GPT-5.4 Pro

GPT-5.4 Pro is a reasoning model from OpenAI in the GPT-5.4 family. 12 benchmarks count toward its score, in 4 categories.

availableShows if the model has enough results for an index.
IndexOverall score out of 100.76.5 ±8.7
CoverageShare of the index weight with results.60%
SpeedOutput tokens per second.1/s
Input / 1MUS dollars per 1M input tokens.$30 batch $15
Output / 1MUS dollars per 1M output tokens.$180 batch $90 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.1.05M
EloLMArena rating and rank.N/A

The index is a score out of 100. The ± range shows how much it can change. Batch work costs less.

CapabilitiesScore per category, out of 100.

Out of 100
AgenticMulti-step tasks with tools.
74.7
CodingCode writing and repair.
N/A
ReasoningLogic problems and puzzles.
85.9
MultimodalTasks with images and text.
N/A
KnowledgeFacts and expert knowledge.
67.2
MultilingualTasks in many languages.
N/A
InstructionTasks with strict rules in the prompt.
N/A
MathMath problems.
78.8

Results

12 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result as a score out of 100.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
GPQA diamondKnowledge94.6%65.6xhigh effortEpoch AI
ARC-AGI-1 (semi-private)Reasoning94.5%71.8xhigh effortARC Prize Foundation
International Physics Olympiad 2025 (Theory)Math93.5%Meta AI
BrowseCompAgentic89.3%74.7OpenAI
ARC-AGI-2 (semi-private)Reasoning83.3%81.8xhigh effortARC Prize Foundation
FrontierMath-Tiers-1-3-v2-PrivateMath82.5%77.9xhigh effortEpoch AI
Humanity's Last ExamKnowledge58.7%78.5Center for AI Safety et al.
Chess PuzzlesReasoning58.6%95.0xhigh effortEpoch AI
FrontierMath-Tier-4-v2-PrivateMath58.5%76.0xhigh effortEpoch AI
FrontierMath-2025-02-28-PrivateMath50.0%77.3xhigh effortEpoch AI
SimpleQA VerifiedKnowledge46.3%64.4xhigh effortEpoch AI
Humanity's Last Exam without toolsKnowledge42.7%65.0OpenAI
FrontierMath-Tier-4-2025-07-01-PrivateMath37.5%84.2Epoch AI
FrontierScienceKnowledge36.7%OpenAI
FrontierScience ResearchKnowledge36.7%Meta AI
Critical Physics TasksReasoning30.0%95.0Artificial Analysis

12 benchmarks count, from 13 of 16 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedEpoch AI, collected directlyCC BY — free to use and redistribute with attributionARC Prize Foundation, collected directlyNo licence stated. Their terms ask for written permission before commercial use

Same level, lower price

MiMo-V2.6-Pro73.5 · $0.87Muse Spark 1.375.0 · $4.25GPT-5.6 Sol76.7 · $10

More from OpenAI

GPT-6 Astra83.5GPT-5.6 Sol76.7GPT-5.6 Terra73.4GPT-6 Sol76.9GPT-5.572.3