Skip to main content

GPT-5.4

OpenAISupersededReleased Mar 5, 2026
Overall Score
89Prov. #9 of 119Verified #16 of 28
Arena Elo
1469
Categories Ranked
8of 8
Price (1M tokens)
$2.5 in / $15 out
Speed
74tok/s
Context
1.05M
ProprietaryReasoning
Confidence
base

According to BenchLM.ai, GPT-5.4 ranks #9 out of 119 models on the provisional leaderboard with an overall score of 89/100. It also ranks #16 out of 28 on the verified leaderboard. This places it in the upper tier of AI models, with competitive scores across most benchmark categories.

GPT-5.4 is a proprietary model with a 1.05M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

GPT-5.4 sits inside the GPT-5.4 family alongside GPT-5.4 Pro, GPT-5.4 mini, GPT-5.4 nano. This profile currently has 47 of 225 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Knowledge (#2), while its weakest is Multimodal & Grounded (#50). This performance profile makes it particularly effective for knowledge-intensive tasks like research, analysis, and factual Q&A.

Ranking Distribution

Category rank across 8 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#9
87.4/ 100
Weight: 22%14 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-VerifiedGAIATAU-benchWebArena

Coding

#8
87.8/ 100
Weight: 20%7 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchSciCode

Reasoning

#3
95.6/ 100
Weight: 17%2 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

#2
99.0/ 100
Weight: 12%12 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

#7
94.4/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500FrontierMath

Multilingual

#4
100.0/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#50
60.0/ 100
Weight: 12%11 benchmarks
MMMU-ProOfficeQA ProCharXivCharXiv w/o tools

Inst. Following

#3
96.0/ 100
Weight: 5%1 benchmark
IFEvalIFBench

Chatbot Arena Performance

Text Overall1469CI: ±4.629,672 votes
Coding1513CI: ±7.57,884 votes
Math1455CI: ±14.21,763 votes
Instruction Following1465CI: ±6.99,588 votes
Creative Writing1441CI: ±9.54,580 votes
Multi-turn1483CI: ±8.75,551 votes
Hard Prompts1492CI: ±5.618,711 votes
Hard Prompts (English)1494CI: ±7.09,328 votes
Longer Query1483CI: ±6.811,342 votes

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Frequently Asked Questions

How does GPT-5.4 perform overall in AI benchmarks?

GPT-5.4 currently ranks #9 out of 119 models on BenchLM's provisional leaderboard with an overall score of 89. It also ranks #16 out of 28 on the verified leaderboard. It is created by OpenAI and features a 1.05M context window.

Is GPT-5.4 good for knowledge and understanding?

GPT-5.4 ranks #2 out of 119 models in knowledge and understanding benchmarks with an average score of 99. It is among the top performers in this category.

Is GPT-5.4 good for coding and programming?

GPT-5.4 ranks #8 out of 119 models in coding and programming benchmarks with an average score of 87.8. It is among the top performers in this category.

Is GPT-5.4 good for reasoning and logic?

GPT-5.4 ranks #3 out of 119 models in reasoning and logic benchmarks with an average score of 95.6. It is among the top performers in this category.

Is GPT-5.4 good for agentic tool use and computer tasks?

GPT-5.4 ranks #9 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 87.4. It is among the top performers in this category.

Is GPT-5.4 good for multimodal and grounded tasks?

GPT-5.4 ranks #50 out of 119 models in multimodal and grounded tasks benchmarks with an average score of 60. There are stronger options in this category.

Is GPT-5.4 good for instruction following?

GPT-5.4 ranks #3 out of 119 models in instruction following benchmarks with an average score of 96. It is among the top performers in this category.

Which sibling models are related to GPT-5.4?

GPT-5.4 belongs to the GPT-5.4 family. Related variants on BenchLM include GPT-5.4 Pro, GPT-5.4 mini, GPT-5.4 nano.

Does GPT-5.4 have full benchmark coverage on BenchLM?

Not yet. GPT-5.4 currently has 47 published benchmark scores out of the 225 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of GPT-5.4?

GPT-5.4 has a context window of 1.05M, which determines how much text it can process in a single interaction.

Last updated: June 2, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Don't miss the next GPT moment

Which models moved up, what’s new, and what it costs. One email a week, 3-min read.

Free. One email per week.