GPT-5.4

openai/gpt-5.4-20260305

OpenAI's GPT-5.4, released on 2026-03-05, accepts text, image, and file inputs and generates text output. It provides a context length of 1,050,000 tokens, supports tool usage and reasoning, and does not have open weights. Pricing is $2.5 per million input tokens and $15 per million output tokens.

tool use
structured outputs
reasoning

At a glance

provideropenai

releasedFeb 26, 2026

context1.1M

input / M$2.50

Specifications

What the API gives you

Context window: 1.1M tokens
Max output: 128K tokens
Input price: $2.50 / 1M tokens
Output price: $15 / 1M tokens
Cache read: $0.25 / 1M tokens
Modalities: text, image, file → text
Knowledge cutoff: —
Released: Feb 26, 2026

Measured evidence

Public benchmark record

Aider Polyglot: 44.9%2026-07-17
Aider Polyglot: 44.9%2026-07-21
Aider Polyglot: 44.9%2026-07-23
Aider Polyglot: 44.9%2026-08-02
Aider Polyglot: 44.9%2026-07-28
Aider Polyglot: 44.9%2026-07-27
Aider Polyglot: 44.9%2026-07-29
Aider Polyglot: 44.9%2026-07-30
Aider Polyglot: 44.9%2026-07-31
Aider Polyglot: 44.9%2026-08-01
Aider Polyglot: 44.9%2026-08-05
Aider Polyglot: 44.9%2026-08-03
Aider Polyglot: 44.9%2026-08-24
Aider Polyglot: 44.9%2026-08-09
Aider Polyglot: 44.9%2026-08-04
Aider Polyglot: 44.9%2026-08-06
Aider Polyglot: 44.9%2026-08-07
Aider Polyglot: 44.9%2026-08-14
Aider Polyglot: 44.9%2026-08-08
Aider Polyglot: 44.9%2026-08-10
Aider Polyglot: 44.9%2026-08-11
Aider Polyglot: 44.9%2026-08-18
Aider Polyglot: 44.9%2026-08-12
Aider Polyglot: 44.9%2026-08-19
Aider Polyglot: 44.9%2026-08-13
Aider Polyglot: 44.9%2026-08-15
Aider Polyglot: 44.9%2026-08-20
Aider Polyglot: 44.9%2026-08-16
Aider Polyglot: 44.9%2026-08-17
Aider Polyglot: 44.9%2026-08-21
Aider Polyglot: 44.9%2026-08-22
Aider Polyglot: 44.9%2026-08-27
Aider Polyglot: 44.9%2026-08-23
Aider Polyglot: 44.9%2026-08-25
Aider Polyglot: 44.9%2026-09-05
Aider Polyglot: 44.9%2026-08-26
Aider Polyglot: 44.9%2026-08-28
Aider Polyglot: 44.9%2026-09-06
Aider Polyglot: 44.9%2026-08-29
Aider Polyglot: 44.9%2026-08-30
Aider Polyglot: 44.9%2026-08-31
Aider Polyglot: 44.9%2026-09-01
Aider Polyglot: 44.9%2026-09-02
Aider Polyglot: 44.9%2026-09-03
Aider Polyglot: 44.9%2026-09-04
Design Arena Coding: 1208 Elo2026-07-28
Design Arena Coding: 1208 Elo2026-07-27
Design Arena Coding: 1208 Elo2026-07-30
Design Arena Coding: 1208 Elo2026-07-29
Design Arena Coding: 1208 Elo2026-07-31
Design Arena Coding: 1208 Elo2026-08-02
Design Arena Coding: 1207 Elo2026-08-05
Design Arena Coding: 1208 Elo2026-08-01
Design Arena Coding: 1206 Elo2026-08-09
Design Arena Coding: 1207 Elo2026-08-03
Design Arena Coding: 1207 Elo2026-08-04
Design Arena Coding: 1203 Elo2026-08-14
Design Arena Coding: 1207 Elo2026-08-06
Design Arena Coding: 1206 Elo2026-08-10
Design Arena Coding: 1207 Elo2026-08-07
Design Arena Coding: 1197 Elo2026-08-18
Design Arena Coding: 1206 Elo2026-08-08
Design Arena Coding: 1197 Elo2026-08-15
Design Arena Coding: 1206 Elo2026-08-11
Design Arena Coding: 1205 Elo2026-08-12
Design Arena Coding: 1203 Elo2026-08-13
Design Arena Coding: 1196 Elo2026-08-19
Design Arena Coding: 1202 Elo2026-08-27
Design Arena Coding: 1203 Elo2026-08-21
Design Arena Coding: 1196 Elo2026-08-20
Design Arena Coding: 1197 Elo2026-08-16
Design Arena Coding: 1195 Elo2026-09-05
Design Arena Coding: 1197 Elo2026-08-17
Design Arena Coding: 1203 Elo2026-08-22
Design Arena Coding: 1203 Elo2026-08-23
Design Arena Coding: 1202 Elo2026-08-28
Design Arena Coding: 1203 Elo2026-08-24
Design Arena Coding: 1203 Elo2026-08-25
Design Arena Coding: 1203 Elo2026-08-26
Design Arena Coding: 1194 Elo2026-09-06
Design Arena Coding: 1202 Elo2026-08-29
Design Arena Coding: 1202 Elo2026-08-30
Design Arena Coding: 1202 Elo2026-08-31
Design Arena Coding: 1202 Elo2026-09-01
Design Arena Coding: 1201 Elo2026-09-02
Design Arena Coding: 1199 Elo2026-09-03
Design Arena Coding: 1197 Elo2026-09-04
Design Arena Full-stack Agent: 1064 Elo2026-07-28
Design Arena Full-stack Agent: 1066 Elo2026-07-27
Design Arena Full-stack Agent: 1057 Elo2026-07-30
Design Arena Full-stack Agent: 1059 Elo2026-07-29
Design Arena Full-stack Agent: 1057 Elo2026-07-31
Design Arena Full-stack Agent: 1060 Elo2026-08-02
Design Arena Full-stack Agent: 1059 Elo2026-08-01
Design Arena Full-stack Agent: 1060 Elo2026-08-05
Design Arena Full-stack Agent: 1051 Elo2026-08-09
Design Arena Full-stack Agent: 1061 Elo2026-08-03
Design Arena Full-stack Agent: 1061 Elo2026-08-04
Design Arena Full-stack Agent: 1051 Elo2026-08-14
Design Arena Full-stack Agent: 1060 Elo2026-08-06
Design Arena Full-stack Agent: 1049 Elo2026-08-10
Design Arena Full-stack Agent: 1060 Elo2026-08-07
Design Arena Full-stack Agent: 1049 Elo2026-08-18
Design Arena Full-stack Agent: 1059 Elo2026-08-08
Design Arena Full-stack Agent: 1052 Elo2026-08-11
Design Arena Full-stack Agent: 1054 Elo2026-08-15
Design Arena Full-stack Agent: 1052 Elo2026-08-12
Design Arena Full-stack Agent: 1051 Elo2026-08-13
Design Arena Full-stack Agent: 1049 Elo2026-08-19
Design Arena Full-stack Agent: 1041 Elo2026-08-27
Design Arena Full-stack Agent: 1049 Elo2026-08-20
Design Arena Full-stack Agent: 1054 Elo2026-08-16
Design Arena Full-stack Agent: 1031 Elo2026-09-05
Design Arena Full-stack Agent: 1054 Elo2026-08-17
Design Arena Full-stack Agent: 1052 Elo2026-08-21
Design Arena Full-stack Agent: 1051 Elo2026-08-22
Design Arena Full-stack Agent: 1050 Elo2026-08-23
Design Arena Full-stack Agent: 1041 Elo2026-08-28
Design Arena Full-stack Agent: 1038 Elo2026-08-24
Design Arena Full-stack Agent: 1041 Elo2026-08-25
Design Arena Full-stack Agent: 1041 Elo2026-08-26
Design Arena Full-stack Agent: 1029 Elo2026-09-06
Design Arena Full-stack Agent: 1041 Elo2026-08-29
Design Arena Full-stack Agent: 1041 Elo2026-08-30
Design Arena Full-stack Agent: 1041 Elo2026-08-31
Design Arena Full-stack Agent: 1041 Elo2026-09-01
Design Arena Full-stack Agent: 1042 Elo2026-09-02
Design Arena Full-stack Agent: 1042 Elo2026-09-03
Design Arena Full-stack Agent: 1042 Elo2026-09-04
Design Arena UI: 1234 Elo2026-07-28
Design Arena UI: 1235 Elo2026-07-27
Design Arena UI: 1234 Elo2026-07-30
Design Arena UI: 1234 Elo2026-07-29
Design Arena UI: 1234 Elo2026-07-31
Design Arena UI: 1235 Elo2026-08-02
Design Arena UI: 1234 Elo2026-08-01
Design Arena UI: 1234 Elo2026-08-05
Design Arena UI: 1231 Elo2026-08-09
Design Arena UI: 1234 Elo2026-08-03
Design Arena UI: 1235 Elo2026-08-04
Design Arena UI: 1230 Elo2026-08-14
Design Arena UI: 1234 Elo2026-08-06
Design Arena UI: 1234 Elo2026-08-07
Design Arena UI: 1232 Elo2026-08-10
Design Arena UI: 1232 Elo2026-08-08
Design Arena UI: 1221 Elo2026-08-18
Design Arena UI: 1232 Elo2026-08-11
Design Arena UI: 1222 Elo2026-08-15
Design Arena UI: 1232 Elo2026-08-12
Design Arena UI: 1232 Elo2026-08-13
Design Arena UI: 1221 Elo2026-08-19
Design Arena UI: 1222 Elo2026-08-16
Design Arena UI: 1221 Elo2026-08-20
Design Arena UI: 1225 Elo2026-08-27
Design Arena UI: 1221 Elo2026-08-17
Design Arena UI: 1221 Elo2026-09-05
Design Arena UI: 1226 Elo2026-08-21
Design Arena UI: 1226 Elo2026-08-22
Design Arena UI: 1226 Elo2026-08-23
Design Arena UI: 1225 Elo2026-08-28
Design Arena UI: 1226 Elo2026-08-24
Design Arena UI: 1226 Elo2026-08-25
Design Arena UI: 1226 Elo2026-08-26
Design Arena UI: 1222 Elo2026-09-06
Design Arena UI: 1225 Elo2026-08-29
Design Arena UI: 1226 Elo2026-08-30
Design Arena UI: 1225 Elo2026-08-31
Design Arena UI: 1225 Elo2026-09-01
Design Arena UI: 1225 Elo2026-09-02
Design Arena UI: 1223 Elo2026-09-03
Design Arena UI: 1221 Elo2026-09-04
Design Arena Web-app Agent: 1120 Elo2026-07-28
Design Arena Web-app Agent: 1120 Elo2026-07-27
Design Arena Web-app Agent: 1117 Elo2026-07-30
Design Arena Web-app Agent: 1117 Elo2026-07-29
Design Arena Web-app Agent: 1117 Elo2026-07-31
Design Arena Web-app Agent: 1118 Elo2026-08-02
Design Arena Web-app Agent: 1118 Elo2026-08-01
Design Arena Web-app Agent: 1107 Elo2026-08-05
Design Arena Web-app Agent: 1102 Elo2026-08-09
Design Arena Web-app Agent: 1118 Elo2026-08-03
Design Arena Web-app Agent: 1118 Elo2026-08-04
Design Arena Web-app Agent: 1096 Elo2026-08-14
Design Arena Web-app Agent: 1107 Elo2026-08-06
Design Arena Web-app Agent: 1099 Elo2026-08-10
Design Arena Web-app Agent: 1107 Elo2026-08-07
Design Arena Web-app Agent: 1097 Elo2026-08-18
Design Arena Web-app Agent: 1107 Elo2026-08-08
Design Arena Web-app Agent: 1099 Elo2026-08-11
Design Arena Web-app Agent: 1098 Elo2026-08-15
Design Arena Web-app Agent: 1099 Elo2026-08-12
Design Arena Web-app Agent: 1099 Elo2026-08-13
Design Arena Web-app Agent: 1097 Elo2026-08-19
Design Arena Web-app Agent: 1091 Elo2026-08-27
Design Arena Web-app Agent: 1097 Elo2026-08-20
Design Arena Web-app Agent: 1100 Elo2026-08-16
Design Arena Web-app Agent: 1100 Elo2026-08-17
Design Arena Web-app Agent: 1089 Elo2026-09-05
Design Arena Web-app Agent: 1095 Elo2026-08-21
Design Arena Web-app Agent: 1096 Elo2026-08-22
Design Arena Web-app Agent: 1096 Elo2026-08-23
Design Arena Web-app Agent: 1090 Elo2026-08-28
Design Arena Web-app Agent: 1091 Elo2026-08-24
Design Arena Web-app Agent: 1092 Elo2026-08-25
Design Arena Web-app Agent: 1092 Elo2026-08-26
Design Arena Web-app Agent: 1089 Elo2026-09-06
Design Arena Web-app Agent: 1090 Elo2026-08-29
Design Arena Web-app Agent: 1090 Elo2026-08-30
Design Arena Web-app Agent: 1089 Elo2026-08-31
Design Arena Web-app Agent: 1089 Elo2026-09-01
Design Arena Web-app Agent: 1089 Elo2026-09-02
Design Arena Web-app Agent: 1089 Elo2026-09-03
Design Arena Web-app Agent: 1089 Elo2026-09-04
Design Arena Website: 1222 Elo2026-07-28
Design Arena Website: 1222 Elo2026-07-30
Design Arena Website: 1222 Elo2026-07-27
Design Arena Website: 1222 Elo2026-07-29
Design Arena Website: 1222 Elo2026-07-31
Design Arena Website: 1221 Elo2026-08-02
Design Arena Website: 1221 Elo2026-08-01
Design Arena Website: 1221 Elo2026-08-05
Design Arena Website: 1221 Elo2026-08-03
Design Arena Website: 1220 Elo2026-08-09
Design Arena Website: 1221 Elo2026-08-04
Design Arena Website: 1217 Elo2026-08-14
Design Arena Website: 1221 Elo2026-08-06
Design Arena Website: 1221 Elo2026-08-07
Design Arena Website: 1220 Elo2026-08-10
Design Arena Website: 1220 Elo2026-08-08
Design Arena Website: 1209 Elo2026-08-18
Design Arena Website: 1220 Elo2026-08-11
Design Arena Website: 1209 Elo2026-08-15
Design Arena Website: 1219 Elo2026-08-12
Design Arena Website: 1218 Elo2026-08-13
Design Arena Website: 1209 Elo2026-08-19
Design Arena Website: 1209 Elo2026-08-16
Design Arena Website: 1209 Elo2026-08-20
Design Arena Website: 1217 Elo2026-08-27
Design Arena Website: 1209 Elo2026-08-17
Design Arena Website: 1213 Elo2026-09-05
Design Arena Website: 1217 Elo2026-08-21
Design Arena Website: 1218 Elo2026-08-22
Design Arena Website: 1218 Elo2026-08-23
Design Arena Website: 1218 Elo2026-08-24
Design Arena Website: 1218 Elo2026-08-28
Design Arena Website: 1218 Elo2026-08-25
Design Arena Website: 1218 Elo2026-08-26
Design Arena Website: 1211 Elo2026-09-06
Design Arena Website: 1217 Elo2026-08-29
Design Arena Website: 1217 Elo2026-08-30
Design Arena Website: 1217 Elo2026-08-31
Design Arena Website: 1217 Elo2026-09-01
Design Arena Website: 1216 Elo2026-09-02
Design Arena Website: 1214 Elo2026-09-03
Design Arena Website: 1213 Elo2026-09-04
LiveBench Agentic Coding: 53.8%2026-06-25
LiveBench Coding: 77.5%2026-06-25
LiveBench Data Analysis: 79.3%2026-06-25
LiveBench Instruction Following: 70.2%2026-06-25
LiveBench Language: 82.6%2026-06-25
LiveBench Math: 94.2%2026-06-25
LiveBench Reasoning: 88.1%2026-06-25
LMArena Agent: 5.92026-07-13
LMArena Agent: 5.92026-07-20
LMArena Agent: 5.42026-07-27
LMArena Agent: 5.62026-07-21
LMArena Agent: 5.12026-07-28
LMArena Agent: 4.72026-08-03
LMArena Agent: 52026-08-12
LMArena Agent: 5.32026-08-06
LMArena Agent: 52026-08-11
LMArena Agent: 52026-08-13
LMArena Agent: 4.62026-08-24
LMArena Agent: 3.22026-08-31
LMArena Agent: 32026-09-05
LMArena Agent: 4.12026-08-27
LMArena Creative Writing: 1438 Elo2026-07-21
LMArena Creative Writing: 1439 Elo2026-07-27
LMArena Creative Writing: 1439 Elo2026-07-30
LMArena Creative Writing: 1439 Elo2026-08-02
LMArena Creative Writing: 1439 Elo2026-08-03
LMArena Creative Writing: 1439 Elo2026-08-06
LMArena Creative Writing: 1440 Elo2026-08-12
LMArena Creative Writing: 1440 Elo2026-08-21
LMArena Creative Writing: 1440 Elo2026-09-02
LMArena Creative Writing: 1440 Elo2026-08-27
LMArena Creative Writing: 1440 Elo2026-09-01
LMArena Instruction Following: 1471 Elo2026-07-21
LMArena Instruction Following: 1471 Elo2026-07-27
LMArena Instruction Following: 1471 Elo2026-07-30
LMArena Instruction Following: 1471 Elo2026-08-02
LMArena Instruction Following: 1471 Elo2026-08-03
LMArena Instruction Following: 1471 Elo2026-08-06
LMArena Instruction Following: 1471 Elo2026-08-12
LMArena Instruction Following: 1470 Elo2026-08-21
LMArena Instruction Following: 1470 Elo2026-09-02
LMArena Instruction Following: 1470 Elo2026-08-27
LMArena Instruction Following: 1470 Elo2026-09-01
LMArena Long Query: 1474 Elo2026-07-21
LMArena Long Query: 1474 Elo2026-07-27
LMArena Long Query: 1474 Elo2026-07-30
LMArena Long Query: 1474 Elo2026-08-02
LMArena Long Query: 1474 Elo2026-08-03
LMArena Long Query: 1475 Elo2026-08-06
LMArena Long Query: 1475 Elo2026-08-12
LMArena Long Query: 1475 Elo2026-08-21
LMArena Long Query: 1475 Elo2026-09-02
LMArena Long Query: 1475 Elo2026-08-27
LMArena Long Query: 1475 Elo2026-09-01
LMArena Math: 1490 Elo2026-07-21
LMArena Math: 1489 Elo2026-07-27
LMArena Math: 1489 Elo2026-07-30
LMArena Math: 1489 Elo2026-08-02
LMArena Math: 1489 Elo2026-08-03
LMArena Math: 1490 Elo2026-08-06
LMArena Math: 1490 Elo2026-08-12
LMArena Math: 1490 Elo2026-08-21
LMArena Math: 1490 Elo2026-08-27
LMArena Math: 1490 Elo2026-09-01
LMArena Text: 1470 Elo2026-07-16
LMArena Text: 1499 Elo2026-07-20
LMArena Text: 1478 Elo2026-07-21
LMArena Text: 1477 Elo2026-07-27
LMArena Text: 1477 Elo2026-07-30
LMArena Text: 1477 Elo2026-08-02
LMArena Text: 1477 Elo2026-08-06
LMArena Text: 1477 Elo2026-08-03
LMArena Text: 1477 Elo2026-08-10
LMArena Text: 1476 Elo2026-08-21
LMArena Text: 1477 Elo2026-08-12
LMArena Text: 1476 Elo2026-09-01
LMArena Text: 1477 Elo2026-09-02
LMArena Text: 1477 Elo2026-08-27
LMArena Vision: 1299 Elo2026-07-12
LMArena Vision: 1282 Elo2026-07-21
LMArena Vision: 1283 Elo2026-07-26
LMArena Vision: 1283 Elo2026-07-30
LMArena Vision: 1281 Elo2026-08-02
LMArena Vision: 1280 Elo2026-08-21
LMArena Vision: 1283 Elo2026-08-06
LMArena Vision: 1281 Elo2026-08-27
LMArena WebDev: 1386 Elo2026-07-16
LMArena WebDev: 1457 Elo2026-07-21
LMArena WebDev: 1385 Elo2026-07-20
LMArena WebDev: 1462 Elo2026-07-27
LMArena WebDev: 1462 Elo2026-07-24
LMArena WebDev: 1462 Elo2026-07-28
LMArena WebDev: 1462 Elo2026-07-30
LMArena WebDev: 1462 Elo2026-08-01
LMArena WebDev: 1462 Elo2026-07-31
LMArena WebDev: 1462 Elo2026-08-06
LMArena WebDev: 1462 Elo2026-08-02
LMArena WebDev: 1463 Elo2026-08-12
LMArena WebDev: 1463 Elo2026-08-10
LMArena WebDev: 1463 Elo2026-08-14
LMArena WebDev: 1463 Elo2026-09-01
LMArena WebDev: 1463 Elo2026-09-05
LMArena WebDev: 1463 Elo2026-08-21
LMArena WebDev: 1463 Elo2026-08-30
SWE-rebench^‡: 57.6% ± 0.82026-05-15tools

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 Code CompletionEstablished evidence
100% of intended weighted task evidence across 3 independent sources. 4 of 4 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 Local LLM for CodingEstablished evidence
100% of intended weighted task evidence across 4 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 Debugging & Code ReviewEstablished evidence
90% of intended weighted task evidence across 4 independent sources. 6 of 6 configured evaluation feeds currently have results.
Best LLM for CodingEstablished evidence
84% of intended weighted task evidence across 5 independent sources. 8 of 8 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 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 Agentic CodingEstablished evidence
64% of intended weighted task evidence across 4 independent sources. 8 of 8 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 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 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 Autonomous AgentsProvisional evidence
49% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Frontier-Bench or OSWorld Verified. 7 of 7 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 Hermes AgentProvisional evidence
45% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsProvisional evidence
45% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseProvisional evidence
45% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawProvisional evidence
45% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for AI AgentsProvisional evidence
42% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or OSWorld Verified. 7 of 7 configured evaluation feeds currently have results.
Best LLM for JSON & Schema OutputProvisional evidence
39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Structured Data ExtractionProvisional evidence
39% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Structured-output eval. 4 of 5 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 Tool & Function CallingProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Search. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Computer & Browser UseProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling 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.