Muse Spark 1.2

meta/muse-spark-1.2-20260805

Meta: Muse Spark 1.2 is a multimodal AI model from Meta that accepts text, image, video, file, and audio inputs to generate text outputs. It has a context length of 1,048,576 tokens, supports tools and reasoning, and is not open weights.

tool use
structured outputs
reasoning

At a glance

providermeta

releasedAug 5, 2026

context1.0M

input / M$1.25

Specifications

What the API gives you

Context window: 1.0M tokens
Max output: 944K tokens
Input price: $1.25 / 1M tokens
Output price: $4.25 / 1M tokens
Cache read: $0.15 / 1M tokens
Modalities: text, image, video, file, audio → text
Knowledge cutoff: —
Released: Aug 5, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1350 Elo2026-08-09
Design Arena Coding: 1347 Elo2026-08-14
Design Arena Coding: 1353 Elo2026-08-10
Design Arena Coding: 1340 Elo2026-08-18
Design Arena Coding: 1343 Elo2026-08-21
Design Arena Coding: 1341 Elo2026-08-15
Design Arena Coding: 1353 Elo2026-08-11
Design Arena Coding: 1349 Elo2026-08-12
Design Arena Coding: 1338 Elo2026-08-19
Design Arena Coding: 1347 Elo2026-08-13
Design Arena Coding: 1341 Elo2026-08-27
Design Arena Coding: 1331 Elo2026-09-05
Design Arena Coding: 1338 Elo2026-08-20
Design Arena Coding: 1340 Elo2026-08-16
Design Arena Coding: 1340 Elo2026-08-17
Design Arena Coding: 1343 Elo2026-08-22
Design Arena Coding: 1344 Elo2026-08-23
Design Arena Coding: 1340 Elo2026-08-28
Design Arena Coding: 1344 Elo2026-08-24
Design Arena Coding: 1327 Elo2026-09-16
Design Arena Coding: 1343 Elo2026-08-25
Design Arena Coding: 1343 Elo2026-08-26
Design Arena Coding: 1330 Elo2026-09-06
Design Arena Coding: 1341 Elo2026-08-29
Design Arena Coding: 1341 Elo2026-08-30
Design Arena Coding: 1330 Elo2026-09-07
Design Arena Coding: 1341 Elo2026-08-31
Design Arena Coding: 1341 Elo2026-09-01
Design Arena Coding: 1340 Elo2026-09-02
Design Arena Coding: 1327 Elo2026-09-17
Design Arena Coding: 1331 Elo2026-09-08
Design Arena Coding: 1336 Elo2026-09-03
Design Arena Coding: 1335 Elo2026-09-04
Design Arena Coding: 1327 Elo2026-09-18
Design Arena Coding: 1328 Elo2026-09-09
Design Arena Coding: 1328 Elo2026-09-10
Design Arena Coding: 1327 Elo2026-09-11
Design Arena Coding: 1326 Elo2026-09-12
Design Arena Coding: 1327 Elo2026-09-19
Design Arena Coding: 1326 Elo2026-09-13
Design Arena Coding: 1326 Elo2026-09-14
Design Arena Coding: 1327 Elo2026-09-15
Design Arena Coding: 1326 Elo2026-09-20
Design Arena Full-stack Agent: 1244 Elo2026-08-14
Design Arena Full-stack Agent: 1242 Elo2026-08-18
Design Arena Full-stack Agent: 1246 Elo2026-08-15
Design Arena Full-stack Agent: 1259 Elo2026-08-11
Design Arena Full-stack Agent: 1238 Elo2026-08-12
Design Arena Full-stack Agent: 1248 Elo2026-08-13
Design Arena Full-stack Agent: 1241 Elo2026-08-19
Design Arena Full-stack Agent: 1239 Elo2026-08-27
Design Arena Full-stack Agent: 1241 Elo2026-08-20
Design Arena Full-stack Agent: 1247 Elo2026-08-16
Design Arena Full-stack Agent: 1226 Elo2026-09-05
Design Arena Full-stack Agent: 1247 Elo2026-08-17
Design Arena Full-stack Agent: 1247 Elo2026-08-21
Design Arena Full-stack Agent: 1246 Elo2026-08-22
Design Arena Full-stack Agent: 1246 Elo2026-08-23
Design Arena Full-stack Agent: 1237 Elo2026-08-28
Design Arena Full-stack Agent: 1235 Elo2026-08-24
Design Arena Full-stack Agent: 1239 Elo2026-08-25
Design Arena Full-stack Agent: 1221 Elo2026-09-16
Design Arena Full-stack Agent: 1239 Elo2026-08-26
Design Arena Full-stack Agent: 1223 Elo2026-09-06
Design Arena Full-stack Agent: 1238 Elo2026-08-29
Design Arena Full-stack Agent: 1236 Elo2026-08-30
Design Arena Full-stack Agent: 1220 Elo2026-09-07
Design Arena Full-stack Agent: 1236 Elo2026-08-31
Design Arena Full-stack Agent: 1236 Elo2026-09-01
Design Arena Full-stack Agent: 1236 Elo2026-09-02
Design Arena Full-stack Agent: 1236 Elo2026-09-03
Design Arena Full-stack Agent: 1221 Elo2026-09-08
Design Arena Full-stack Agent: 1221 Elo2026-09-17
Design Arena Full-stack Agent: 1236 Elo2026-09-04
Design Arena Full-stack Agent: 1219 Elo2026-09-09
Design Arena Full-stack Agent: 1221 Elo2026-09-18
Design Arena Full-stack Agent: 1222 Elo2026-09-10
Design Arena Full-stack Agent: 1222 Elo2026-09-11
Design Arena Full-stack Agent: 1223 Elo2026-09-12
Design Arena Full-stack Agent: 1220 Elo2026-09-19
Design Arena Full-stack Agent: 1224 Elo2026-09-13
Design Arena Full-stack Agent: 1224 Elo2026-09-14
Design Arena Full-stack Agent: 1221 Elo2026-09-15
Design Arena Full-stack Agent: 1219 Elo2026-09-20
Design Arena UI: 1371 Elo2026-08-09
Design Arena UI: 1349 Elo2026-08-14
Design Arena UI: 1351 Elo2026-08-10
Design Arena UI: 1343 Elo2026-08-18
Design Arena UI: 1353 Elo2026-08-11
Design Arena UI: 1345 Elo2026-08-15
Design Arena UI: 1348 Elo2026-08-12
Design Arena UI: 1343 Elo2026-08-13
Design Arena UI: 1343 Elo2026-08-19
Design Arena UI: 1349 Elo2026-08-27
Design Arena UI: 1345 Elo2026-08-16
Design Arena UI: 1343 Elo2026-08-20
Design Arena UI: 1344 Elo2026-08-17
Design Arena UI: 1351 Elo2026-09-05
Design Arena UI: 1344 Elo2026-08-21
Design Arena UI: 1346 Elo2026-08-22
Design Arena UI: 1349 Elo2026-08-23
Design Arena UI: 1348 Elo2026-08-28
Design Arena UI: 1353 Elo2026-08-24
Design Arena UI: 1350 Elo2026-08-25
Design Arena UI: 1351 Elo2026-08-26
Design Arena UI: 1352 Elo2026-09-06
Design Arena UI: 1326 Elo2026-09-16
Design Arena UI: 1345 Elo2026-08-29
Design Arena UI: 1345 Elo2026-08-30
Design Arena UI: 1349 Elo2026-09-07
Design Arena UI: 1348 Elo2026-08-31
Design Arena UI: 1350 Elo2026-09-01
Design Arena UI: 1351 Elo2026-09-02
Design Arena UI: 1351 Elo2026-09-03
Design Arena UI: 1338 Elo2026-09-08
Design Arena UI: 1327 Elo2026-09-17
Design Arena UI: 1349 Elo2026-09-04
Design Arena UI: 1333 Elo2026-09-09
Design Arena UI: 1327 Elo2026-09-18
Design Arena UI: 1333 Elo2026-09-10
Design Arena UI: 1334 Elo2026-09-11
Design Arena UI: 1333 Elo2026-09-12
Design Arena UI: 1330 Elo2026-09-19
Design Arena UI: 1325 Elo2026-09-13
Design Arena UI: 1328 Elo2026-09-14
Design Arena UI: 1327 Elo2026-09-15
Design Arena UI: 1330 Elo2026-09-20
Design Arena Web-app Agent: 1261 Elo2026-08-14
Design Arena Web-app Agent: 1262 Elo2026-08-18
Design Arena Web-app Agent: 1279 Elo2026-08-11
Design Arena Web-app Agent: 1261 Elo2026-08-15
Design Arena Web-app Agent: 1264 Elo2026-08-12
Design Arena Web-app Agent: 1260 Elo2026-08-13
Design Arena Web-app Agent: 1262 Elo2026-08-19
Design Arena Web-app Agent: 1257 Elo2026-08-27
Design Arena Web-app Agent: 1262 Elo2026-08-20
Design Arena Web-app Agent: 1264 Elo2026-08-16
Design Arena Web-app Agent: 1256 Elo2026-09-05
Design Arena Web-app Agent: 1265 Elo2026-08-17
Design Arena Web-app Agent: 1261 Elo2026-08-21
Design Arena Web-app Agent: 1262 Elo2026-08-22
Design Arena Web-app Agent: 1264 Elo2026-08-23
Design Arena Web-app Agent: 1259 Elo2026-08-28
Design Arena Web-app Agent: 1258 Elo2026-08-24
Design Arena Web-app Agent: 1258 Elo2026-08-25
Design Arena Web-app Agent: 1256 Elo2026-08-26
Design Arena Web-app Agent: 1241 Elo2026-09-16
Design Arena Web-app Agent: 1256 Elo2026-09-06
Design Arena Web-app Agent: 1259 Elo2026-08-29
Design Arena Web-app Agent: 1256 Elo2026-08-30
Design Arena Web-app Agent: 1252 Elo2026-09-07
Design Arena Web-app Agent: 1257 Elo2026-08-31
Design Arena Web-app Agent: 1256 Elo2026-09-01
Design Arena Web-app Agent: 1256 Elo2026-09-02
Design Arena Web-app Agent: 1256 Elo2026-09-03
Design Arena Web-app Agent: 1253 Elo2026-09-08
Design Arena Web-app Agent: 1240 Elo2026-09-17
Design Arena Web-app Agent: 1256 Elo2026-09-04
Design Arena Web-app Agent: 1247 Elo2026-09-09
Design Arena Web-app Agent: 1240 Elo2026-09-18
Design Arena Web-app Agent: 1247 Elo2026-09-10
Design Arena Web-app Agent: 1246 Elo2026-09-11
Design Arena Web-app Agent: 1244 Elo2026-09-12
Design Arena Web-app Agent: 1240 Elo2026-09-19
Design Arena Web-app Agent: 1243 Elo2026-09-13
Design Arena Web-app Agent: 1243 Elo2026-09-14
Design Arena Web-app Agent: 1239 Elo2026-09-15
Design Arena Web-app Agent: 1240 Elo2026-09-20
Design Arena Website: 1332 Elo2026-08-09
Design Arena Website: 1338 Elo2026-08-14
Design Arena Website: 1340 Elo2026-08-10
Design Arena Website: 1333 Elo2026-08-08
Design Arena Website: 1329 Elo2026-08-18
Design Arena Website: 1339 Elo2026-08-11
Design Arena Website: 1329 Elo2026-08-15
Design Arena Website: 1336 Elo2026-08-12
Design Arena Website: 1336 Elo2026-08-13
Design Arena Website: 1329 Elo2026-08-19
Design Arena Website: 1328 Elo2026-08-16
Design Arena Website: 1329 Elo2026-08-20
Design Arena Website: 1332 Elo2026-08-27
Design Arena Website: 1329 Elo2026-08-17
Design Arena Website: 1326 Elo2026-09-05
Design Arena Website: 1335 Elo2026-08-21
Design Arena Website: 1336 Elo2026-08-22
Design Arena Website: 1335 Elo2026-08-23
Design Arena Website: 1335 Elo2026-08-24
Design Arena Website: 1332 Elo2026-08-28
Design Arena Website: 1335 Elo2026-08-25
Design Arena Website: 1334 Elo2026-08-26
Design Arena Website: 1324 Elo2026-09-06
Design Arena Website: 1322 Elo2026-09-16
Design Arena Website: 1332 Elo2026-08-29
Design Arena Website: 1333 Elo2026-08-30
Design Arena Website: 1333 Elo2026-08-31
Design Arena Website: 1324 Elo2026-09-07
Design Arena Website: 1333 Elo2026-09-01
Design Arena Website: 1332 Elo2026-09-02
Design Arena Website: 1329 Elo2026-09-03
Design Arena Website: 1325 Elo2026-09-08
Design Arena Website: 1322 Elo2026-09-17
Design Arena Website: 1327 Elo2026-09-04
Design Arena Website: 1321 Elo2026-09-09
Design Arena Website: 1321 Elo2026-09-18
Design Arena Website: 1322 Elo2026-09-10
Design Arena Website: 1322 Elo2026-09-11
Design Arena Website: 1321 Elo2026-09-12
Design Arena Website: 1321 Elo2026-09-19
Design Arena Website: 1323 Elo2026-09-13
Design Arena Website: 1321 Elo2026-09-14
Design Arena Website: 1321 Elo2026-09-15
Design Arena Website: 1321 Elo2026-09-20
LiveBench Agentic Coding: 57.6%2026-06-25
LiveBench Coding: 77.5%2026-06-25
LiveBench Data Analysis: 76.5%2026-06-25
LiveBench Instruction Following: 74.3%2026-06-25
LiveBench Language: 78.6%2026-06-25
LiveBench Math: 91.2%2026-06-25
LiveBench Reasoning: 90%2026-06-25
LMArena Agent: 1.62026-08-24
LMArena Agent: 12026-08-31
LMArena Agent: 0.52026-09-05
LMArena Agent: 1.32026-08-27
LMArena Agent: -1.82026-09-15
LMArena Agent: -1.82026-09-10
LMArena Agent: -1.62026-09-14
LMArena Creative Writing: 1453 Elo2026-08-06
LMArena Creative Writing: 1449 Elo2026-08-12
LMArena Creative Writing: 1446 Elo2026-08-21
LMArena Creative Writing: 1445 Elo2026-08-27
LMArena Creative Writing: 1444 Elo2026-09-01
LMArena Creative Writing: 1446 Elo2026-09-02
LMArena Creative Writing: 1448 Elo2026-09-11
LMArena Creative Writing: 1448 Elo2026-09-13
LMArena Instruction Following: 1460 Elo2026-08-06
LMArena Instruction Following: 1469 Elo2026-08-12
LMArena Instruction Following: 1468 Elo2026-08-21
LMArena Instruction Following: 1469 Elo2026-08-27
LMArena Instruction Following: 1471 Elo2026-09-13
LMArena Instruction Following: 1469 Elo2026-09-01
LMArena Instruction Following: 1469 Elo2026-09-02
LMArena Instruction Following: 1471 Elo2026-09-11
LMArena Long Query: 1478 Elo2026-08-06
LMArena Long Query: 1485 Elo2026-08-12
LMArena Long Query: 1484 Elo2026-08-21
LMArena Long Query: 1485 Elo2026-08-27
LMArena Long Query: 1486 Elo2026-09-01
LMArena Long Query: 1486 Elo2026-09-02
LMArena Long Query: 1487 Elo2026-09-11
LMArena Long Query: 1487 Elo2026-09-13
LMArena Text: 1498 Elo2026-08-06
LMArena Text: 1499 Elo2026-08-12
LMArena Text: 1499 Elo2026-08-10
LMArena Text: 1498 Elo2026-08-21
LMArena Text: 1499 Elo2026-09-01
LMArena Text: 1499 Elo2026-09-02
LMArena Text: 1498 Elo2026-08-27
LMArena Text: 1500 Elo2026-09-13
LMArena Text: 1499 Elo2026-09-11
LMArena Vision: 1290 Elo2026-08-06
LMArena Vision: 1292 Elo2026-08-21
LMArena Vision: 1292 Elo2026-09-13
LMArena Vision: 1292 Elo2026-08-27
LMArena WebDev: 1544 Elo2026-08-06
LMArena WebDev: 1535 Elo2026-08-12
LMArena WebDev: 1535 Elo2026-08-10
LMArena WebDev: 1535 Elo2026-08-14
LMArena WebDev: 1534 Elo2026-09-01
LMArena WebDev: 1534 Elo2026-09-05
LMArena WebDev: 1534 Elo2026-08-21
LMArena WebDev: 1534 Elo2026-08-30
LMArena WebDev: 1534 Elo2026-09-11

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.

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 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 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 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 Logic & Problem SolvingEstablished evidence
85% 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 Competition MathEstablished evidence
75% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Math & ReasoningEstablished evidence
75% of intended weighted task evidence across 2 independent sources. 5 of 5 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 CodingProvisional evidence
58% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Aider Polyglot or SWE-bench Verified. 8 of 8 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 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 Agentic CodingProvisional evidence
46% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Frontier-Bench or SWE-rebench. 8 of 8 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 Hermes AgentProvisional evidence
33% of intended weighted task evidence across 1 independent source; 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
33% of intended weighted task evidence across 1 independent source; 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
33% of intended weighted task evidence across 1 independent source; 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
33% of intended weighted task evidence across 1 independent source; 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 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 AI AgentsProvisional evidence
27% of intended weighted task evidence across 2 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 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 Autonomous AgentsProvisional evidence
25% of intended weighted task evidence across 2 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 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 OCR & DocumentsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Vision & DocumentsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Charts & DiagramsProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Document ParsingProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 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 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

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