GPT-5.1
Nov 2025
GPT-5.1Compare inon
Benchmarks of GPT-5.166
BenchmarkByScoreRank
Overall1
Knowledge5
Reasoning4
Math16
Science2
Coding4
Agents4
Multimodal3Leads on 1
Writing17
Health & law3
Documents2
Legacy · saturated or no longer reported5
No benchmark matches
Rankingat high effort?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProthinkingOpen+73%-84%$0.13Pass back reasoning_content+3BetterGPT-6 Lunahigh+16%-94%$0.029Function calling only with none · Chat Completions+3
CheaperMuse Spark 1.3max+71%-42%$3.69Only auto tool_choice is supported+5
CheaperMiniMax M3.1 Flashthinking+68%-92%$0.22No strict JSON+1
CheaperGemini 3.8 Flashhigh+68%-56%*$3.49Sampling parameters are ignored+1ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen+73%-84%$0.13Pass back reasoning_content+3Muse Spark 1.3max+71%-42%$3.69Only auto tool_choice is supported+5MiniMax M3.1 Flashthinking+68%-92%$0.22No strict JSON+1Gemini 3.8 Flashhigh+68%-56%*$3.49Sampling parameters are ignored+1
Step 5 PreviewthinkingOpen+63%-59%$1.03web_search not available · Chat Completions+2ModelScoreCostPer taskWhat changes
GPT-6 Lunahigh+16%-94%$0.029Function calling only with none · Chat Completions+3GPT-5.6 Lunahigh+17%-87%$0.044
Claude Haiku 5.5medium+19%-94%$0.047Remove sampling parameters+5GPT-6.1 Terralow+26%-42%$0.055MiMo v2.6 FlashthinkingOpen+23%-95%$0.062Pass back reasoning_content+3ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen+73%-84%$0.13Pass back reasoning_content+3
Kimi K3maxOpen+65%+75%$2.00Sampling parameters are fixed+3Step 5 PreviewthinkingOpen+63%-59%$1.03web_search not available · Chat Completions+2Muse Spark OpenxhighOpen+54%-42%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1
DeepSeek V4.1 Flash 1017maxOpen+52%-85%$0.26Pass back reasoning_content · Chat Completions+4ModelScoreCostPer taskWhat changes
GPT-6 Astrahigh+86%—$1.73Monitoring can return HTTP 403+2GPT-6.1 Solhigh+80%—$0.32Remove unsupported parameters+5GPT-5.6 Solhigh+61%—$0.81GPT-5.5high+58%—$1.40Prompts with >272K input tokensGPT-6 Solhigh+55%—$0.37GPT-6.1 Terrahigh+52%—$0.13GPT-5.3 Codexxhigh+49%—$1.75 / $14DeprecatedGPT-5.6 Terrahigh+35%—$0.34Prompts with >272K input tokensAll OpenAI models →History
17 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam28.5#90
Arena Text · overall1,456#43
Arena Text · Chinese1,495#41
Arena Text · English1,450.9#48
Arena Text · French1,450.2#61
Arena Text · German1,438.2#49
Arena Text · instruction following1,442.6#41
Arena Text · Japanese1,453.5#19
Arena Text · Korean1,400.3#44
Arena Text · non-English1,431.3#45
Arena Text · Polish1,439.6#39
Arena Text · Russian1,435.4#50
Arena Text · Spanish1,433.4#65
AA Omniscience Index5.4#50
CritPt (physics)4.9#81
AA Intelligence Index 4.3.2≈24.7#89
AA Omniscience · Accuracy37.7#55
ARC-AGI-1 · semi-private72.8#42
ARC-AGI-2 · semi-private17.6#45
MathArena · Apex1#25
MathArena · Apex Shortlist55.9#21
MathArena · BRUMO 202593.3#7
MathArena · CMIMC 202594.4#3
MMLU-Pro · official boardlab86.4
Arena Text · overall · October 22, 20261,442.8#47
Arena Text · overall · October 15, 20261,442.7#45
GPQA Diamond87.3#55
MathArena · AIME 202594.2#7
Coding
Terminal-Bench 2.152.4#66
Agents & Tool Use
GDPval-AA (work tasks) 2.116.3#139
MCP-Atlas · full 100050.1#14
MCP-Atlas Public53.6#14
τ³-Banking · AA15.9#66
τ²-bench · AA81.9#74
Writing & Language
Arena Text · creative writing1,429#46
IFBench (instructions)72.9#34
Vision & Documents
MMMU-Pro (vision)75.5#44
Arena Vision · overall1,249.5#45
FAQ
How much does GPT-5.1 cost?›
$1.25 per 1M input tokens and $10 per 1M output tokens; cached input $0.13 per 1M.
Is GPT-5.1 free to use?›
There is no free API; the cheapest paid price is $1.25 per 1M input tokens.
How good is GPT-5.1, and what is it best at?›
#90 of 336 in Chat & Knowledge, #72 of 97 in Coding, #139 of 177 in Agents & Tool Use, #42 of 197 in Writing & Language, #44 of 125 in Vision & Documents. Strongest at: Science, Long context, Knowledge, Instructions.
Is GPT-5.1 better than GPT-5?›
On Humanity's Last Exam, GPT-5.1 scores 28.5 vs 28.5 — about the same.
How can I use GPT-5.1?›
Through the API of Azure, OpenAI.
What is the context window of GPT-5.1?›
400K tokens, with up to 128K output tokens.
When was GPT-5.1 released? Is there a newer version?›
Released 2025-11-13. It has been superseded by GPT-6 Sol.
Is GPT-5.1 open source?›
No, GPT-5.1 is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can GPT-5.1 read images?›
It accepts text and images, PDF files as input.
What is GPT-5.1?›
GPT-5.1 is a closed language model from OpenAI, released Nov 2025.
What are the best alternatives to GPT-5.1?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).