GPT-5.1 (2025-11-13)
Nov 2025
GPT-5.1 (2025-11-13)Compare inon
GPT-5.1 (2025-11-13) measured on 8 of 109 Chat & Knowledge benchmarks8
BenchmarkByScoreRank
Knowledge3
Reasoning1
Math2
Legacy · saturated or no longer reported2
No benchmark matches
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperDeepSeek V4.1 Flash 1017maxOpen×3.3-85%$0.26Pass back reasoning_content · Chat Completions+4BetterGPT-5.6 Lunalow+13%-87%$0.01
CheaperGemini 3.8 Flashhigh×3.1-56%*$3.49Sampling parameters are ignored+1CheaperDeepSeek V4 Pro 0813maxOpen×2.9-42%$0.67No image input+5
CheaperGrok 4.6xhigh×2.3-13%$1.75ModelScoreCostPer taskWhat changes
DeepSeek V4.1 Flash 1017maxOpen×3.3-85%$0.26Pass back reasoning_content · Chat Completions+4Gemini 3.8 Flashhigh×3.1-56%*$3.49Sampling parameters are ignored+1DeepSeek V4 Pro 0813maxOpen×2.9-42%$0.67No image input+5Grok 4.6xhigh×2.3-13%$1.75
GLM 5.3maxOpen×2.2-37%$2.01No image input+4ModelScoreCostPer taskWhat changes
GPT-5.6 Lunalow+13%-87%$0.01GPT-5.6 Terralow+27%+31%$0.14Prompts with >272K input tokens
Claude Haiku 5.5max×2-94%$0.21Remove sampling parameters+5GPT-5.6 Sollow+73%+133%$0.26DeepSeek V4.1 Flash 1017maxOpen×3.3-85%$0.26Pass back reasoning_content · Chat Completions+4ModelScoreCostPer taskWhat changes
DeepSeek V4.1 Flash 1017maxOpen×3.3-85%$0.26Pass back reasoning_content · Chat Completions+4DeepSeek V4 Pro 0813maxOpen×2.9-42%$0.67No image input+5GLM 5.3maxOpen×2.2-37%$2.01No image input+4
Kimi K3maxOpen+73%+75%$2.00Sampling parameters are fixed+3
Qwen3.6 35B A3BnoneOpen+47%-84%$0.25 / $1.49Context: 400K → 262KModelScoreCostPer taskWhat changes
GPT-6 Astramax×5.6—$3.26Monitoring can return HTTP 403+2GPT-6.1 Solmax×5.3—$0.72Remove unsupported parameters+5GPT-6 Solmax×3.7—$1.04GPT-5.6 Solnone×2.2—$4 / $20o3 (2025-04-16)medium+53%—$2 / $8Context: 400K → 200KGPT-5.6 Lunanone+33%—$0.20 / $1.20GPT-5.5none+20%—$5 / $30Prompts with >272K input tokensGPT-5.4 (2026-03-05)none+7%—$2.50 / $15All OpenAI models →History
17 versionsBenchmarks
in Chat & KnowledgeGPQA Diamond · Epoch66.7#86
OTIS Mock AIME 2024 202537.8#98
FrontierMath2.1#35
Chess Puzzles4#66
Mystery Game Puzzles15#50
FAQ
How much does GPT-5.1 (2025-11-13) cost?›
$1.25 per 1M input tokens and $10 per 1M output tokens.
Is GPT-5.1 (2025-11-13) 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 (2025-11-13), and what is it best at?›
#30 of 84 in Chat & Knowledge.
Is GPT-5.1 (2025-11-13) better than Qwen3.6 Max Preview?›
On Mystery Game Puzzles, GPT-5.1 (2025-11-13) scores 19 vs 19 — about the same.
How can I use GPT-5.1 (2025-11-13)?›
Through the OpenAI API.
What is the context window of GPT-5.1 (2025-11-13)?›
400K tokens.
When was GPT-5.1 (2025-11-13) released? Is there a newer version?›
Released 2025-11-13. It has been superseded by GPT-6 Sol.
Can GPT-5.1 (2025-11-13) read images?›
It accepts text and images as input.
What is GPT-5.1 (2025-11-13)?›
GPT-5.1 (2025-11-13) is a language model from OpenAI, released Nov 2025.
What are the best alternatives to GPT-5.1 (2025-11-13)?›
DeepSeek V4.1 Flash 1017 (cheaper), GPT-5.6 Luna (better).