GPT-5.4 Pro (2026-03-05)
Mar 2026
GPT-5.4 Pro (2026-03-05)Compare inon
GPT-5.4 Pro (2026-03-05) measured on 6 of 104 Chat & Knowledge benchmarks6
BenchmarkByScoreRank
Knowledge1
Reasoning1
Math3Leads on 1
Legacy · saturated or no longer reported1
No benchmark matches
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGemini 3.1 Pro Previewunstated+67%-93%$2 / $12Context: 1.05M → 1M+1
BetterDeepSeek V4 Pro 0813maxOpen+14%-97%$0.67Context: 1.05M → 1M+6CheaperGemini 4 Argonhigh+64%-94%*$1.99Context: 1.05M → 1M+3CheaperGPT-6 Astraunstated+64%-70%$10 / $50Monitoring can return HTTP 403+2CheaperGemini 3.8 Flashunstated+61%-98%*$0.75 / $3.75Context: 1.05M → 1M+2ModelScoreCostPer taskWhat changes
Gemini 3.1 Pro Previewunstated+67%-93%$2 / $12Context: 1.05M → 1M+1Gemini 4 Argonhigh+64%-94%*$1.99Context: 1.05M → 1M+3GPT-6 Astraunstated+64%-70%$10 / $50Monitoring can return HTTP 403+2Gemini 3.8 Flashunstated+61%-98%*$0.75 / $3.75Context: 1.05M → 1M+2GPT-6.1 Solmax+60%-94%$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen+14%-97%$0.67Context: 1.05M → 1M+6GPT-6.1 Solmax+60%-94%$0.72Remove unsupported parameters+5
Grok 4.5high+4%-96%$0.88Context: 1.05M → 500K
Muse Spark 1.2xhigh+30%-97%$0.97Context: 1.05M → 1M+2GPT-6 Solmax+31%-94%$1.04ModelScoreCostPer taskWhat changes
DeepSeek V4 Pro 0813maxOpen+14%-97%$0.67Context: 1.05M → 1M+6
Kimi K3maxOpen+9%-91%$2.00Context: 1.05M → 1M+4
GLM 5.3maxOpen-11%-97%$2.01Context: 1.05M → 1M+5
Qwen3 235B A22B Thinking 2507unstatedOpen-13%-99%$0.23 / $2.30Context: 1.05M → 262K+1TInklingxhighOpen-13%-97%$0.95 / $4.05Context: 1.05M → 256KModelScoreCostPer taskWhat changes
GPT-6 Astraunstated+64%—$10 / $50Monitoring can return HTTP 403+2GPT-6.1 Solmax+60%—$0.72Remove unsupported parameters+5GPT-5.6 Solmax+51%—$1.99GPT-6 Solunstated+39%—$2 / $10GPT-5.5xhigh+36%—$2.63Prompts with >272K input tokenso3unstated+13%—$2 / $8Context: 1.05M → 200KGPT-5 (2025-08-07)high+8%—$1.25 / $10Context: 1.05M → 400Ko3 (2025-04-16)high+7%—$2 / $8Context: 1.05M → 200KAll OpenAI models →Benchmarks
in Chat & KnowledgeGPQA Diamond · Epoch94.6#6
FrontierMath50#1
FrontierMath Tiers 1–3 (v2)82.5#14
FrontierMath Tier 4 (v2)58.5#16
SimpleQA Verified v146.3#34
Chess Puzzles59#6
FAQ
How much does GPT-5.4 Pro (2026-03-05) cost?›
$30 per 1M input tokens and $180 per 1M output tokens.
Is GPT-5.4 Pro (2026-03-05) free to use?›
There is no free API; the cheapest paid price is $30 per 1M input tokens.
How good is GPT-5.4 Pro (2026-03-05), and what is it best at?›
#34 of 83 in Chat & Knowledge.
Is GPT-5.4 Pro (2026-03-05) better than Claude Sonnet 5.5?›
On SimpleQA Verified v1, GPT-5.4 Pro (2026-03-05) scores 46.3 vs 46.5 — about the same.
How can I use GPT-5.4 Pro (2026-03-05)?›
Through the OpenAI API.
What is the context window of GPT-5.4 Pro (2026-03-05)?›
1.05M tokens.
When was GPT-5.4 Pro (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 Pro (2026-03-05) read images?›
It accepts text and images as input.
What is GPT-5.4 Pro (2026-03-05)?›
GPT-5.4 Pro (2026-03-05) is a language model from OpenAI, released Mar 2026.
What are the best alternatives to GPT-5.4 Pro (2026-03-05)?›
Gemini 3.1 Pro Preview (cheaper), DeepSeek V4 Pro 0813 (better).