GPT-5.5

openai/gpt-5.5-20260423

OpenAI's GPT-5.5, released on 2026-04-23, processes file, image, and text inputs and outputs text. It supports tools and reasoning, has a context length of 1,050,000 tokens, and is not provided with open weights. Pricing is $5 per million input tokens and $30 per million output tokens.

tool use
structured outputs
reasoning

At a glance

provideropenai

releasedMar 5, 2026

context1.1M

input / M$5

Specifications

What the API gives you

Context window: 1.1M tokens
Max output: 128K tokens
Input price: $5 / 1M tokens
Output price: $30 / 1M tokens
Cache read: $0.50 / 1M tokens
Modalities: file, image, text → text
Knowledge cutoff: Dec 1, 2025
Released: Mar 5, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1285 Elo2026-07-28
Design Arena Coding: 1285 Elo2026-07-27
Design Arena Coding: 1285 Elo2026-07-30
Design Arena Coding: 1285 Elo2026-07-29
Design Arena Coding: 1285 Elo2026-07-31
Design Arena Coding: 1284 Elo2026-08-02
Design Arena Coding: 1286 Elo2026-08-05
Design Arena Coding: 1284 Elo2026-08-01
Design Arena Coding: 1285 Elo2026-08-09
Design Arena Coding: 1284 Elo2026-08-03
Design Arena Coding: 1286 Elo2026-08-04
Design Arena Coding: 1283 Elo2026-08-14
Design Arena Coding: 1286 Elo2026-08-06
Design Arena Coding: 1285 Elo2026-08-10
Design Arena Coding: 1286 Elo2026-08-07
Design Arena Coding: 1279 Elo2026-08-18
Design Arena Coding: 1286 Elo2026-08-08
Design Arena Coding: 1279 Elo2026-08-15
Design Arena Coding: 1285 Elo2026-08-11
Design Arena Coding: 1285 Elo2026-08-12
Design Arena Coding: 1284 Elo2026-08-21
Design Arena Coding: 1283 Elo2026-08-13
Design Arena Coding: 1278 Elo2026-08-19
Design Arena Coding: 1284 Elo2026-08-27
Design Arena Coding: 1278 Elo2026-08-20
Design Arena Coding: 1279 Elo2026-08-16
Design Arena Coding: 1275 Elo2026-09-05
Design Arena Coding: 1279 Elo2026-08-17
Design Arena Coding: 1284 Elo2026-08-22
Design Arena Coding: 1284 Elo2026-08-23
Design Arena Coding: 1283 Elo2026-08-28
Design Arena Coding: 1284 Elo2026-08-24
Design Arena Coding: 1284 Elo2026-08-25
Design Arena Coding: 1284 Elo2026-08-26
Design Arena Coding: 1275 Elo2026-09-06
Design Arena Coding: 1283 Elo2026-08-29
Design Arena Coding: 1283 Elo2026-08-30
Design Arena Coding: 1283 Elo2026-08-31
Design Arena Coding: 1283 Elo2026-09-01
Design Arena Coding: 1281 Elo2026-09-02
Design Arena Coding: 1279 Elo2026-09-03
Design Arena Coding: 1278 Elo2026-09-04
Design Arena Full-stack Agent: 1131 Elo2026-07-28
Design Arena Full-stack Agent: 1132 Elo2026-07-27
Design Arena Full-stack Agent: 1124 Elo2026-07-30
Design Arena Full-stack Agent: 1125 Elo2026-07-29
Design Arena Full-stack Agent: 1126 Elo2026-07-31
Design Arena Full-stack Agent: 1128 Elo2026-08-02
Design Arena Full-stack Agent: 1128 Elo2026-08-05
Design Arena Full-stack Agent: 1127 Elo2026-08-01
Design Arena Full-stack Agent: 1121 Elo2026-08-09
Design Arena Full-stack Agent: 1129 Elo2026-08-03
Design Arena Full-stack Agent: 1129 Elo2026-08-04
Design Arena Full-stack Agent: 1121 Elo2026-08-14
Design Arena Full-stack Agent: 1128 Elo2026-08-06
Design Arena Full-stack Agent: 1118 Elo2026-08-10
Design Arena Full-stack Agent: 1129 Elo2026-08-07
Design Arena Full-stack Agent: 1118 Elo2026-08-18
Design Arena Full-stack Agent: 1129 Elo2026-08-08
Design Arena Full-stack Agent: 1122 Elo2026-08-11
Design Arena Full-stack Agent: 1124 Elo2026-08-15
Design Arena Full-stack Agent: 1123 Elo2026-08-12
Design Arena Full-stack Agent: 1121 Elo2026-08-13
Design Arena Full-stack Agent: 1118 Elo2026-08-19
Design Arena Full-stack Agent: 1114 Elo2026-08-27
Design Arena Full-stack Agent: 1118 Elo2026-08-20
Design Arena Full-stack Agent: 1124 Elo2026-08-16
Design Arena Full-stack Agent: 1104 Elo2026-09-05
Design Arena Full-stack Agent: 1124 Elo2026-08-17
Design Arena Full-stack Agent: 1123 Elo2026-08-21
Design Arena Full-stack Agent: 1123 Elo2026-08-22
Design Arena Full-stack Agent: 1123 Elo2026-08-23
Design Arena Full-stack Agent: 1113 Elo2026-08-28
Design Arena Full-stack Agent: 1110 Elo2026-08-24
Design Arena Full-stack Agent: 1114 Elo2026-08-25
Design Arena Full-stack Agent: 1114 Elo2026-08-26
Design Arena Full-stack Agent: 1101 Elo2026-09-06
Design Arena Full-stack Agent: 1113 Elo2026-08-29
Design Arena Full-stack Agent: 1114 Elo2026-08-30
Design Arena Full-stack Agent: 1114 Elo2026-08-31
Design Arena Full-stack Agent: 1114 Elo2026-09-01
Design Arena Full-stack Agent: 1114 Elo2026-09-02
Design Arena Full-stack Agent: 1115 Elo2026-09-03
Design Arena Full-stack Agent: 1114 Elo2026-09-04
Design Arena UI: 1290 Elo2026-07-28
Design Arena UI: 1291 Elo2026-07-27
Design Arena UI: 1290 Elo2026-07-30
Design Arena UI: 1291 Elo2026-07-29
Design Arena UI: 1290 Elo2026-07-31
Design Arena UI: 1292 Elo2026-08-02
Design Arena UI: 1292 Elo2026-08-01
Design Arena UI: 1293 Elo2026-08-05
Design Arena UI: 1289 Elo2026-08-09
Design Arena UI: 1293 Elo2026-08-03
Design Arena UI: 1294 Elo2026-08-04
Design Arena UI: 1287 Elo2026-08-14
Design Arena UI: 1292 Elo2026-08-06
Design Arena UI: 1292 Elo2026-08-07
Design Arena UI: 1290 Elo2026-08-10
Design Arena UI: 1291 Elo2026-08-08
Design Arena UI: 1284 Elo2026-08-18
Design Arena UI: 1290 Elo2026-08-11
Design Arena UI: 1285 Elo2026-08-15
Design Arena UI: 1289 Elo2026-08-12
Design Arena UI: 1290 Elo2026-08-13
Design Arena UI: 1284 Elo2026-08-19
Design Arena UI: 1285 Elo2026-08-16
Design Arena UI: 1284 Elo2026-08-20
Design Arena UI: 1280 Elo2026-08-27
Design Arena UI: 1285 Elo2026-08-17
Design Arena UI: 1279 Elo2026-09-05
Design Arena UI: 1283 Elo2026-08-21
Design Arena UI: 1281 Elo2026-08-22
Design Arena UI: 1282 Elo2026-08-23
Design Arena UI: 1281 Elo2026-08-28
Design Arena UI: 1283 Elo2026-08-24
Design Arena UI: 1283 Elo2026-08-25
Design Arena UI: 1282 Elo2026-08-26
Design Arena UI: 1279 Elo2026-09-06
Design Arena UI: 1281 Elo2026-08-29
Design Arena UI: 1282 Elo2026-08-30
Design Arena UI: 1282 Elo2026-08-31
Design Arena UI: 1281 Elo2026-09-01
Design Arena UI: 1280 Elo2026-09-02
Design Arena UI: 1278 Elo2026-09-03
Design Arena UI: 1278 Elo2026-09-04
Design Arena Web-app Agent: 1166 Elo2026-07-28
Design Arena Web-app Agent: 1166 Elo2026-07-27
Design Arena Web-app Agent: 1165 Elo2026-07-30
Design Arena Web-app Agent: 1165 Elo2026-07-29
Design Arena Web-app Agent: 1166 Elo2026-07-31
Design Arena Web-app Agent: 1167 Elo2026-08-02
Design Arena Web-app Agent: 1166 Elo2026-08-01
Design Arena Web-app Agent: 1165 Elo2026-08-05
Design Arena Web-app Agent: 1159 Elo2026-08-09
Design Arena Web-app Agent: 1167 Elo2026-08-03
Design Arena Web-app Agent: 1167 Elo2026-08-04
Design Arena Web-app Agent: 1154 Elo2026-08-14
Design Arena Web-app Agent: 1165 Elo2026-08-06
Design Arena Web-app Agent: 1157 Elo2026-08-10
Design Arena Web-app Agent: 1165 Elo2026-08-07
Design Arena Web-app Agent: 1154 Elo2026-08-18
Design Arena Web-app Agent: 1166 Elo2026-08-08
Design Arena Web-app Agent: 1156 Elo2026-08-11
Design Arena Web-app Agent: 1157 Elo2026-08-15
Design Arena Web-app Agent: 1156 Elo2026-08-12
Design Arena Web-app Agent: 1155 Elo2026-08-13
Design Arena Web-app Agent: 1154 Elo2026-08-19
Design Arena Web-app Agent: 1148 Elo2026-08-27
Design Arena Web-app Agent: 1154 Elo2026-08-20
Design Arena Web-app Agent: 1158 Elo2026-08-16
Design Arena Web-app Agent: 1158 Elo2026-08-17
Design Arena Web-app Agent: 1147 Elo2026-09-05
Design Arena Web-app Agent: 1152 Elo2026-08-21
Design Arena Web-app Agent: 1153 Elo2026-08-22
Design Arena Web-app Agent: 1153 Elo2026-08-23
Design Arena Web-app Agent: 1148 Elo2026-08-28
Design Arena Web-app Agent: 1148 Elo2026-08-24
Design Arena Web-app Agent: 1149 Elo2026-08-25
Design Arena Web-app Agent: 1149 Elo2026-08-26
Design Arena Web-app Agent: 1147 Elo2026-09-06
Design Arena Web-app Agent: 1148 Elo2026-08-29
Design Arena Web-app Agent: 1147 Elo2026-08-30
Design Arena Web-app Agent: 1148 Elo2026-08-31
Design Arena Web-app Agent: 1147 Elo2026-09-01
Design Arena Web-app Agent: 1147 Elo2026-09-02
Design Arena Web-app Agent: 1147 Elo2026-09-03
Design Arena Web-app Agent: 1147 Elo2026-09-04
Design Arena Website: 1280 Elo2026-07-28
Design Arena Website: 1280 Elo2026-07-30
Design Arena Website: 1280 Elo2026-07-27
Design Arena Website: 1281 Elo2026-07-29
Design Arena Website: 1280 Elo2026-07-31
Design Arena Website: 1280 Elo2026-08-02
Design Arena Website: 1280 Elo2026-08-01
Design Arena Website: 1280 Elo2026-08-05
Design Arena Website: 1280 Elo2026-08-03
Design Arena Website: 1280 Elo2026-08-09
Design Arena Website: 1280 Elo2026-08-04
Design Arena Website: 1277 Elo2026-08-14
Design Arena Website: 1280 Elo2026-08-06
Design Arena Website: 1281 Elo2026-08-07
Design Arena Website: 1280 Elo2026-08-10
Design Arena Website: 1280 Elo2026-08-08
Design Arena Website: 1268 Elo2026-08-18
Design Arena Website: 1280 Elo2026-08-11
Design Arena Website: 1269 Elo2026-08-15
Design Arena Website: 1280 Elo2026-08-12
Design Arena Website: 1278 Elo2026-08-13
Design Arena Website: 1268 Elo2026-08-19
Design Arena Website: 1268 Elo2026-08-16
Design Arena Website: 1268 Elo2026-08-20
Design Arena Website: 1276 Elo2026-08-27
Design Arena Website: 1268 Elo2026-08-17
Design Arena Website: 1271 Elo2026-09-05
Design Arena Website: 1276 Elo2026-08-21
Design Arena Website: 1276 Elo2026-08-22
Design Arena Website: 1276 Elo2026-08-23
Design Arena Website: 1276 Elo2026-08-24
Design Arena Website: 1276 Elo2026-08-28
Design Arena Website: 1276 Elo2026-08-25
Design Arena Website: 1277 Elo2026-08-26
Design Arena Website: 1269 Elo2026-09-06
Design Arena Website: 1276 Elo2026-08-29
Design Arena Website: 1275 Elo2026-08-30
Design Arena Website: 1275 Elo2026-08-31
Design Arena Website: 1275 Elo2026-09-01
Design Arena Website: 1274 Elo2026-09-02
Design Arena Website: 1272 Elo2026-09-03
Design Arena Website: 1271 Elo2026-09-04
LiveBench Agentic Coding: 54.0%2026-06-25
LiveBench Coding: 82.2%2026-06-25
LiveBench Data Analysis: 81.6%2026-06-25
LiveBench Instruction Following: 70.7%2026-06-25
LiveBench Language: 87.4%2026-06-25
LiveBench Math: 95.9%2026-06-25
LiveBench Reasoning: 89.7%2026-06-25
LMArena Agent: 7.22026-07-13
LMArena Agent: 7.72026-07-20
LMArena Agent: 8.62026-07-27
LMArena Agent: 8.42026-07-21
LMArena Agent: 8.52026-07-28
LMArena Agent: 8.52026-08-03
LMArena Agent: 8.52026-08-06
LMArena Agent: 8.82026-08-12
LMArena Agent: 8.72026-08-11
LMArena Agent: 8.92026-08-13
LMArena Agent: 8.62026-08-24
LMArena Agent: 7.92026-08-31
LMArena Agent: 7.22026-09-05
LMArena Agent: 7.92026-08-27
LMArena Creative Writing: 1450 Elo2026-07-21
LMArena Creative Writing: 1451 Elo2026-07-27
LMArena Creative Writing: 1451 Elo2026-07-30
LMArena Creative Writing: 1453 Elo2026-08-02
LMArena Creative Writing: 1453 Elo2026-08-03
LMArena Creative Writing: 1454 Elo2026-08-06
LMArena Creative Writing: 1453 Elo2026-08-12
LMArena Creative Writing: 1455 Elo2026-08-21
LMArena Creative Writing: 1455 Elo2026-09-02
LMArena Creative Writing: 1455 Elo2026-08-27
LMArena Creative Writing: 1455 Elo2026-09-01
LMArena Instruction Following: 1477 Elo2026-07-21
LMArena Instruction Following: 1476 Elo2026-07-27
LMArena Instruction Following: 1476 Elo2026-07-30
LMArena Instruction Following: 1478 Elo2026-08-02
LMArena Instruction Following: 1478 Elo2026-08-03
LMArena Instruction Following: 1479 Elo2026-08-06
LMArena Instruction Following: 1479 Elo2026-08-12
LMArena Instruction Following: 1478 Elo2026-08-21
LMArena Instruction Following: 1478 Elo2026-09-02
LMArena Instruction Following: 1479 Elo2026-08-27
LMArena Instruction Following: 1478 Elo2026-09-01
LMArena Long Query: 1481 Elo2026-07-21
LMArena Long Query: 1481 Elo2026-07-27
LMArena Long Query: 1481 Elo2026-07-30
LMArena Long Query: 1482 Elo2026-08-02
LMArena Long Query: 1482 Elo2026-08-03
LMArena Long Query: 1483 Elo2026-08-06
LMArena Long Query: 1483 Elo2026-08-12
LMArena Long Query: 1483 Elo2026-08-21
LMArena Long Query: 1485 Elo2026-09-02
LMArena Long Query: 1484 Elo2026-08-27
LMArena Long Query: 1485 Elo2026-09-01
LMArena Math: 1482 Elo2026-07-21
LMArena Math: 1482 Elo2026-07-27
LMArena Math: 1482 Elo2026-07-30
LMArena Math: 1485 Elo2026-08-02
LMArena Math: 1485 Elo2026-08-03
LMArena Math: 1485 Elo2026-08-06
LMArena Math: 1484 Elo2026-08-12
LMArena Math: 1484 Elo2026-08-21
LMArena Math: 1485 Elo2026-08-27
LMArena Math: 1488 Elo2026-09-01
LMArena Text: 1470 Elo2026-07-16
LMArena Text: 1491 Elo2026-07-20
LMArena Text: 1482 Elo2026-07-21
LMArena Text: 1482 Elo2026-07-27
LMArena Text: 1482 Elo2026-07-30
LMArena Text: 1482 Elo2026-08-02
LMArena Text: 1482 Elo2026-08-06
LMArena Text: 1482 Elo2026-08-03
LMArena Text: 1481 Elo2026-08-10
LMArena Text: 1482 Elo2026-08-21
LMArena Text: 1482 Elo2026-08-12
LMArena Text: 1482 Elo2026-09-01
LMArena Text: 1482 Elo2026-09-02
LMArena Text: 1482 Elo2026-08-27
LMArena Vision: 1297 Elo2026-07-12
LMArena Vision: 1286 Elo2026-07-21
LMArena Vision: 1287 Elo2026-07-26
LMArena Vision: 1287 Elo2026-07-30
LMArena Vision: 1287 Elo2026-08-02
LMArena Vision: 1286 Elo2026-08-06
LMArena Vision: 1285 Elo2026-08-21
LMArena Vision: 1286 Elo2026-08-27
LMArena WebDev: 1507 Elo2026-07-21
LMArena WebDev: 1507 Elo2026-07-27
LMArena WebDev: 1505 Elo2026-07-24
LMArena WebDev: 1507 Elo2026-07-28
LMArena WebDev: 1507 Elo2026-07-30
LMArena WebDev: 1509 Elo2026-08-01
LMArena WebDev: 1508 Elo2026-07-31
LMArena WebDev: 1509 Elo2026-08-06
LMArena WebDev: 1509 Elo2026-08-02
LMArena WebDev: 1509 Elo2026-08-12
LMArena WebDev: 1508 Elo2026-08-10
LMArena WebDev: 1507 Elo2026-08-14
LMArena WebDev: 1510 Elo2026-09-01
LMArena WebDev: 1510 Elo2026-09-05
LMArena WebDev: 1508 Elo2026-08-21
LMArena WebDev: 1510 Elo2026-08-30
OSWorld Verified^‡: 13%2026-06-24xhigh effort
SWE-rebench^‡: 62.7% ± 0.92026-05-15tools
Terminal-Bench 2.1^‡: 83.2% ± 1.12026-05-01xhigh effort

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 Computer & Browser UseEstablished evidence
90% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
Best LLM for Agentic CodingEstablished evidence
86% of intended weighted task evidence across 5 independent sources. 8 of 8 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 LLM for Autonomous AgentsEstablished evidence
82% of intended weighted task evidence across 5 independent sources. 7 of 7 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 Debugging & Code ReviewEstablished evidence
70% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.
Best LLM for AI AgentsEstablished evidence
70% of intended weighted task evidence across 5 independent sources. 7 of 7 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 Hermes AgentEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 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 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 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 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.