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 high effort?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGLM 5.2maxOpen+2%-62%$1.47Context: 1.05M → 1M+1
BetterClaude Opus 4.7max+9%+78%$5 / $25Context: 1.05M → 1M
CheaperDeepSeek V4 Pro 0813maxOpensame-65%$1.32 / $3.96Context: 1.05M → 1M+6
CheaperQwen3.7 Maxmaxsame-61%$1.48 / $4.43Context: 1.05M → 1M+1
CheaperKimi K2.6unstatedOpensame-70%$0.95 / $4Context: 1.05M → 256KModelScoreCostPer taskWhat changes
GLM 5.2maxOpen+2%-62%$1.47Context: 1.05M → 1M+1DeepSeek V4 Pro 0813maxOpensame-65%$1.32 / $3.96Context: 1.05M → 1M+6Qwen3.7 Maxmaxsame-61%$1.48 / $4.43Context: 1.05M → 1M+1Kimi K2.6unstatedOpensame-70%$0.95 / $4Context: 1.05M → 256KQwen3.6 Max Previewunstatedsame-48%$1.30 / $7.80Context: 1.05M → 262K+2ModelScoreCostPer taskWhat changes
Claude Opus 4.7max+9%+78%$5 / $25Context: 1.05M → 1MModelScoreCostPer taskWhat changes
GLM 5.2maxOpen+2%-62%$1.47Context: 1.05M → 1M+1DeepSeek V4 Pro 0813maxOpensame-65%$1.32 / $3.96Context: 1.05M → 1M+6Kimi K2.6unstatedOpensame-70%$0.95 / $4Context: 1.05M → 256KGLM 5.1unstatedOpen-3%-62%$1.40 / $4.40Context: 1.05M → 203K+1Kimi K2.5unstatedOpen-4%-79%$0.60 / $3Context: 1.05M → 256KModelScoreCostPer taskWhat changes
GPT-5.3 Codexhigh-3%—$1.75 / $14Context: 1.05M → 400K+1GPT-5.2 (2025-12-11)high-4%—$1.75 / $14Context: 1.05M → 400KGPT-5 (2025-08-07)high-4%—$1.25 / $10Context: 1.05M → 400KGPT-5 Mini (2025-08-07)medium-16%—$0.25 / $2Context: 1.05M → 400Ko3 (2025-04-16)medium-19%—$2 / $8Context: 1.05M → 200KGPT-4.1 (2025-04-14)-37%—$2 / $8Context: 1.05M → 1MGPT-4ounstated-60%—$2.50 / $10Context: 1.05M → 128KGPT-6.1 Solmediumn/a—$0.21Remove unsupported parameters+5All OpenAI models →History
17 versionsBenchmarks
all categoriesChat & Knowledge
Chess Puzzles42#25
GPQA Diamond · Epoch89.9#33
OTIS Mock AIME 2024 202597.8#26
Coding
MirrorCode15.6#7
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 Qwen3.7 Max?›
On SWE-bench Verified · Epoch, GPT-5.4 (2026-03-05) scores 76.9 vs 77.3 — about the same.
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)?›
GLM 5.2 (cheaper), Claude Opus 4.7 (better).