GPT-5.4 Pro
OpenAICurrentReleased 2026-03-05
Overall Score
92#1 of 104Arena Elo
1484Categories Ranked
8of 8Price (1M tokens)
$30 in / $180 out
Speed
74tok/sContext
1.05MProprietaryReasoning
Confidence
proRanking Distribution
Category rank across 8 benchmark categories (lower is better)
Category Performance
Scores across all benchmark categories (0-100 scale)
Category Breakdown
Agentic
#188.9/ 100
Weight: 22%3 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-Verified
Coding
#188.3/ 100
Weight: 20%4 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-Rebench
Reasoning
#195.7/ 100
Weight: 17%4 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2
Knowledge
#284.9/ 100
Weight: 12%7 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA
Math
#198.5/ 100
Weight: 5%8 benchmarks
AIME 2025BRUMO 2025MATH-500
Multilingual
#195.7/ 100
Weight: 7%2 benchmarks
MGSMMMLU-ProX
Multimodal
#494.9/ 100
Weight: 12%2 benchmarks
MMMU-ProOfficeQA Pro
Inst. Following
#196.9/ 100
Weight: 5%1 benchmark
IFEval
Chatbot Arena Performance
Text Overall1484CI: ±7.47,160 votes
Coding1533CI: ±14.91,596 votes
Math1517CI: ±28.3428 votes
Instruction Following1488CI: ±13.51,988 votes
Creative Writing1461CI: ±19.41,004 votes
Multi-turn1502CI: ±16.11,361 votes
Hard Prompts1508CI: ±9.54,032 votes
Hard Prompts (English)1510CI: ±14.11,801 votes
Longer Query1492CI: ±13.22,044 votes
Benchmark Details
Compare This Model
See how GPT-5.4 Pro stacks up against similar models