GPT-5.4 (2026-03-05)
Mar 2026
GPT-5.4 (2026-03-05)Compare inon
Benchmarks of GPT-5.4 (2026-03-05)19
BenchmarkByScoreRank
Knowledge2
Reasoning1
Math4
Coding1
Agents2
Legacy · saturated or no longer reported9
No benchmark matches
Rankingat xhigh effort?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGemini 3.1 Pro Previewunstated+72%-20%$2 / $12Context: 1.05M → 1M+1
BetterDeepSeek V4 Pro 0813maxOpen+17%-65%$0.67Context: 1.05M → 1M+6CheaperGemini 4 Argonhigh+69%-29%*$1.99Context: 1.05M → 1M+3CheaperGemini 3.8 Flashunstated+65%-73%*$0.75 / $3.75Context: 1.05M → 1M+2CheaperGPT-6.1 Solmax+64%-29%$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
Gemini 3.1 Pro Previewunstated+72%-20%$2 / $12Context: 1.05M → 1M+1Gemini 4 Argonhigh+69%-29%*$1.99Context: 1.05M → 1M+3Gemini 3.8 Flashunstated+65%-73%*$0.75 / $3.75Context: 1.05M → 1M+2GPT-6.1 Solmax+64%-29%$0.72Remove unsupported parameters+5Gemini 3 Flash Previewhigh+48%-80%$0.50 / $3Context: 1.05M → 1MModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen+17%-65%$0.67Context: 1.05M → 1M+6GPT-6.1 Solmax+64%-29%$0.72Remove unsupported parameters+5
Grok 4.5high+7%-47%$0.88Context: 1.05M → 500K
Muse Spark 1.2xhigh+34%-64%$0.97Context: 1.05M → 1M+2GPT-6 Solmax+35%-29%$1.04ModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen+17%-65%$0.67Context: 1.05M → 1M+6
Kimi K3maxOpen+12%+7%$2.00Context: 1.05M → 1M+4
GLM 5.3maxOpen-9%-62%$2.01Context: 1.05M → 1M+5
Qwen3 235B A22B Thinking 2507unstatedOpen-10%-87%$0.23 / $2.30Context: 1.05M → 262K+2TInklingxhighOpen-11%-69%$0.95 / $4.05Context: 1.05M → 256K+1ModelScoreCostPer taskWhat changes
GPT-6 Astraunstated+68%—$10 / $50Monitoring can return HTTP 403+2GPT-6.1 Solmax+64%—$0.72Remove unsupported parameters+5GPT-5.6 Solmax+55%—$1.99GPT-6 Solunstated+43%—$2 / $10GPT-5.5xhigh+40%—$2.63Prompts with >272K input tokenso3unstated+16%—$2 / $8Context: 1.05M → 200KGPT-5 (2025-08-07)high+11%—$1.25 / $10Context: 1.05M → 400Ko3 (2025-04-16)high+10%—$2 / $8Context: 1.05M → 200KAll OpenAI models →History
17 versionsBenchmarks
all categoriesChat & Knowledge
SimpleQA Verified v145.1#35
FrontierMath47.6#2
FrontierMath Tier 427.1#2
FrontierMath Tiers 1–3 (v2)78.6#19
Chess Puzzles48#15
Mystery Game Puzzles37#15
GPQA Diamond · Epoch93.3#15
OTIS Mock AIME 2024 202595.3#34
Agents & Tool Use
EBR Bench25.4#15
Furniture Assembly37.5#19
FAQ
How much does GPT-5.4 (2026-03-05) cost?›
$2.50 per 1M input tokens and $15 per 1M output tokens.
Is GPT-5.4 (2026-03-05) free to use?›
There is no free API; the cheapest paid price is $2.50 per 1M input tokens.
How good is GPT-5.4 (2026-03-05), and what is it best at?›
#35 of 83 in Chat & Knowledge, #5 of 24 in Coding, #19 of 31 in Agents & Tool Use.
Is GPT-5.4 (2026-03-05) better than GPT-5.4 Pro (2026-03-05)?›
On SimpleQA Verified v1, GPT-5.4 (2026-03-05) scores 45.1 vs 46.3 — lower.
How can I use GPT-5.4 (2026-03-05)?›
Through the OpenAI API.
What is the context window of GPT-5.4 (2026-03-05)?›
1.05M tokens.
When was GPT-5.4 (2026-03-05) released? Is there a newer version?›
Released 2026-03-05. It is the current version in its line.
Can GPT-5.4 (2026-03-05) read images?›
It accepts text and images as input.
What is GPT-5.4 (2026-03-05)?›
GPT-5.4 (2026-03-05) is a language model from OpenAI, released Mar 2026.
What are the best alternatives to GPT-5.4 (2026-03-05)?›
Gemini 3.1 Pro Preview (cheaper), DeepSeek V4 Pro 0813 (better).