GPT-5.1 Codex (high)
OpenAIGPTProprietary
Description
GPT-5.1 Codex is a version of GPT-5.1 optimized for agentic coding tasks in Codex or similar environments. It features higher reasoning capabilities and is available in the Responses API. The underlying model snapshot is regularly updated.
Release Date
2025-11-13
Parameters
—
Context Length
400K
Modalities
image, text
Capability Radar
43
general
85
coding
94
reasoning
67
science
50
agents
85
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 146 | 75.0 | AA |
| General Ranking | 103 | 67.0 | AA |
| Science | 158 | 65.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Math
AIME 2025
96.7%SR
Reasoning
SWE-Bench Verified
73.7%SR
SWE-Lancer
66.3%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)
52.8%SR
AA Evaluation Indices
(Artificial Analysis)Math Index(Artificial Analysis)95.7
Aime 25(MAA (Mathematical Association of America))95.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))86.0
Gpqa(NYU + Cohere + Anthropic (2023))86.0
Livecodebench(UC Berkeley + MIT + Cornell (2024))84.9
Tau2(Sierra + U Toronto + Vector Institute (2025))83.0
Ifbench(Google Research (2023))70.0
Lcr(Artificial Analysis)69.3
Terminalbench Hard(Stanford × Laude Institute (2026))34.8
Hle(Center for AI Safety + Scale AI (2025))25.7
Intelligence Index(Artificial Analysis)23.7
LLM Stats Category Scores
(LLM Stats (zeroeval))Frontend Development70
Reasoning60
General60
Code60
Agents50
Tool Calling50
Pricing
Input Price$1.25 / 1M tokens
Output Price$10 / 1M tokens
Blended Price (3:1)$3.438 / 1M tokens
Cache Read Price$0.13 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
9 providers
Cheapest: PoeMost Expensive: Impossibl
ProviderInputOutput
1PoeCheapest
$1.1
$9
2OpenAIPRIMARY
$1.25
$10
3NanoGPT
$1.25
$10
4OpenRouter
$1.25
$10
5ZenMux
$1.25
$10
6Kilo Gateway
$1.25
$10
7Vercel AI Gateway
$1.25
$10
8OrcaRouter
$1.25
$10
9Impossibl
$1.25
$10
Compare pricing across different API providers for this model.