—	1,607
AlgoTune	—	1.85

Agentic & Tool Use Not comparable

GPT-4V: —, GPT-5.4: 46.5 (#12)

Agentic & Tool Use benchmarks
Benchmark	GPT-4V	GPT-5.4
Terminal-Bench	—	81.8%
APEX-Agents	—	52.4%
τ²-bench Banking	—	39.4%
DeepResearch Bench	—	35.1%
PostTrainBench	—	19%
GBAEval	—	45.1%
LMArena Search	—	1197
METR Time Horizons	—	74.3%
Vending-Bench 2	—	6,144

Reasoning Not comparable

GPT-4V: —, GPT-5.4: 61.7 (#17)

Reasoning benchmarks
Benchmark	GPT-4V	GPT-5.4
ARC-AGI-2	—	74%
Kagi LLM Benchmark	—	63.8%
NYT Connections (extended)	—	91.3%
ARC-AGI-1	—	93.7%
CritPt	—	23.4%
Chess Puzzles	—	44%
EnigmaEval	—	16%
Thematic Generalization	—	80%
EBR-Bench	—	25.4%
LMArena Hard Prompts	—	1485
Mystery Game Puzzles	—	37%
DTBench	—	94.4%
LMCA	—	52%
Epoch Capabilities Index	—	156.92
ForecastBench	—	59.5

Math Not comparable

GPT-4V: —, GPT-5.4: 73.3 (#14)

Math benchmarks
Benchmark	GPT-4V	GPT-5.4
FrontierMath (Tiers 1-3)	—	78.6%
FrontierMath Tier 4	—	49%
MathArena Final-Answer Competitions	—	83.1%
OTIS Mock AIME 2024-2025	—	97.8%
ProofBench	—	56%
LMArena Math	—	1488
FrontierMath (Feb 2025 set)	—	47.6%
FrontierMath Tier 4 (v1)	—	27.1%

Knowledge Not comparable

GPT-4V: —, GPT-5.4: 65.3 (#13)

Knowledge benchmarks
Benchmark	GPT-4V	GPT-5.4
GPQA Diamond	—	93.3%
Humanity's Last Exam	—	36.2%
SimpleQA Verified	—	45.1%
Vectara Hallucination Rate	—	7%
LMArena Expert	—	1507

Multimodal GPT-5.4 leads

GPT-4V: 32.5, GPT-5.4: 43.8 (#19)

Multimodal benchmarks
Benchmark	GPT-4V	GPT-5.4
LMArena Vision	—	1302
Video-MME	59.9%	—
Blueprint-Bench 2	—	27.1%
Furniture Assembly	—	37.5%
LMArena Document	—	1471

Multilingual Not comparable

GPT-4V: —, GPT-5.4: 56.4 (#22)

Multilingual benchmarks
Benchmark	GPT-4V	GPT-5.4
LMArena Non-English	—	1465
LMArena Chinese	—	1520
LMArena French	—	1493
LMArena German	—	1472
LMArena Japanese	—	1484
LMArena Korean	—	1449
LMArena Russian	—	1480
LMArena Spanish	—	1453

Instruction Following Not comparable

GPT-4V: —, GPT-5.4: 77.3 (#25)

Instruction Following benchmarks
Benchmark	GPT-4V	GPT-5.4
LMArena Instruction Following	—	1469

Long Context Not comparable

GPT-4V: —, GPT-5.4: 50.3 (#8)

Long Context benchmarks
Benchmark	GPT-4V	GPT-5.4
CL-bench	—	27.9%
CL-bench Life	—	21.7%
LMArena Longer Query	—	1474

Writing & Preference Not comparable

GPT-4V: —, GPT-5.4: 72.1 (#18)

Writing & Preference benchmarks
Benchmark	GPT-4V	GPT-5.4
LMArena Text	—	1469
LMArena Creative Writing	—	1439
EQ-Bench Creative Writing	—	1840
EQ-Bench 4	—	1272
LMArena Multi-Turn	—	1482

Frequently asked questions

Is GPT-4V better than GPT-5.4?