GPT-5.3-Codex

openai/gpt-5.3-codex-20260224

GPT-5.3-Codex, released by OpenAI on 2026-02-

tool use
structured outputs
reasoning

At a glance

provideropenai

releasedFeb 5, 2026

context400K

input / M$1.75

Specifications

What the API gives you

Context window: 400K tokens
Max output: 128K tokens
Input price: $1.75 / 1M tokens
Output price: $14 / 1M tokens
Cache read: $0.17 / 1M tokens
Modalities: text, image, file → text
Knowledge cutoff: —
Released: Feb 5, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1175 Elo2026-07-28
Design Arena Coding: 1175 Elo2026-07-27
Design Arena Coding: 1175 Elo2026-07-30
Design Arena Coding: 1175 Elo2026-07-29
Design Arena Coding: 1175 Elo2026-07-31
Design Arena Coding: 1174 Elo2026-08-02
Design Arena Coding: 1173 Elo2026-08-05
Design Arena Coding: 1174 Elo2026-08-01
Design Arena Coding: 1172 Elo2026-08-09
Design Arena Coding: 1174 Elo2026-08-03
Design Arena Coding: 1174 Elo2026-08-04
Design Arena Coding: 1169 Elo2026-08-14
Design Arena Coding: 1173 Elo2026-08-06
Design Arena Coding: 1172 Elo2026-08-10
Design Arena Coding: 1174 Elo2026-08-07
Design Arena Coding: 1164 Elo2026-08-18
Design Arena Coding: 1172 Elo2026-08-08
Design Arena Coding: 1165 Elo2026-08-15
Design Arena Coding: 1172 Elo2026-08-11
Design Arena Coding: 1171 Elo2026-08-12
Design Arena Coding: 1170 Elo2026-08-13
Design Arena Coding: 1163 Elo2026-08-19
Design Arena Coding: 1169 Elo2026-08-27
Design Arena Coding: 1163 Elo2026-08-20
Design Arena Coding: 1164 Elo2026-08-16
Design Arena Coding: 1161 Elo2026-09-05
Design Arena Coding: 1164 Elo2026-08-17
Design Arena Coding: 1169 Elo2026-08-21
Design Arena Coding: 1169 Elo2026-08-22
Design Arena Coding: 1169 Elo2026-08-23
Design Arena Coding: 1169 Elo2026-08-28
Design Arena Coding: 1169 Elo2026-08-24
Design Arena Coding: 1170 Elo2026-08-25
Design Arena Coding: 1170 Elo2026-08-26
Design Arena Coding: 1161 Elo2026-09-06
Design Arena Coding: 1169 Elo2026-08-29
Design Arena Coding: 1168 Elo2026-08-30
Design Arena Coding: 1168 Elo2026-08-31
Design Arena Coding: 1168 Elo2026-09-01
Design Arena Coding: 1167 Elo2026-09-02
Design Arena Coding: 1165 Elo2026-09-03
Design Arena Coding: 1164 Elo2026-09-04
Design Arena Full-stack Agent: 1030 Elo2026-07-28
Design Arena Full-stack Agent: 1031 Elo2026-07-27
Design Arena Full-stack Agent: 1022 Elo2026-07-30
Design Arena Full-stack Agent: 1024 Elo2026-07-29
Design Arena Full-stack Agent: 1023 Elo2026-07-31
Design Arena Full-stack Agent: 1026 Elo2026-08-02
Design Arena Full-stack Agent: 1024 Elo2026-08-01
Design Arena Full-stack Agent: 1025 Elo2026-08-05
Design Arena Full-stack Agent: 1016 Elo2026-08-09
Design Arena Full-stack Agent: 1026 Elo2026-08-03
Design Arena Full-stack Agent: 1026 Elo2026-08-04
Design Arena Full-stack Agent: 1016 Elo2026-08-14
Design Arena Full-stack Agent: 1025 Elo2026-08-06
Design Arena Full-stack Agent: 1014 Elo2026-08-10
Design Arena Full-stack Agent: 1025 Elo2026-08-07
Design Arena Full-stack Agent: 1014 Elo2026-08-18
Design Arena Full-stack Agent: 1025 Elo2026-08-08
Design Arena Full-stack Agent: 1017 Elo2026-08-11
Design Arena Full-stack Agent: 1019 Elo2026-08-15
Design Arena Full-stack Agent: 1018 Elo2026-08-12
Design Arena Full-stack Agent: 1016 Elo2026-08-13
Design Arena Full-stack Agent: 1014 Elo2026-08-19
Design Arena Full-stack Agent: 1007 Elo2026-08-27
Design Arena Full-stack Agent: 1014 Elo2026-08-20
Design Arena Full-stack Agent: 1020 Elo2026-08-16
Design Arena Full-stack Agent: 997 Elo2026-09-05
Design Arena Full-stack Agent: 1019 Elo2026-08-17
Design Arena Full-stack Agent: 1016 Elo2026-08-21
Design Arena Full-stack Agent: 1016 Elo2026-08-22
Design Arena Full-stack Agent: 1016 Elo2026-08-23
Design Arena Full-stack Agent: 1006 Elo2026-08-28
Design Arena Full-stack Agent: 1003 Elo2026-08-24
Design Arena Full-stack Agent: 1007 Elo2026-08-25
Design Arena Full-stack Agent: 1007 Elo2026-08-26
Design Arena Full-stack Agent: 994 Elo2026-09-06
Design Arena Full-stack Agent: 1006 Elo2026-08-29
Design Arena Full-stack Agent: 1007 Elo2026-08-30
Design Arena Full-stack Agent: 1006 Elo2026-08-31
Design Arena Full-stack Agent: 1007 Elo2026-09-01
Design Arena Full-stack Agent: 1007 Elo2026-09-02
Design Arena Full-stack Agent: 1007 Elo2026-09-03
Design Arena Full-stack Agent: 1007 Elo2026-09-04
Design Arena UI: 1173 Elo2026-07-28
Design Arena UI: 1174 Elo2026-07-27
Design Arena UI: 1174 Elo2026-07-30
Design Arena UI: 1174 Elo2026-07-29
Design Arena UI: 1173 Elo2026-07-31
Design Arena UI: 1174 Elo2026-08-02
Design Arena UI: 1174 Elo2026-08-01
Design Arena UI: 1173 Elo2026-08-05
Design Arena UI: 1170 Elo2026-08-09
Design Arena UI: 1174 Elo2026-08-03
Design Arena UI: 1174 Elo2026-08-04
Design Arena UI: 1168 Elo2026-08-14
Design Arena UI: 1173 Elo2026-08-06
Design Arena UI: 1172 Elo2026-08-07
Design Arena UI: 1171 Elo2026-08-10
Design Arena UI: 1171 Elo2026-08-08
Design Arena UI: 1171 Elo2026-08-18
Design Arena UI: 1171 Elo2026-08-11
Design Arena UI: 1172 Elo2026-08-15
Design Arena UI: 1171 Elo2026-08-12
Design Arena UI: 1171 Elo2026-08-13
Design Arena UI: 1171 Elo2026-08-19
Design Arena UI: 1172 Elo2026-08-16
Design Arena UI: 1171 Elo2026-08-20
Design Arena UI: 1163 Elo2026-08-27
Design Arena UI: 1171 Elo2026-08-17
Design Arena UI: 1160 Elo2026-09-05
Design Arena UI: 1164 Elo2026-08-21
Design Arena UI: 1164 Elo2026-08-22
Design Arena UI: 1164 Elo2026-08-23
Design Arena UI: 1164 Elo2026-08-24
Design Arena UI: 1163 Elo2026-08-28
Design Arena UI: 1165 Elo2026-08-25
Design Arena UI: 1165 Elo2026-08-26
Design Arena UI: 1160 Elo2026-09-06
Design Arena UI: 1164 Elo2026-08-29
Design Arena UI: 1164 Elo2026-08-30
Design Arena UI: 1164 Elo2026-08-31
Design Arena UI: 1163 Elo2026-09-01
Design Arena UI: 1163 Elo2026-09-02
Design Arena UI: 1161 Elo2026-09-03
Design Arena UI: 1159 Elo2026-09-04
Design Arena Web-app Agent: 1100 Elo2026-07-28
Design Arena Web-app Agent: 1100 Elo2026-07-27
Design Arena Web-app Agent: 1098 Elo2026-07-30
Design Arena Web-app Agent: 1098 Elo2026-07-29
Design Arena Web-app Agent: 1099 Elo2026-07-31
Design Arena Web-app Agent: 1099 Elo2026-08-02
Design Arena Web-app Agent: 1099 Elo2026-08-01
Design Arena Web-app Agent: 1082 Elo2026-08-05
Design Arena Web-app Agent: 1077 Elo2026-08-09
Design Arena Web-app Agent: 1099 Elo2026-08-03
Design Arena Web-app Agent: 1099 Elo2026-08-04
Design Arena Web-app Agent: 1072 Elo2026-08-14
Design Arena Web-app Agent: 1083 Elo2026-08-06
Design Arena Web-app Agent: 1074 Elo2026-08-10
Design Arena Web-app Agent: 1083 Elo2026-08-07
Design Arena Web-app Agent: 1083 Elo2026-08-08
Design Arena Web-app Agent: 1073 Elo2026-08-18
Design Arena Web-app Agent: 1074 Elo2026-08-11
Design Arena Web-app Agent: 1076 Elo2026-08-15
Design Arena Web-app Agent: 1075 Elo2026-08-12
Design Arena Web-app Agent: 1073 Elo2026-08-13
Design Arena Web-app Agent: 1073 Elo2026-08-19
Design Arena Web-app Agent: 1064 Elo2026-08-27
Design Arena Web-app Agent: 1073 Elo2026-08-20
Design Arena Web-app Agent: 1076 Elo2026-08-16
Design Arena Web-app Agent: 1076 Elo2026-08-17
Design Arena Web-app Agent: 1063 Elo2026-09-05
Design Arena Web-app Agent: 1069 Elo2026-08-21
Design Arena Web-app Agent: 1070 Elo2026-08-22
Design Arena Web-app Agent: 1070 Elo2026-08-23
Design Arena Web-app Agent: 1064 Elo2026-08-28
Design Arena Web-app Agent: 1064 Elo2026-08-24
Design Arena Web-app Agent: 1065 Elo2026-08-25
Design Arena Web-app Agent: 1065 Elo2026-08-26
Design Arena Web-app Agent: 1063 Elo2026-09-06
Design Arena Web-app Agent: 1064 Elo2026-08-29
Design Arena Web-app Agent: 1063 Elo2026-08-30
Design Arena Web-app Agent: 1063 Elo2026-08-31
Design Arena Web-app Agent: 1063 Elo2026-09-01
Design Arena Web-app Agent: 1062 Elo2026-09-02
Design Arena Web-app Agent: 1063 Elo2026-09-03
Design Arena Web-app Agent: 1063 Elo2026-09-04
Design Arena Website: 1187 Elo2026-07-28
Design Arena Website: 1187 Elo2026-07-30
Design Arena Website: 1187 Elo2026-07-27
Design Arena Website: 1187 Elo2026-07-29
Design Arena Website: 1187 Elo2026-07-31
Design Arena Website: 1186 Elo2026-08-02
Design Arena Website: 1186 Elo2026-08-01
Design Arena Website: 1186 Elo2026-08-05
Design Arena Website: 1186 Elo2026-08-03
Design Arena Website: 1185 Elo2026-08-09
Design Arena Website: 1186 Elo2026-08-04
Design Arena Website: 1182 Elo2026-08-14
Design Arena Website: 1186 Elo2026-08-06
Design Arena Website: 1186 Elo2026-08-07
Design Arena Website: 1185 Elo2026-08-10
Design Arena Website: 1185 Elo2026-08-08
Design Arena Website: 1175 Elo2026-08-18
Design Arena Website: 1185 Elo2026-08-11
Design Arena Website: 1174 Elo2026-08-15
Design Arena Website: 1184 Elo2026-08-12
Design Arena Website: 1183 Elo2026-08-13
Design Arena Website: 1174 Elo2026-08-19
Design Arena Website: 1174 Elo2026-08-16
Design Arena Website: 1174 Elo2026-08-20
Design Arena Website: 1182 Elo2026-08-27
Design Arena Website: 1174 Elo2026-08-17
Design Arena Website: 1178 Elo2026-09-05
Design Arena Website: 1182 Elo2026-08-21
Design Arena Website: 1183 Elo2026-08-22
Design Arena Website: 1183 Elo2026-08-23
Design Arena Website: 1183 Elo2026-08-24
Design Arena Website: 1183 Elo2026-08-28
Design Arena Website: 1183 Elo2026-08-25
Design Arena Website: 1183 Elo2026-08-26
Design Arena Website: 1176 Elo2026-09-06
Design Arena Website: 1182 Elo2026-08-29
Design Arena Website: 1182 Elo2026-08-30
Design Arena Website: 1182 Elo2026-08-31
Design Arena Website: 1182 Elo2026-09-01
Design Arena Website: 1181 Elo2026-09-02
Design Arena Website: 1179 Elo2026-09-03
Design Arena Website: 1178 Elo2026-09-04
LMArena WebDev: 1406 Elo2026-07-21
LMArena WebDev: 1369 Elo2026-07-27
LMArena WebDev: 1370 Elo2026-07-24
LMArena WebDev: 1370 Elo2026-07-28
LMArena WebDev: 1370 Elo2026-07-30
LMArena WebDev: 1369 Elo2026-08-01
LMArena WebDev: 1369 Elo2026-07-31
LMArena WebDev: 1369 Elo2026-08-06
LMArena WebDev: 1369 Elo2026-08-02
LMArena WebDev: 1369 Elo2026-08-12
LMArena WebDev: 1370 Elo2026-08-10
LMArena WebDev: 1369 Elo2026-08-14
LMArena WebDev: 1369 Elo2026-08-21
LMArena WebDev: 1369 Elo2026-09-01
LMArena WebDev: 1370 Elo2026-09-05
LMArena WebDev: 1369 Elo2026-08-30
SWE-rebench^‡: 58.6% ± 0.92026-03-01tools

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.