GPT-5.1-Codex

openai/gpt-5.1-codex-20251113

OpenAI's GPT-5.1-Codex, released on 2025-01-01, accepts text and image inputs and generates text output. It supports tool use and reasoning, has a context length of 400 000 tokens, and its weights are not open. Pricing is $1.25 per million input tokens and $10 per million output tokens.

tool use
structured outputs
reasoning

At a glance

provideropenai

releasedJan 1, 2025

context400K

input / M$1.25

Specifications

What the API gives you

Context window: 400K tokens
Max output: 128K tokens
Input price: $1.25 / 1M tokens
Output price: $10 / 1M tokens
Cache read: $0.13 / 1M tokens
Modalities: text, image → text
Knowledge cutoff: —
Released: Jan 1, 2025

Measured evidence

Public benchmark record

Design Arena Coding: 1181 Elo2026-07-28
Design Arena Coding: 1181 Elo2026-07-27
Design Arena Coding: 1181 Elo2026-07-30
Design Arena Coding: 1181 Elo2026-07-29
Design Arena Coding: 1181 Elo2026-07-31
Design Arena Coding: 1180 Elo2026-08-02
Design Arena Coding: 1180 Elo2026-08-05
Design Arena Coding: 1180 Elo2026-08-01
Design Arena Coding: 1179 Elo2026-08-09
Design Arena Coding: 1180 Elo2026-08-03
Design Arena Coding: 1180 Elo2026-08-04
Design Arena Coding: 1176 Elo2026-08-14
Design Arena Coding: 1180 Elo2026-08-06
Design Arena Coding: 1179 Elo2026-08-10
Design Arena Coding: 1180 Elo2026-08-07
Design Arena Coding: 1171 Elo2026-08-18
Design Arena Coding: 1179 Elo2026-08-08
Design Arena Coding: 1172 Elo2026-08-15
Design Arena Coding: 1179 Elo2026-08-11
Design Arena Coding: 1178 Elo2026-08-12
Design Arena Coding: 1176 Elo2026-08-13
Design Arena Coding: 1170 Elo2026-08-19
Design Arena Coding: 1177 Elo2026-08-27
Design Arena Coding: 1170 Elo2026-08-20
Design Arena Coding: 1171 Elo2026-08-16
Design Arena Coding: 1169 Elo2026-09-05
Design Arena Coding: 1171 Elo2026-08-17
Design Arena Coding: 1177 Elo2026-08-21
Design Arena Coding: 1177 Elo2026-08-22
Design Arena Coding: 1177 Elo2026-08-23
Design Arena Coding: 1176 Elo2026-08-28
Design Arena Coding: 1177 Elo2026-08-24
Design Arena Coding: 1177 Elo2026-08-25
Design Arena Coding: 1177 Elo2026-08-26
Design Arena Coding: 1169 Elo2026-09-06
Design Arena Coding: 1176 Elo2026-08-29
Design Arena Coding: 1176 Elo2026-08-30
Design Arena Coding: 1176 Elo2026-08-31
Design Arena Coding: 1176 Elo2026-09-01
Design Arena Coding: 1175 Elo2026-09-02
Design Arena Coding: 1173 Elo2026-09-03
Design Arena Coding: 1172 Elo2026-09-04
Design Arena Full-stack Agent: 1086 Elo2026-07-28
Design Arena Full-stack Agent: 1086 Elo2026-07-27
Design Arena Full-stack Agent: 1086 Elo2026-07-30
Design Arena Full-stack Agent: 1086 Elo2026-07-29
Design Arena Full-stack Agent: 1086 Elo2026-07-31
Design Arena Full-stack Agent: 1086 Elo2026-08-02
Design Arena Full-stack Agent: 1086 Elo2026-08-01
Design Arena Full-stack Agent: 1086 Elo2026-08-05
Design Arena Full-stack Agent: 1086 Elo2026-08-09
Design Arena Full-stack Agent: 1086 Elo2026-08-03
Design Arena Full-stack Agent: 1086 Elo2026-08-04
Design Arena Full-stack Agent: 1086 Elo2026-08-14
Design Arena Full-stack Agent: 1086 Elo2026-08-06
Design Arena Full-stack Agent: 1086 Elo2026-08-10
Design Arena Full-stack Agent: 1086 Elo2026-08-07
Design Arena Full-stack Agent: 1086 Elo2026-08-18
Design Arena Full-stack Agent: 1086 Elo2026-08-08
Design Arena Full-stack Agent: 1086 Elo2026-08-11
Design Arena Full-stack Agent: 1086 Elo2026-08-15
Design Arena Full-stack Agent: 1086 Elo2026-08-12
Design Arena Full-stack Agent: 1086 Elo2026-08-13
Design Arena Full-stack Agent: 1086 Elo2026-08-19
Design Arena Full-stack Agent: 1086 Elo2026-08-27
Design Arena Full-stack Agent: 1086 Elo2026-08-20
Design Arena Full-stack Agent: 1086 Elo2026-08-16
Design Arena Full-stack Agent: 1086 Elo2026-09-05
Design Arena Full-stack Agent: 1086 Elo2026-08-17
Design Arena Full-stack Agent: 1086 Elo2026-08-21
Design Arena Full-stack Agent: 1086 Elo2026-08-22
Design Arena Full-stack Agent: 1086 Elo2026-08-23
Design Arena Full-stack Agent: 1086 Elo2026-08-28
Design Arena Full-stack Agent: 1086 Elo2026-08-24
Design Arena Full-stack Agent: 1086 Elo2026-08-25
Design Arena Full-stack Agent: 1086 Elo2026-08-26
Design Arena Full-stack Agent: 1086 Elo2026-09-06
Design Arena Full-stack Agent: 1086 Elo2026-08-29
Design Arena Full-stack Agent: 1086 Elo2026-08-30
Design Arena Full-stack Agent: 1086 Elo2026-08-31
Design Arena Full-stack Agent: 1086 Elo2026-09-01
Design Arena Full-stack Agent: 1086 Elo2026-09-02
Design Arena Full-stack Agent: 1086 Elo2026-09-03
Design Arena Full-stack Agent: 1086 Elo2026-09-04
Design Arena UI: 1264 Elo2026-08-18
Design Arena UI: 1265 Elo2026-08-15
Design Arena UI: 1264 Elo2026-08-19
Design Arena UI: 1265 Elo2026-08-16
Design Arena UI: 1264 Elo2026-08-20
Design Arena UI: 1263 Elo2026-08-27
Design Arena UI: 1264 Elo2026-08-17
Design Arena UI: 1260 Elo2026-09-05
Design Arena UI: 1264 Elo2026-08-21
Design Arena UI: 1264 Elo2026-08-22
Design Arena UI: 1264 Elo2026-08-23
Design Arena UI: 1263 Elo2026-08-28
Design Arena UI: 1264 Elo2026-08-24
Design Arena UI: 1264 Elo2026-08-25
Design Arena UI: 1265 Elo2026-08-26
Design Arena UI: 1260 Elo2026-09-06
Design Arena UI: 1264 Elo2026-08-29
Design Arena UI: 1264 Elo2026-08-30
Design Arena UI: 1264 Elo2026-08-31
Design Arena UI: 1263 Elo2026-09-01
Design Arena UI: 1263 Elo2026-09-02
Design Arena UI: 1261 Elo2026-09-03
Design Arena UI: 1259 Elo2026-09-04
Design Arena Web-app Agent: 1073 Elo2026-07-28
Design Arena Web-app Agent: 1073 Elo2026-07-27
Design Arena Web-app Agent: 1071 Elo2026-07-30
Design Arena Web-app Agent: 1071 Elo2026-07-29
Design Arena Web-app Agent: 1072 Elo2026-07-31
Design Arena Web-app Agent: 1073 Elo2026-08-02
Design Arena Web-app Agent: 1072 Elo2026-08-01
Design Arena Web-app Agent: 1067 Elo2026-08-05
Design Arena Web-app Agent: 1062 Elo2026-08-09
Design Arena Web-app Agent: 1072 Elo2026-08-03
Design Arena Web-app Agent: 1072 Elo2026-08-04
Design Arena Web-app Agent: 1056 Elo2026-08-14
Design Arena Web-app Agent: 1067 Elo2026-08-06
Design Arena Web-app Agent: 1059 Elo2026-08-10
Design Arena Web-app Agent: 1067 Elo2026-08-07
Design Arena Web-app Agent: 1068 Elo2026-08-08
Design Arena Web-app Agent: 1057 Elo2026-08-18
Design Arena Web-app Agent: 1058 Elo2026-08-11
Design Arena Web-app Agent: 1058 Elo2026-08-15
Design Arena Web-app Agent: 1059 Elo2026-08-12
Design Arena Web-app Agent: 1058 Elo2026-08-13
Design Arena Web-app Agent: 1057 Elo2026-08-19
Design Arena Web-app Agent: 1050 Elo2026-08-27
Design Arena Web-app Agent: 1057 Elo2026-08-20
Design Arena Web-app Agent: 1060 Elo2026-08-16
Design Arena Web-app Agent: 1060 Elo2026-08-17
Design Arena Web-app Agent: 1048 Elo2026-09-05
Design Arena Web-app Agent: 1055 Elo2026-08-21
Design Arena Web-app Agent: 1056 Elo2026-08-22
Design Arena Web-app Agent: 1056 Elo2026-08-23
Design Arena Web-app Agent: 1050 Elo2026-08-28
Design Arena Web-app Agent: 1050 Elo2026-08-24
Design Arena Web-app Agent: 1051 Elo2026-08-25
Design Arena Web-app Agent: 1051 Elo2026-08-26
Design Arena Web-app Agent: 1049 Elo2026-09-06
Design Arena Web-app Agent: 1050 Elo2026-08-29
Design Arena Web-app Agent: 1049 Elo2026-08-30
Design Arena Web-app Agent: 1049 Elo2026-08-31
Design Arena Web-app Agent: 1049 Elo2026-09-01
Design Arena Web-app Agent: 1048 Elo2026-09-02
Design Arena Web-app Agent: 1048 Elo2026-09-03
Design Arena Web-app Agent: 1048 Elo2026-09-04
Design Arena Website: 1186 Elo2026-07-28
Design Arena Website: 1186 Elo2026-07-30
Design Arena Website: 1186 Elo2026-07-27
Design Arena Website: 1186 Elo2026-07-29
Design Arena Website: 1185 Elo2026-07-31
Design Arena Website: 1185 Elo2026-08-02
Design Arena Website: 1185 Elo2026-08-01
Design Arena Website: 1184 Elo2026-08-05
Design Arena Website: 1185 Elo2026-08-03
Design Arena Website: 1183 Elo2026-08-09
Design Arena Website: 1184 Elo2026-08-04
Design Arena Website: 1180 Elo2026-08-14
Design Arena Website: 1184 Elo2026-08-06
Design Arena Website: 1184 Elo2026-08-07
Design Arena Website: 1183 Elo2026-08-10
Design Arena Website: 1183 Elo2026-08-08
Design Arena Website: 1173 Elo2026-08-18
Design Arena Website: 1183 Elo2026-08-11
Design Arena Website: 1173 Elo2026-08-15
Design Arena Website: 1182 Elo2026-08-12
Design Arena Website: 1181 Elo2026-08-13
Design Arena Website: 1173 Elo2026-08-19
Design Arena Website: 1173 Elo2026-08-16
Design Arena Website: 1173 Elo2026-08-20
Design Arena Website: 1181 Elo2026-08-27
Design Arena Website: 1173 Elo2026-08-17
Design Arena Website: 1177 Elo2026-09-05
Design Arena Website: 1181 Elo2026-08-21
Design Arena Website: 1182 Elo2026-08-22
Design Arena Website: 1182 Elo2026-08-23
Design Arena Website: 1182 Elo2026-08-24
Design Arena Website: 1182 Elo2026-08-28
Design Arena Website: 1182 Elo2026-08-25
Design Arena Website: 1182 Elo2026-08-26
Design Arena Website: 1175 Elo2026-09-06
Design Arena Website: 1181 Elo2026-08-29
Design Arena Website: 1181 Elo2026-08-30
Design Arena Website: 1181 Elo2026-08-31
Design Arena Website: 1181 Elo2026-09-01
Design Arena Website: 1180 Elo2026-09-02
Design Arena Website: 1178 Elo2026-09-03
Design Arena Website: 1177 Elo2026-09-04
LMArena WebDev: 1330 Elo2026-07-16
LMArena WebDev: 1330 Elo2026-07-21
LMArena WebDev: 1330 Elo2026-07-20
LMArena WebDev: 1336 Elo2026-07-27
LMArena WebDev: 1336 Elo2026-07-24
LMArena WebDev: 1336 Elo2026-07-28
SWE-rebench^‡: 48.8% ± 0.92026-02-01tools

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

Best LLM for Frontend & UIEstablished evidence
90% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for CodingProvisional evidence
58% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Debugging & Code ReviewProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 configured evaluation feeds currently have results.
Best LLM for Code CompletionProvisional evidence
44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.
Best LLM for Agentic CodingProvisional evidence
41% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 8 of 8 configured evaluation feeds currently have results.
Best Local LLM for CodingProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Autonomous AgentsProvisional evidence
29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
Best LLM for AI AgentsProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
Best LLM for Hermes AgentProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.
Best Cheap LLM for High VolumeProvisional evidence
17% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
Cheapest Capable LLMProvisional evidence
17% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Fast SummariesProvisional evidence
14% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
Best Value LLMProvisional evidence
14% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
Best LLM for High-Volume ExtractionProvisional evidence
13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.
Best LLM for Literary TranslationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Everyday TranslationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Best LLM for TranslationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Document SummarizationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
Best LLM for Tool & Function CallingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Business WritingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Creative Writing. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Logic & Problem SolvingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Marketing CopyProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Creative Writing. 5 of 5 configured evaluation feeds currently have results.
Best LLM for SummarizationProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
Best LLM for Chat & RoleplayProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Creative WritingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Computer & Browser UseProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 4 configured evaluation feeds currently have results.
Best LLM for OCR & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Image UnderstandingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Reasoning or LMArena Vision. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Vision & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
Best LLM for WritingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.
Best LLM for Roleplay & CharacterProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Charts & DiagramsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Document ParsingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
Best LLM for a General AssistantProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best Open-Weight LLM for Self-HostingProvisional evidence
8% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Massive ContextProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Long Query. 3 of 4 configured evaluation feeds currently have results.
Best LLM for RAG & Long ContextProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
Best LLM for JSON & Schema OutputProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Structured Data ExtractionProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Competition MathProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Math & ReasoningProvisional evidence
5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.