GPT-5.2

openai/gpt-5.2-20251211

OpenAI's GPT-5.2 is a multimodal model that accepts file, image, and text inputs and produces text output. It supports tool usage and reasoning, offers a context window of 400 000 tokens, and is priced at $1.75 per million input tokens and $14 per million output tokens. The model was released on 2025‑12‑11 and does not have open weights.

tool use
structured outputs
reasoning

At a glance

provideropenai

releasedDec 8, 2025

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: file, image, text → text
Knowledge cutoff: —
Released: Dec 8, 2025

Measured evidence

Public benchmark record

BFCL: 55.9%2026-07-29
BFCL: 55.9%2026-07-31
BFCL: 55.9%2026-07-30
BFCL: 55.9%2026-08-02
BFCL: 55.9%2026-08-01
BFCL: 55.9%2026-08-05
BFCL: 55.9%2026-08-03
BFCL: 55.9%2026-08-09
BFCL: 55.9%2026-08-04
BFCL: 55.9%2026-08-06
BFCL: 55.9%2026-08-07
BFCL: 55.9%2026-08-14
BFCL: 55.9%2026-08-10
BFCL: 55.9%2026-08-08
BFCL: 55.9%2026-08-18
BFCL: 55.9%2026-08-11
BFCL: 55.9%2026-08-15
BFCL: 55.9%2026-08-12
BFCL: 55.9%2026-08-13
BFCL: 55.9%2026-08-19
BFCL: 55.9%2026-08-16
BFCL: 55.9%2026-08-20
BFCL: 55.9%2026-08-27
BFCL: 55.9%2026-08-17
BFCL: 55.9%2026-08-21
BFCL: 55.9%2026-08-22
BFCL: 55.9%2026-08-23
BFCL: 55.9%2026-08-24
BFCL: 55.9%2026-09-05
BFCL: 55.9%2026-08-28
BFCL: 55.9%2026-08-25
BFCL: 55.9%2026-08-26
BFCL: 55.9%2026-09-06
BFCL: 55.9%2026-08-29
BFCL: 55.9%2026-08-30
BFCL: 55.9%2026-08-31
BFCL: 55.9%2026-09-01
BFCL: 55.9%2026-09-02
BFCL: 55.9%2026-09-03
BFCL: 55.9%2026-09-04
Design Arena Coding: 1180 Elo2026-07-28
Design Arena Coding: 1180 Elo2026-07-27
Design Arena Coding: 1180 Elo2026-07-30
Design Arena Coding: 1180 Elo2026-07-29
Design Arena Coding: 1180 Elo2026-07-31
Design Arena Coding: 1179 Elo2026-08-02
Design Arena Coding: 1179 Elo2026-08-05
Design Arena Coding: 1179 Elo2026-08-01
Design Arena Coding: 1178 Elo2026-08-09
Design Arena Coding: 1179 Elo2026-08-03
Design Arena Coding: 1179 Elo2026-08-04
Design Arena Coding: 1175 Elo2026-08-14
Design Arena Coding: 1179 Elo2026-08-06
Design Arena Coding: 1178 Elo2026-08-10
Design Arena Coding: 1179 Elo2026-08-07
Design Arena Coding: 1169 Elo2026-08-18
Design Arena Coding: 1178 Elo2026-08-08
Design Arena Coding: 1170 Elo2026-08-15
Design Arena Coding: 1178 Elo2026-08-11
Design Arena Coding: 1177 Elo2026-08-12
Design Arena Coding: 1175 Elo2026-08-13
Design Arena Coding: 1168 Elo2026-08-19
Design Arena Coding: 1175 Elo2026-08-27
Design Arena Coding: 1168 Elo2026-08-20
Design Arena Coding: 1169 Elo2026-08-16
Design Arena Coding: 1167 Elo2026-09-05
Design Arena Coding: 1169 Elo2026-08-17
Design Arena Coding: 1175 Elo2026-08-21
Design Arena Coding: 1175 Elo2026-08-22
Design Arena Coding: 1175 Elo2026-08-23
Design Arena Coding: 1174 Elo2026-08-28
Design Arena Coding: 1175 Elo2026-08-24
Design Arena Coding: 1175 Elo2026-08-25
Design Arena Coding: 1175 Elo2026-08-26
Design Arena Coding: 1167 Elo2026-09-06
Design Arena Coding: 1174 Elo2026-08-29
Design Arena Coding: 1174 Elo2026-08-30
Design Arena Coding: 1174 Elo2026-08-31
Design Arena Coding: 1174 Elo2026-09-01
Design Arena Coding: 1173 Elo2026-09-02
Design Arena Coding: 1171 Elo2026-09-03
Design Arena Coding: 1170 Elo2026-09-04
Design Arena Full-stack Agent: 1089 Elo2026-07-28
Design Arena Full-stack Agent: 1091 Elo2026-07-27
Design Arena Full-stack Agent: 1082 Elo2026-07-30
Design Arena Full-stack Agent: 1082 Elo2026-07-29
Design Arena Full-stack Agent: 1082 Elo2026-07-31
Design Arena Full-stack Agent: 1086 Elo2026-08-02
Design Arena Full-stack Agent: 1084 Elo2026-08-01
Design Arena Full-stack Agent: 1085 Elo2026-08-05
Design Arena Full-stack Agent: 1076 Elo2026-08-09
Design Arena Full-stack Agent: 1086 Elo2026-08-03
Design Arena Full-stack Agent: 1085 Elo2026-08-04
Design Arena Full-stack Agent: 1076 Elo2026-08-14
Design Arena Full-stack Agent: 1084 Elo2026-08-06
Design Arena Full-stack Agent: 1074 Elo2026-08-10
Design Arena Full-stack Agent: 1084 Elo2026-08-07
Design Arena Full-stack Agent: 1074 Elo2026-08-18
Design Arena Full-stack Agent: 1084 Elo2026-08-08
Design Arena Full-stack Agent: 1077 Elo2026-08-11
Design Arena Full-stack Agent: 1079 Elo2026-08-15
Design Arena Full-stack Agent: 1078 Elo2026-08-12
Design Arena Full-stack Agent: 1076 Elo2026-08-13
Design Arena Full-stack Agent: 1074 Elo2026-08-19
Design Arena Full-stack Agent: 1067 Elo2026-08-27
Design Arena Full-stack Agent: 1074 Elo2026-08-20
Design Arena Full-stack Agent: 1079 Elo2026-08-16
Design Arena Full-stack Agent: 1057 Elo2026-09-05
Design Arena Full-stack Agent: 1079 Elo2026-08-17
Design Arena Full-stack Agent: 1076 Elo2026-08-21
Design Arena Full-stack Agent: 1076 Elo2026-08-22
Design Arena Full-stack Agent: 1076 Elo2026-08-23
Design Arena Full-stack Agent: 1067 Elo2026-08-28
Design Arena Full-stack Agent: 1063 Elo2026-08-24
Design Arena Full-stack Agent: 1067 Elo2026-08-25
Design Arena Full-stack Agent: 1067 Elo2026-08-26
Design Arena Full-stack Agent: 1054 Elo2026-09-06
Design Arena Full-stack Agent: 1067 Elo2026-08-29
Design Arena Full-stack Agent: 1066 Elo2026-08-30
Design Arena Full-stack Agent: 1066 Elo2026-08-31
Design Arena Full-stack Agent: 1067 Elo2026-09-01
Design Arena Full-stack Agent: 1067 Elo2026-09-02
Design Arena Full-stack Agent: 1067 Elo2026-09-03
Design Arena Full-stack Agent: 1067 Elo2026-09-04
Design Arena UI: 1194 Elo2026-07-28
Design Arena UI: 1195 Elo2026-07-27
Design Arena UI: 1195 Elo2026-07-30
Design Arena UI: 1195 Elo2026-07-29
Design Arena UI: 1194 Elo2026-07-31
Design Arena UI: 1195 Elo2026-08-02
Design Arena UI: 1195 Elo2026-08-01
Design Arena UI: 1194 Elo2026-08-05
Design Arena UI: 1191 Elo2026-08-09
Design Arena UI: 1195 Elo2026-08-03
Design Arena UI: 1195 Elo2026-08-04
Design Arena UI: 1190 Elo2026-08-14
Design Arena UI: 1194 Elo2026-08-06
Design Arena UI: 1194 Elo2026-08-07
Design Arena UI: 1192 Elo2026-08-10
Design Arena UI: 1192 Elo2026-08-08
Design Arena UI: 1189 Elo2026-08-18
Design Arena UI: 1192 Elo2026-08-11
Design Arena UI: 1190 Elo2026-08-15
Design Arena UI: 1192 Elo2026-08-12
Design Arena UI: 1192 Elo2026-08-13
Design Arena UI: 1189 Elo2026-08-19
Design Arena UI: 1190 Elo2026-08-16
Design Arena UI: 1189 Elo2026-08-20
Design Arena UI: 1185 Elo2026-08-27
Design Arena UI: 1189 Elo2026-08-17
Design Arena UI: 1181 Elo2026-09-05
Design Arena UI: 1185 Elo2026-08-21
Design Arena UI: 1186 Elo2026-08-22
Design Arena UI: 1186 Elo2026-08-23
Design Arena UI: 1186 Elo2026-08-24
Design Arena UI: 1185 Elo2026-08-28
Design Arena UI: 1186 Elo2026-08-25
Design Arena UI: 1186 Elo2026-08-26
Design Arena UI: 1182 Elo2026-09-06
Design Arena UI: 1185 Elo2026-08-29
Design Arena UI: 1185 Elo2026-08-30
Design Arena UI: 1185 Elo2026-08-31
Design Arena UI: 1185 Elo2026-09-01
Design Arena UI: 1184 Elo2026-09-02
Design Arena UI: 1182 Elo2026-09-03
Design Arena UI: 1181 Elo2026-09-04
Design Arena Web-app Agent: 1140 Elo2026-07-28
Design Arena Web-app Agent: 1140 Elo2026-07-27
Design Arena Web-app Agent: 1139 Elo2026-07-30
Design Arena Web-app Agent: 1139 Elo2026-07-29
Design Arena Web-app Agent: 1138 Elo2026-07-31
Design Arena Web-app Agent: 1138 Elo2026-08-02
Design Arena Web-app Agent: 1138 Elo2026-08-01
Design Arena Web-app Agent: 1134 Elo2026-08-05
Design Arena Web-app Agent: 1129 Elo2026-08-09
Design Arena Web-app Agent: 1138 Elo2026-08-03
Design Arena Web-app Agent: 1139 Elo2026-08-04
Design Arena Web-app Agent: 1123 Elo2026-08-14
Design Arena Web-app Agent: 1134 Elo2026-08-06
Design Arena Web-app Agent: 1126 Elo2026-08-10
Design Arena Web-app Agent: 1134 Elo2026-08-07
Design Arena Web-app Agent: 1113 Elo2026-08-18
Design Arena Web-app Agent: 1135 Elo2026-08-08
Design Arena Web-app Agent: 1126 Elo2026-08-11
Design Arena Web-app Agent: 1115 Elo2026-08-15
Design Arena Web-app Agent: 1126 Elo2026-08-12
Design Arena Web-app Agent: 1126 Elo2026-08-13
Design Arena Web-app Agent: 1113 Elo2026-08-19
Design Arena Web-app Agent: 1117 Elo2026-08-27
Design Arena Web-app Agent: 1113 Elo2026-08-20
Design Arena Web-app Agent: 1116 Elo2026-08-16
Design Arena Web-app Agent: 1117 Elo2026-08-17
Design Arena Web-app Agent: 1116 Elo2026-09-05
Design Arena Web-app Agent: 1122 Elo2026-08-21
Design Arena Web-app Agent: 1123 Elo2026-08-22
Design Arena Web-app Agent: 1123 Elo2026-08-23
Design Arena Web-app Agent: 1117 Elo2026-08-28
Design Arena Web-app Agent: 1118 Elo2026-08-24
Design Arena Web-app Agent: 1118 Elo2026-08-25
Design Arena Web-app Agent: 1118 Elo2026-08-26
Design Arena Web-app Agent: 1116 Elo2026-09-06
Design Arena Web-app Agent: 1117 Elo2026-08-29
Design Arena Web-app Agent: 1116 Elo2026-08-30
Design Arena Web-app Agent: 1116 Elo2026-08-31
Design Arena Web-app Agent: 1116 Elo2026-09-01
Design Arena Web-app Agent: 1116 Elo2026-09-02
Design Arena Web-app Agent: 1116 Elo2026-09-03
Design Arena Web-app Agent: 1116 Elo2026-09-04
Design Arena Website: 1178 Elo2026-07-28
Design Arena Website: 1178 Elo2026-07-30
Design Arena Website: 1178 Elo2026-07-27
Design Arena Website: 1178 Elo2026-07-29
Design Arena Website: 1178 Elo2026-07-31
Design Arena Website: 1177 Elo2026-08-02
Design Arena Website: 1177 Elo2026-08-01
Design Arena Website: 1177 Elo2026-08-05
Design Arena Website: 1177 Elo2026-08-03
Design Arena Website: 1176 Elo2026-08-09
Design Arena Website: 1178 Elo2026-08-04
Design Arena Website: 1174 Elo2026-08-14
Design Arena Website: 1177 Elo2026-08-06
Design Arena Website: 1177 Elo2026-08-07
Design Arena Website: 1176 Elo2026-08-10
Design Arena Website: 1176 Elo2026-08-08
Design Arena Website: 1166 Elo2026-08-18
Design Arena Website: 1176 Elo2026-08-11
Design Arena Website: 1166 Elo2026-08-15
Design Arena Website: 1175 Elo2026-08-12
Design Arena Website: 1174 Elo2026-08-13
Design Arena Website: 1166 Elo2026-08-19
Design Arena Website: 1166 Elo2026-08-16
Design Arena Website: 1166 Elo2026-08-20
Design Arena Website: 1174 Elo2026-08-27
Design Arena Website: 1166 Elo2026-08-17
Design Arena Website: 1170 Elo2026-09-05
Design Arena Website: 1174 Elo2026-08-21
Design Arena Website: 1175 Elo2026-08-22
Design Arena Website: 1175 Elo2026-08-23
Design Arena Website: 1175 Elo2026-08-24
Design Arena Website: 1174 Elo2026-08-28
Design Arena Website: 1175 Elo2026-08-25
Design Arena Website: 1175 Elo2026-08-26
Design Arena Website: 1168 Elo2026-09-06
Design Arena Website: 1174 Elo2026-08-29
Design Arena Website: 1174 Elo2026-08-30
Design Arena Website: 1174 Elo2026-08-31
Design Arena Website: 1174 Elo2026-09-01
Design Arena Website: 1173 Elo2026-09-02
Design Arena Website: 1171 Elo2026-09-03
Design Arena Website: 1170 Elo2026-09-04
LiveBench Agentic Coding: 50.3%2026-06-25
LiveBench Coding: 76.1%2026-06-25
LiveBench Data Analysis: 78.2%2026-06-25
LiveBench Instruction Following: 61.8%2026-06-25
LiveBench Language: 79.8%2026-06-25
LiveBench Math: 93.2%2026-06-25
LiveBench Reasoning: 83.2%2026-06-25
LMArena Creative Writing: 1377 Elo2026-07-21
LMArena Creative Writing: 1402 Elo2026-07-27
LMArena Creative Writing: 1402 Elo2026-07-30
LMArena Creative Writing: 1402 Elo2026-08-02
LMArena Creative Writing: 1402 Elo2026-08-03
LMArena Creative Writing: 1402 Elo2026-08-06
LMArena Creative Writing: 1402 Elo2026-08-12
LMArena Creative Writing: 1402 Elo2026-08-21
LMArena Creative Writing: 1402 Elo2026-09-02
LMArena Creative Writing: 1402 Elo2026-08-27
LMArena Creative Writing: 1402 Elo2026-09-01
LMArena Instruction Following: 1409 Elo2026-07-21
LMArena Instruction Following: 1417 Elo2026-07-27
LMArena Instruction Following: 1417 Elo2026-07-30
LMArena Instruction Following: 1417 Elo2026-08-02
LMArena Instruction Following: 1417 Elo2026-08-03
LMArena Instruction Following: 1417 Elo2026-08-06
LMArena Instruction Following: 1417 Elo2026-08-12
LMArena Instruction Following: 1417 Elo2026-08-21
LMArena Instruction Following: 1417 Elo2026-09-02
LMArena Instruction Following: 1417 Elo2026-08-27
LMArena Instruction Following: 1417 Elo2026-09-01
LMArena Long Query: 1412 Elo2026-07-21
LMArena Long Query: 1429 Elo2026-07-27
LMArena Long Query: 1429 Elo2026-07-30
LMArena Long Query: 1429 Elo2026-08-02
LMArena Long Query: 1429 Elo2026-08-03
LMArena Long Query: 1429 Elo2026-08-06
LMArena Long Query: 1429 Elo2026-08-12
LMArena Long Query: 1429 Elo2026-08-21
LMArena Long Query: 1429 Elo2026-09-02
LMArena Long Query: 1429 Elo2026-08-27
LMArena Long Query: 1429 Elo2026-09-01
LMArena Math: 1441 Elo2026-07-21
LMArena Math: 1441 Elo2026-07-27
LMArena Math: 1441 Elo2026-07-30
LMArena Math: 1441 Elo2026-08-02
LMArena Math: 1441 Elo2026-08-03
LMArena Math: 1441 Elo2026-08-06
LMArena Math: 1441 Elo2026-08-12
LMArena Math: 1441 Elo2026-08-21
LMArena Math: 1441 Elo2026-09-01
LMArena Math: 1441 Elo2026-08-27
LMArena Text: 1487 Elo2026-07-20
LMArena Text: 1437 Elo2026-07-21
LMArena Text: 1437 Elo2026-07-27
LMArena Text: 1437 Elo2026-08-02
LMArena Text: 1437 Elo2026-07-30
LMArena Text: 1437 Elo2026-08-10
LMArena Text: 1438 Elo2026-08-06
LMArena Text: 1437 Elo2026-08-03
LMArena Text: 1438 Elo2026-08-21
LMArena Text: 1437 Elo2026-08-12
LMArena Text: 1438 Elo2026-09-01
LMArena Text: 1438 Elo2026-09-02
LMArena Text: 1438 Elo2026-08-27
LMArena Vision: 1229 Elo2026-07-12
LMArena Vision: 1229 Elo2026-07-21
LMArena Vision: 1229 Elo2026-07-26
LMArena Vision: 1229 Elo2026-07-30
LMArena Vision: 1229 Elo2026-08-02
LMArena Vision: 1229 Elo2026-08-06
LMArena Vision: 1230 Elo2026-08-21
LMArena Vision: 1230 Elo2026-08-27
LMArena WebDev: 1406 Elo2026-07-16
LMArena WebDev: 1406 Elo2026-07-21
LMArena WebDev: 1406 Elo2026-07-20
LMArena WebDev: 1419 Elo2026-07-27
LMArena WebDev: 1419 Elo2026-07-24
LMArena WebDev: 1419 Elo2026-07-28
LMArena WebDev: 1419 Elo2026-07-30
LMArena WebDev: 1419 Elo2026-08-01
LMArena WebDev: 1419 Elo2026-07-31
LMArena WebDev: 1419 Elo2026-08-06
LMArena WebDev: 1419 Elo2026-08-02
LMArena WebDev: 1418 Elo2026-08-12
LMArena WebDev: 1417 Elo2026-08-10
LMArena WebDev: 1418 Elo2026-08-14
LMArena WebDev: 1418 Elo2026-08-21
LMArena WebDev: 1416 Elo2026-09-01
LMArena WebDev: 1416 Elo2026-09-05
LMArena WebDev: 1416 Elo2026-08-30
SWE-rebench^‡: 59.3% ± 0.52026-03-01tools
SWE-rebench^‡: 56.6% ± 0.32026-02-01tools

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 Competition MathEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Business WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Logic & Problem SolvingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Marketing CopyEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Chat & RoleplayEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Creative WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Frontend & UIEstablished evidence
100% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Roleplay & CharacterEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Math & ReasoningEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for a General AssistantEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Code CompletionEstablished evidence
81% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
Best LLM for CodingEstablished evidence
74% of intended weighted task evidence across 4 independent sources. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Debugging & Code ReviewEstablished evidence
70% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.
Best Open-Weight LLM for Self-HostingEstablished evidence
67% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Image UnderstandingEstablished evidence
65% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
Best Local LLM for CodingEstablished evidence
64% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Fast SummariesEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
Best Value LLMEstablished evidence
64% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Document SummarizationEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 4 of 6 configured evaluation feeds currently have results.
Best LLM for SummarizationEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 4 of 6 configured evaluation feeds currently have results.
Best LLM for Tool & Function CallingProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 of 5 configured evaluation feeds currently have results.
Best LLM for AI AgentsProvisional evidence
60% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 7 of 7 configured evaluation feeds currently have results.
Best LLM for JSON & Schema OutputProvisional evidence
56% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Structured Data ExtractionProvisional evidence
56% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Hermes AgentProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Literary TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Everyday TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
Best LLM for TranslationProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from WMT translation. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Agentic CodingProvisional evidence
55% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Frontier-Bench or LMArena Agent. 8 of 8 configured evaluation feeds currently have results.
Best Cheap LLM for High VolumeProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.
Cheapest Capable LLMProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Massive ContextProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 3 of 4 configured evaluation feeds currently have results.
Best LLM for OCR & DocumentsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Vision & DocumentsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Charts & DiagramsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Document ParsingProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Autonomous AgentsProvisional evidence
41% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Frontier-Bench or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.
Best LLM for RAG & Long ContextProvisional evidence
35% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Search. 4 of 6 configured evaluation feeds currently have results.
Best LLM for High-Volume ExtractionProvisional evidence
31% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Route reliability or Structured-output eval. 2 of 4 configured evaluation feeds currently have results.
Best LLM for Computer & Browser UseProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 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.

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.