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
53
general
54
coding
94
reasoning
57
scienceest.
50
agents
85
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agents & Tools | 68 | 53.0 | LS |
| Code Ranking | 48 | 73.0 | AA |
| General Ranking | 42 | 80.0 | AA |
| Math Reasoning | 7 | 97.0 | AA |
| Science | 55 | 70.0 | AA |
Benchmark Scores (LLM Stats)
Agents
Terminal-Bench 2.0
52.8%SR
Code
SWE-Bench Verified
73.7%SR
SWE-Lancer
66.3%SR
AA Evaluation Indices
Math Index95.7
Intelligence Index43.1
Coding Index36.6
Aime 251.0
Mmlu Pro0.9
Gpqa0.9
Livecodebench0.8
Tau20.8
Ifbench0.7
Lcr0.7
Scicode0.4
Terminalbench Hard0.3
Hle0.2
LLM Stats Category Scores
Frontend Development70
Code60
Reasoning60
Tool Calling50
Agents50
Pricing
Input Price$1.25 / 1M tokens
Output Price$10 / 1M tokens
Blended Price (3:1)$3.438 / 1M tokens
Speed
Tokens/sec192.8 tokens/s
Time to First Token4.58s
Time to Answer4.58s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| OpenAI | 1.3M | 10.0M |