Grok 4.5

x-ai/grok-4.5-20260708

xAI: Grok 4.5, provided by x‑ai, accepts text, image, and file inputs and generates text output. It supports a context length of 500 000 tokens, with pricing of $2 per million input tokens and $6 per million output tokens, and offers both tool use and reasoning capabilities.

tool use
structured outputs
reasoning

At a glance

providerx-ai

releasedJul 7, 2026

context500K

input / M$2

Specifications

What the API gives you

Context window: 500K tokens
Max output: 450K tokens
Input price: $2 / 1M tokens
Output price: $6 / 1M tokens
Cache read: $0.30 / 1M tokens
Modalities: text, image, file → text
Knowledge cutoff: —
Released: Jul 7, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1312 Elo2026-07-28
Design Arena Coding: 1312 Elo2026-07-27
Design Arena Coding: 1313 Elo2026-07-30
Design Arena Coding: 1312 Elo2026-07-29
Design Arena Coding: 1313 Elo2026-07-31
Design Arena Coding: 1312 Elo2026-08-02
Design Arena Coding: 1312 Elo2026-08-05
Design Arena Coding: 1312 Elo2026-08-01
Design Arena Coding: 1311 Elo2026-08-09
Design Arena Coding: 1312 Elo2026-08-03
Design Arena Coding: 1313 Elo2026-08-04
Design Arena Coding: 1308 Elo2026-08-14
Design Arena Coding: 1312 Elo2026-08-06
Design Arena Coding: 1311 Elo2026-08-10
Design Arena Coding: 1313 Elo2026-08-07
Design Arena Coding: 1301 Elo2026-08-18
Design Arena Coding: 1312 Elo2026-08-08
Design Arena Coding: 1307 Elo2026-08-21
Design Arena Coding: 1300 Elo2026-08-15
Design Arena Coding: 1311 Elo2026-08-11
Design Arena Coding: 1310 Elo2026-08-12
Design Arena Coding: 1299 Elo2026-08-19
Design Arena Coding: 1308 Elo2026-08-13
Design Arena Coding: 1305 Elo2026-08-27
Design Arena Coding: 1295 Elo2026-09-05
Design Arena Coding: 1299 Elo2026-08-20
Design Arena Coding: 1300 Elo2026-08-16
Design Arena Coding: 1299 Elo2026-08-17
Design Arena Coding: 1306 Elo2026-08-22
Design Arena Coding: 1306 Elo2026-08-23
Design Arena Coding: 1304 Elo2026-08-28
Design Arena Coding: 1306 Elo2026-08-24
Design Arena Coding: 1306 Elo2026-08-25
Design Arena Coding: 1306 Elo2026-08-26
Design Arena Coding: 1295 Elo2026-09-06
Design Arena Coding: 1304 Elo2026-08-29
Design Arena Coding: 1304 Elo2026-08-30
Design Arena Coding: 1303 Elo2026-08-31
Design Arena Coding: 1303 Elo2026-09-01
Design Arena Coding: 1302 Elo2026-09-02
Design Arena Coding: 1300 Elo2026-09-03
Design Arena Coding: 1299 Elo2026-09-04
Design Arena Full-stack Agent: 1289 Elo2026-07-28
Design Arena Full-stack Agent: 1293 Elo2026-07-27
Design Arena Full-stack Agent: 1281 Elo2026-07-30
Design Arena Full-stack Agent: 1283 Elo2026-07-29
Design Arena Full-stack Agent: 1281 Elo2026-07-31
Design Arena Full-stack Agent: 1283 Elo2026-08-02
Design Arena Full-stack Agent: 1290 Elo2026-08-05
Design Arena Full-stack Agent: 1281 Elo2026-08-01
Design Arena Full-stack Agent: 1282 Elo2026-08-09
Design Arena Full-stack Agent: 1285 Elo2026-08-03
Design Arena Full-stack Agent: 1286 Elo2026-08-04
Design Arena Full-stack Agent: 1281 Elo2026-08-14
Design Arena Full-stack Agent: 1290 Elo2026-08-06
Design Arena Full-stack Agent: 1279 Elo2026-08-10
Design Arena Full-stack Agent: 1290 Elo2026-08-07
Design Arena Full-stack Agent: 1275 Elo2026-08-18
Design Arena Full-stack Agent: 1290 Elo2026-08-08
Design Arena Full-stack Agent: 1283 Elo2026-08-15
Design Arena Full-stack Agent: 1286 Elo2026-08-11
Design Arena Full-stack Agent: 1286 Elo2026-08-12
Design Arena Full-stack Agent: 1282 Elo2026-08-13
Design Arena Full-stack Agent: 1274 Elo2026-08-19
Design Arena Full-stack Agent: 1271 Elo2026-08-27
Design Arena Full-stack Agent: 1274 Elo2026-08-20
Design Arena Full-stack Agent: 1280 Elo2026-08-16
Design Arena Full-stack Agent: 1264 Elo2026-09-05
Design Arena Full-stack Agent: 1280 Elo2026-08-17
Design Arena Full-stack Agent: 1279 Elo2026-08-21
Design Arena Full-stack Agent: 1278 Elo2026-08-22
Design Arena Full-stack Agent: 1277 Elo2026-08-23
Design Arena Full-stack Agent: 1270 Elo2026-08-28
Design Arena Full-stack Agent: 1265 Elo2026-08-24
Design Arena Full-stack Agent: 1268 Elo2026-08-25
Design Arena Full-stack Agent: 1270 Elo2026-08-26
Design Arena Full-stack Agent: 1261 Elo2026-09-06
Design Arena Full-stack Agent: 1272 Elo2026-08-29
Design Arena Full-stack Agent: 1273 Elo2026-08-30
Design Arena Full-stack Agent: 1273 Elo2026-08-31
Design Arena Full-stack Agent: 1274 Elo2026-09-01
Design Arena Full-stack Agent: 1274 Elo2026-09-02
Design Arena Full-stack Agent: 1274 Elo2026-09-03
Design Arena Full-stack Agent: 1274 Elo2026-09-04
Design Arena UI: 1325 Elo2026-07-28
Design Arena UI: 1323 Elo2026-07-27
Design Arena UI: 1325 Elo2026-07-30
Design Arena UI: 1324 Elo2026-07-29
Design Arena UI: 1326 Elo2026-07-31
Design Arena UI: 1324 Elo2026-08-02
Design Arena UI: 1324 Elo2026-08-01
Design Arena UI: 1320 Elo2026-08-05
Design Arena UI: 1322 Elo2026-08-09
Design Arena UI: 1325 Elo2026-08-03
Design Arena UI: 1326 Elo2026-08-04
Design Arena UI: 1318 Elo2026-08-14
Design Arena UI: 1321 Elo2026-08-06
Design Arena UI: 1322 Elo2026-08-07
Design Arena UI: 1322 Elo2026-08-10
Design Arena UI: 1322 Elo2026-08-08
Design Arena UI: 1310 Elo2026-08-18
Design Arena UI: 1322 Elo2026-08-11
Design Arena UI: 1314 Elo2026-08-15
Design Arena UI: 1322 Elo2026-08-12
Design Arena UI: 1322 Elo2026-08-13
Design Arena UI: 1310 Elo2026-08-19
Design Arena UI: 1304 Elo2026-08-27
Design Arena UI: 1314 Elo2026-08-16
Design Arena UI: 1310 Elo2026-08-20
Design Arena UI: 1311 Elo2026-08-17
Design Arena UI: 1299 Elo2026-09-05
Design Arena UI: 1312 Elo2026-08-21
Design Arena UI: 1310 Elo2026-08-22
Design Arena UI: 1312 Elo2026-08-23
Design Arena UI: 1304 Elo2026-08-28
Design Arena UI: 1309 Elo2026-08-24
Design Arena UI: 1309 Elo2026-08-25
Design Arena UI: 1306 Elo2026-08-26
Design Arena UI: 1300 Elo2026-09-06
Design Arena UI: 1304 Elo2026-08-29
Design Arena UI: 1303 Elo2026-08-30
Design Arena UI: 1300 Elo2026-08-31
Design Arena UI: 1301 Elo2026-09-01
Design Arena UI: 1302 Elo2026-09-02
Design Arena UI: 1300 Elo2026-09-03
Design Arena UI: 1298 Elo2026-09-04
Design Arena Web-app Agent: 1264 Elo2026-07-28
Design Arena Web-app Agent: 1264 Elo2026-07-27
Design Arena Web-app Agent: 1261 Elo2026-07-30
Design Arena Web-app Agent: 1261 Elo2026-07-29
Design Arena Web-app Agent: 1261 Elo2026-07-31
Design Arena Web-app Agent: 1262 Elo2026-08-02
Design Arena Web-app Agent: 1261 Elo2026-08-01
Design Arena Web-app Agent: 1259 Elo2026-08-05
Design Arena Web-app Agent: 1255 Elo2026-08-09
Design Arena Web-app Agent: 1262 Elo2026-08-03
Design Arena Web-app Agent: 1263 Elo2026-08-04
Design Arena Web-app Agent: 1250 Elo2026-08-14
Design Arena Web-app Agent: 1259 Elo2026-08-06
Design Arena Web-app Agent: 1253 Elo2026-08-10
Design Arena Web-app Agent: 1259 Elo2026-08-07
Design Arena Web-app Agent: 1249 Elo2026-08-18
Design Arena Web-app Agent: 1261 Elo2026-08-08
Design Arena Web-app Agent: 1253 Elo2026-08-11
Design Arena Web-app Agent: 1250 Elo2026-08-15
Design Arena Web-app Agent: 1253 Elo2026-08-12
Design Arena Web-app Agent: 1251 Elo2026-08-13
Design Arena Web-app Agent: 1249 Elo2026-08-19
Design Arena Web-app Agent: 1245 Elo2026-08-27
Design Arena Web-app Agent: 1249 Elo2026-08-20
Design Arena Web-app Agent: 1252 Elo2026-08-16
Design Arena Web-app Agent: 1245 Elo2026-09-05
Design Arena Web-app Agent: 1252 Elo2026-08-17
Design Arena Web-app Agent: 1248 Elo2026-08-21
Design Arena Web-app Agent: 1249 Elo2026-08-22
Design Arena Web-app Agent: 1250 Elo2026-08-23
Design Arena Web-app Agent: 1246 Elo2026-08-28
Design Arena Web-app Agent: 1244 Elo2026-08-24
Design Arena Web-app Agent: 1246 Elo2026-08-25
Design Arena Web-app Agent: 1246 Elo2026-08-26
Design Arena Web-app Agent: 1245 Elo2026-09-06
Design Arena Web-app Agent: 1246 Elo2026-08-29
Design Arena Web-app Agent: 1245 Elo2026-08-30
Design Arena Web-app Agent: 1246 Elo2026-08-31
Design Arena Web-app Agent: 1246 Elo2026-09-01
Design Arena Web-app Agent: 1245 Elo2026-09-02
Design Arena Web-app Agent: 1245 Elo2026-09-03
Design Arena Web-app Agent: 1245 Elo2026-09-04
Design Arena Website: 1321 Elo2026-07-28
Design Arena Website: 1321 Elo2026-07-27
Design Arena Website: 1323 Elo2026-07-30
Design Arena Website: 1321 Elo2026-07-29
Design Arena Website: 1323 Elo2026-07-31
Design Arena Website: 1323 Elo2026-08-02
Design Arena Website: 1323 Elo2026-08-01
Design Arena Website: 1319 Elo2026-08-05
Design Arena Website: 1322 Elo2026-08-03
Design Arena Website: 1317 Elo2026-08-09
Design Arena Website: 1321 Elo2026-08-04
Design Arena Website: 1312 Elo2026-08-14
Design Arena Website: 1319 Elo2026-08-06
Design Arena Website: 1319 Elo2026-08-07
Design Arena Website: 1317 Elo2026-08-10
Design Arena Website: 1318 Elo2026-08-08
Design Arena Website: 1299 Elo2026-08-18
Design Arena Website: 1316 Elo2026-08-11
Design Arena Website: 1303 Elo2026-08-15
Design Arena Website: 1315 Elo2026-08-12
Design Arena Website: 1313 Elo2026-08-13
Design Arena Website: 1299 Elo2026-08-19
Design Arena Website: 1303 Elo2026-08-16
Design Arena Website: 1299 Elo2026-08-20
Design Arena Website: 1305 Elo2026-08-27
Design Arena Website: 1300 Elo2026-08-17
Design Arena Website: 1300 Elo2026-09-05
Design Arena Website: 1308 Elo2026-08-21
Design Arena Website: 1308 Elo2026-08-22
Design Arena Website: 1308 Elo2026-08-23
Design Arena Website: 1308 Elo2026-08-24
Design Arena Website: 1305 Elo2026-08-28
Design Arena Website: 1307 Elo2026-08-25
Design Arena Website: 1307 Elo2026-08-26
Design Arena Website: 1298 Elo2026-09-06
Design Arena Website: 1305 Elo2026-08-29
Design Arena Website: 1305 Elo2026-08-30
Design Arena Website: 1304 Elo2026-08-31
Design Arena Website: 1304 Elo2026-09-01
Design Arena Website: 1303 Elo2026-09-02
Design Arena Website: 1302 Elo2026-09-03
Design Arena Website: 1301 Elo2026-09-04
Frontier-Bench^‡: 15.7% ± 1.52026-07-15Cursor CLI, xhigh effort
Frontier-Bench^‡: 12.4%2026-07-16Grok Build, high effort
LiveBench Agentic Coding: 56.5%2026-06-25
LiveBench Coding: 68.6%2026-06-25
LiveBench Data Analysis: 73.0%2026-06-25
LiveBench Instruction Following: 71.5%2026-06-25
LiveBench Language: 82.8%2026-06-25
LiveBench Math: 90.8%2026-06-25
LiveBench Reasoning: 87.2%2026-06-25
LMArena Agent: 52026-07-13
LMArena Agent: 6.42026-07-20
LMArena Agent: 5.52026-07-27
LMArena Agent: 5.62026-07-21
LMArena Agent: 5.52026-07-28
LMArena Agent: 5.62026-08-03
LMArena Agent: 62026-08-12
LMArena Agent: 5.62026-08-06
LMArena Agent: 5.72026-08-11
LMArena Agent: 6.22026-08-13
LMArena Agent: 6.42026-08-24
LMArena Agent: 6.12026-08-31
LMArena Agent: 5.72026-09-05
LMArena Agent: 6.52026-08-27
LMArena Creative Writing: 1431 Elo2026-07-21
LMArena Creative Writing: 1439 Elo2026-07-27
LMArena Creative Writing: 1439 Elo2026-07-30
LMArena Creative Writing: 1438 Elo2026-08-02
LMArena Creative Writing: 1438 Elo2026-08-03
LMArena Creative Writing: 1436 Elo2026-08-06
LMArena Creative Writing: 1434 Elo2026-08-12
LMArena Creative Writing: 1439 Elo2026-08-21
LMArena Creative Writing: 1441 Elo2026-09-02
LMArena Creative Writing: 1440 Elo2026-08-27
LMArena Creative Writing: 1440 Elo2026-09-01
LMArena Instruction Following: 1445 Elo2026-07-21
LMArena Instruction Following: 1442 Elo2026-07-27
LMArena Instruction Following: 1442 Elo2026-07-30
LMArena Instruction Following: 1447 Elo2026-08-02
LMArena Instruction Following: 1447 Elo2026-08-03
LMArena Instruction Following: 1448 Elo2026-08-06
LMArena Instruction Following: 1447 Elo2026-08-12
LMArena Instruction Following: 1449 Elo2026-08-21
LMArena Instruction Following: 1449 Elo2026-09-02
LMArena Instruction Following: 1447 Elo2026-08-27
LMArena Instruction Following: 1448 Elo2026-09-01
LMArena Long Query: 1467 Elo2026-07-21
LMArena Long Query: 1466 Elo2026-07-27
LMArena Long Query: 1466 Elo2026-07-30
LMArena Long Query: 1467 Elo2026-08-02
LMArena Long Query: 1467 Elo2026-08-03
LMArena Long Query: 1466 Elo2026-08-06
LMArena Long Query: 1467 Elo2026-08-12
LMArena Long Query: 1468 Elo2026-08-21
LMArena Long Query: 1469 Elo2026-09-02
LMArena Long Query: 1467 Elo2026-08-27
LMArena Long Query: 1468 Elo2026-09-01
LMArena Math: 1490 Elo2026-07-21
LMArena Math: 1484 Elo2026-07-27
LMArena Math: 1484 Elo2026-07-30
LMArena Math: 1475 Elo2026-08-02
LMArena Math: 1475 Elo2026-08-03
LMArena Math: 1466 Elo2026-08-06
LMArena Math: 1466 Elo2026-08-12
LMArena Math: 1464 Elo2026-08-21
LMArena Math: 1464 Elo2026-09-01
LMArena Math: 1467 Elo2026-08-27
LMArena Text: 1452 Elo2026-07-16
LMArena Text: 1476 Elo2026-07-20
LMArena Text: 1468 Elo2026-07-21
LMArena Text: 1468 Elo2026-07-27
LMArena Text: 1468 Elo2026-07-30
LMArena Text: 1469 Elo2026-08-02
LMArena Text: 1468 Elo2026-08-06
LMArena Text: 1469 Elo2026-08-03
LMArena Text: 1469 Elo2026-08-10
LMArena Text: 1470 Elo2026-08-21
LMArena Text: 1468 Elo2026-08-12
LMArena Text: 1470 Elo2026-09-01
LMArena Text: 1471 Elo2026-09-02
LMArena Text: 1470 Elo2026-08-27
LMArena Vision: 1282 Elo2026-07-26
LMArena Vision: 1282 Elo2026-07-30
LMArena Vision: 1282 Elo2026-08-02
LMArena Vision: 1285 Elo2026-08-06
LMArena Vision: 1282 Elo2026-08-21
LMArena Vision: 1282 Elo2026-08-27
LMArena WebDev: 1558 Elo2026-07-16
LMArena WebDev: 1557 Elo2026-07-21
LMArena WebDev: 1556 Elo2026-07-20
LMArena WebDev: 1550 Elo2026-07-27
LMArena WebDev: 1550 Elo2026-07-24
LMArena WebDev: 1550 Elo2026-07-28
LMArena WebDev: 1550 Elo2026-07-30
LMArena WebDev: 1549 Elo2026-08-01
LMArena WebDev: 1550 Elo2026-07-31
LMArena WebDev: 1552 Elo2026-08-06
LMArena WebDev: 1549 Elo2026-08-02
LMArena WebDev: 1554 Elo2026-08-10
LMArena WebDev: 1553 Elo2026-08-12
LMArena WebDev: 1555 Elo2026-08-14
LMArena WebDev: 1555 Elo2026-09-01
LMArena WebDev: 1556 Elo2026-09-05
LMArena WebDev: 1556 Elo2026-08-21
LMArena WebDev: 1556 Elo2026-08-30
SWE-rebench^‡: 63.8% ± 0.62026-07-01tools
Terminal-Bench 2.1^‡: 79.3% ± 1.52026-07-09high effort
Terminal-Bench 2.1^‡: 12.4%2026-07-16high 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 Agentic CodingEstablished evidence
100% of intended weighted task evidence across 6 independent sources. 8 of 8 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 Autonomous AgentsEstablished evidence
95% of intended weighted task evidence across 5 independent sources. 7 of 7 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 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 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 AI AgentsProvisional evidence
60% of intended weighted task evidence across 4 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 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 RAG & Long ContextProvisional evidence
47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LongBench v2. 4 of 6 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 Tool & Function CallingProvisional evidence
35% of intended weighted task evidence across 1 independent source; 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 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 Grounded RAGProvisional evidence
30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 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.

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.