Grok 4.6

x-ai/grok-4.6-20260810

SpaceXAI: Grok 4.6 is a model from x-ai that processes text, image, and file inputs to generate text outputs. It has a context length of 500,000 tokens, supports tool use and reasoning, and is not open-weight. It was released on August 10, 2026.

tool use
structured outputs
reasoning

At a glance

providerx-ai

releasedAug 10, 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: $0.50 / 1M tokens
Modalities: text, image, file → text
Knowledge cutoff: —
Released: Aug 10, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1336 Elo2026-08-14
Design Arena Coding: 1322 Elo2026-08-18
Design Arena Coding: 1327 Elo2026-08-21
Design Arena Coding: 1326 Elo2026-08-15
Design Arena Coding: 1320 Elo2026-08-19
Design Arena Coding: 1325 Elo2026-08-27
Design Arena Coding: 1320 Elo2026-08-20
Design Arena Coding: 1327 Elo2026-08-16
Design Arena Coding: 1324 Elo2026-08-17
Design Arena Coding: 1327 Elo2026-08-22
Design Arena Coding: 1327 Elo2026-08-23
Design Arena Coding: 1324 Elo2026-08-28
Design Arena Coding: 1326 Elo2026-08-24
Design Arena Coding: 1326 Elo2026-08-25
Design Arena Coding: 1326 Elo2026-08-26
Design Arena Coding: 1324 Elo2026-08-29
Design Arena Coding: 1323 Elo2026-08-30
Design Arena Coding: 1323 Elo2026-08-31
Design Arena Coding: 1323 Elo2026-09-01
Design Arena Coding: 1321 Elo2026-09-02
Design Arena Coding: 1318 Elo2026-09-03
Design Arena Coding: 1317 Elo2026-09-04
Design Arena Full-stack Agent: 1287 Elo2026-08-14
Design Arena Full-stack Agent: 1285 Elo2026-08-18
Design Arena Full-stack Agent: 1290 Elo2026-08-15
Design Arena Full-stack Agent: 1285 Elo2026-08-19
Design Arena Full-stack Agent: 1286 Elo2026-08-27
Design Arena Full-stack Agent: 1285 Elo2026-08-20
Design Arena Full-stack Agent: 1288 Elo2026-08-16
Design Arena Full-stack Agent: 1289 Elo2026-08-17
Design Arena Full-stack Agent: 1292 Elo2026-08-21
Design Arena Full-stack Agent: 1292 Elo2026-08-22
Design Arena Full-stack Agent: 1293 Elo2026-08-23
Design Arena Full-stack Agent: 1285 Elo2026-08-28
Design Arena Full-stack Agent: 1281 Elo2026-08-24
Design Arena Full-stack Agent: 1284 Elo2026-08-25
Design Arena Full-stack Agent: 1285 Elo2026-08-26
Design Arena Full-stack Agent: 1285 Elo2026-08-29
Design Arena Full-stack Agent: 1285 Elo2026-08-30
Design Arena Full-stack Agent: 1285 Elo2026-08-31
Design Arena Full-stack Agent: 1285 Elo2026-09-01
Design Arena Full-stack Agent: 1286 Elo2026-09-02
Design Arena Full-stack Agent: 1286 Elo2026-09-03
Design Arena Full-stack Agent: 1286 Elo2026-09-04
Design Arena UI: 1347 Elo2026-08-18
Design Arena UI: 1354 Elo2026-08-15
Design Arena UI: 1347 Elo2026-08-19
Design Arena UI: 1340 Elo2026-08-27
Design Arena UI: 1346 Elo2026-08-16
Design Arena UI: 1347 Elo2026-08-20
Design Arena UI: 1340 Elo2026-08-17
Design Arena UI: 1339 Elo2026-08-21
Design Arena UI: 1337 Elo2026-08-22
Design Arena UI: 1336 Elo2026-08-23
Design Arena UI: 1337 Elo2026-08-28
Design Arena UI: 1340 Elo2026-08-24
Design Arena UI: 1341 Elo2026-08-25
Design Arena UI: 1342 Elo2026-08-26
Design Arena UI: 1334 Elo2026-08-29
Design Arena UI: 1336 Elo2026-08-30
Design Arena UI: 1336 Elo2026-08-31
Design Arena UI: 1335 Elo2026-09-01
Design Arena UI: 1339 Elo2026-09-02
Design Arena UI: 1335 Elo2026-09-03
Design Arena UI: 1334 Elo2026-09-04
Design Arena Web-app Agent: 1281 Elo2026-08-14
Design Arena Web-app Agent: 1279 Elo2026-08-18
Design Arena Web-app Agent: 1283 Elo2026-08-15
Design Arena Web-app Agent: 1279 Elo2026-08-19
Design Arena Web-app Agent: 1276 Elo2026-08-27
Design Arena Web-app Agent: 1279 Elo2026-08-20
Design Arena Web-app Agent: 1277 Elo2026-08-16
Design Arena Web-app Agent: 1281 Elo2026-08-17
Design Arena Web-app Agent: 1281 Elo2026-08-21
Design Arena Web-app Agent: 1282 Elo2026-08-22
Design Arena Web-app Agent: 1282 Elo2026-08-23
Design Arena Web-app Agent: 1277 Elo2026-08-28
Design Arena Web-app Agent: 1276 Elo2026-08-24
Design Arena Web-app Agent: 1277 Elo2026-08-25
Design Arena Web-app Agent: 1278 Elo2026-08-26
Design Arena Web-app Agent: 1277 Elo2026-08-29
Design Arena Web-app Agent: 1276 Elo2026-08-30
Design Arena Web-app Agent: 1276 Elo2026-08-31
Design Arena Web-app Agent: 1276 Elo2026-09-01
Design Arena Web-app Agent: 1276 Elo2026-09-02
Design Arena Web-app Agent: 1276 Elo2026-09-03
Design Arena Web-app Agent: 1276 Elo2026-09-04
Design Arena Website: 1325 Elo2026-08-14
Design Arena Website: 1317 Elo2026-08-18
Design Arena Website: 1308 Elo2026-08-15
Design Arena Website: 1317 Elo2026-08-19
Design Arena Website: 1309 Elo2026-08-16
Design Arena Website: 1317 Elo2026-08-20
Design Arena Website: 1321 Elo2026-08-27
Design Arena Website: 1314 Elo2026-08-17
Design Arena Website: 1323 Elo2026-08-21
Design Arena Website: 1323 Elo2026-08-22
Design Arena Website: 1323 Elo2026-08-23
Design Arena Website: 1322 Elo2026-08-24
Design Arena Website: 1320 Elo2026-08-28
Design Arena Website: 1322 Elo2026-08-25
Design Arena Website: 1322 Elo2026-08-26
Design Arena Website: 1319 Elo2026-08-29
Design Arena Website: 1319 Elo2026-08-30
Design Arena Website: 1318 Elo2026-08-31
Design Arena Website: 1318 Elo2026-09-01
Design Arena Website: 1316 Elo2026-09-02
Design Arena Website: 1313 Elo2026-09-03
Design Arena Website: 1312 Elo2026-09-04
Frontier-Bench^‡: 20.3%2026-08-12Grok Build, high effort
LiveBench Agentic Coding: 57.0%2026-06-25
LiveBench Coding: 76.8%2026-06-25
LiveBench Data Analysis: 73.9%2026-06-25
LiveBench Instruction Following: 71.9%2026-06-25
LiveBench Language: 83.7%2026-06-25
LiveBench Math: 92.6%2026-06-25
LiveBench Reasoning: 90.5%2026-06-25
LMArena Agent: 6.12026-08-27
LMArena Agent: 5.82026-08-31
LMArena Creative Writing: 1463 Elo2026-08-12
LMArena Creative Writing: 1448 Elo2026-08-21
LMArena Creative Writing: 1448 Elo2026-08-27
LMArena Creative Writing: 1449 Elo2026-09-01
LMArena Instruction Following: 1448 Elo2026-08-12
LMArena Instruction Following: 1445 Elo2026-08-21
LMArena Instruction Following: 1446 Elo2026-08-27
LMArena Instruction Following: 1446 Elo2026-09-01
LMArena Long Query: 1474 Elo2026-08-12
LMArena Long Query: 1468 Elo2026-08-21
LMArena Long Query: 1468 Elo2026-08-27
LMArena Long Query: 1467 Elo2026-09-01
LMArena Math: 1404 Elo2026-08-21
LMArena Math: 1402 Elo2026-08-27
LMArena Math: 1401 Elo2026-09-01
LMArena Text: 1461 Elo2026-08-21
LMArena Text: 1464 Elo2026-08-12
LMArena Text: 1461 Elo2026-08-27
LMArena Text: 1461 Elo2026-09-01
LMArena WebDev: 1618 Elo2026-08-12
LMArena WebDev: 1631 Elo2026-08-14
LMArena WebDev: 1629 Elo2026-08-21
LMArena WebDev: 1629 Elo2026-08-30
LMArena WebDev: 1629 Elo2026-09-01
Terminal-Bench 2.1^‡: 20.3%2026-08-12high 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 Agentic CodingEstablished evidence
82% 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 Autonomous AgentsEstablished evidence
71% of intended weighted task evidence across 4 independent sources. 7 of 7 configured evaluation feeds currently have results.
Best LLM for CodingEstablished evidence
68% of intended weighted task evidence across 4 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 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 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 Hermes AgentProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawProvisional evidence
51% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or SWE-rebench. 5 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 Local LLM for CodingProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-rebench. 5 of 5 configured evaluation feeds currently have results.
Best LLM for AI AgentsProvisional evidence
45% 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 Debugging & Code ReviewProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-bench Verified. 6 of 6 configured evaluation feeds currently have results.
Best LLM for Document SummarizationProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
Best LLM for SummarizationProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
Best LLM for JSON & Schema OutputProvisional evidence
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 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 Massive ContextProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 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 Image UnderstandingProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or VLMEvalKit tasks. 3 of 4 configured evaluation feeds currently have results.
Best LLM for RAG & Long ContextProvisional evidence
18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.
Best LLM for OCR & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Vision & DocumentsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.
Best LLM for Charts & DiagramsProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Document ParsingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.