Grok 4.3

x-ai/grok-4.3-20260430

xAI: Grok 4.3 is a model released by x‑ai on 2026‑04‑17. It accepts text, image, and file inputs, produces text output, and supports a context window of up to 1,000,000 tokens. The model includes tool and reasoning support, is not released with open weights, and is priced at $1.25 per M input tokens and $2.50 per M output tokens.

tool use
structured outputs
reasoning

At a glance

providerx-ai

releasedApr 17, 2026

context1M

input / M$1.25

Specifications

What the API gives you

Context window: 1M tokens
Max output: 900K tokens
Input price: $1.25 / 1M tokens
Output price: $2.50 / 1M tokens
Cache read: $0.20 / 1M tokens
Modalities: text, image, file → text
Knowledge cutoff: —
Released: Apr 17, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1218 Elo2026-07-28
Design Arena Coding: 1218 Elo2026-07-27
Design Arena Coding: 1217 Elo2026-07-30
Design Arena Coding: 1218 Elo2026-07-29
Design Arena Coding: 1217 Elo2026-07-31
Design Arena Coding: 1216 Elo2026-08-02
Design Arena Coding: 1215 Elo2026-08-05
Design Arena Coding: 1216 Elo2026-08-01
Design Arena Coding: 1214 Elo2026-08-09
Design Arena Coding: 1216 Elo2026-08-03
Design Arena Coding: 1215 Elo2026-08-04
Design Arena Coding: 1211 Elo2026-08-14
Design Arena Coding: 1215 Elo2026-08-06
Design Arena Coding: 1214 Elo2026-08-10
Design Arena Coding: 1215 Elo2026-08-07
Design Arena Coding: 1205 Elo2026-08-18
Design Arena Coding: 1214 Elo2026-08-08
Design Arena Coding: 1206 Elo2026-08-15
Design Arena Coding: 1214 Elo2026-08-11
Design Arena Coding: 1213 Elo2026-08-12
Design Arena Coding: 1212 Elo2026-08-13
Design Arena Coding: 1204 Elo2026-08-19
Design Arena Coding: 1210 Elo2026-08-27
Design Arena Coding: 1211 Elo2026-08-21
Design Arena Coding: 1204 Elo2026-08-20
Design Arena Coding: 1206 Elo2026-08-16
Design Arena Coding: 1202 Elo2026-09-05
Design Arena Coding: 1206 Elo2026-08-17
Design Arena Coding: 1211 Elo2026-08-22
Design Arena Coding: 1211 Elo2026-08-23
Design Arena Coding: 1210 Elo2026-08-28
Design Arena Coding: 1211 Elo2026-08-24
Design Arena Coding: 1211 Elo2026-08-25
Design Arena Coding: 1211 Elo2026-08-26
Design Arena Coding: 1202 Elo2026-09-06
Design Arena Coding: 1210 Elo2026-08-29
Design Arena Coding: 1209 Elo2026-08-30
Design Arena Coding: 1210 Elo2026-08-31
Design Arena Coding: 1210 Elo2026-09-01
Design Arena Coding: 1208 Elo2026-09-02
Design Arena Coding: 1206 Elo2026-09-03
Design Arena Coding: 1205 Elo2026-09-04
Design Arena Full-stack Agent: 1055 Elo2026-07-28
Design Arena Full-stack Agent: 1057 Elo2026-07-27
Design Arena Full-stack Agent: 1049 Elo2026-07-30
Design Arena Full-stack Agent: 1050 Elo2026-07-29
Design Arena Full-stack Agent: 1049 Elo2026-07-31
Design Arena Full-stack Agent: 1049 Elo2026-08-02
Design Arena Full-stack Agent: 1049 Elo2026-08-01
Design Arena Full-stack Agent: 1046 Elo2026-08-05
Design Arena Full-stack Agent: 1038 Elo2026-08-09
Design Arena Full-stack Agent: 1048 Elo2026-08-03
Design Arena Full-stack Agent: 1047 Elo2026-08-04
Design Arena Full-stack Agent: 1038 Elo2026-08-14
Design Arena Full-stack Agent: 1046 Elo2026-08-06
Design Arena Full-stack Agent: 1034 Elo2026-08-10
Design Arena Full-stack Agent: 1046 Elo2026-08-07
Design Arena Full-stack Agent: 1037 Elo2026-08-18
Design Arena Full-stack Agent: 1047 Elo2026-08-08
Design Arena Full-stack Agent: 1038 Elo2026-08-11
Design Arena Full-stack Agent: 1042 Elo2026-08-15
Design Arena Full-stack Agent: 1039 Elo2026-08-12
Design Arena Full-stack Agent: 1038 Elo2026-08-13
Design Arena Full-stack Agent: 1037 Elo2026-08-19
Design Arena Full-stack Agent: 1030 Elo2026-08-27
Design Arena Full-stack Agent: 1037 Elo2026-08-20
Design Arena Full-stack Agent: 1042 Elo2026-08-16
Design Arena Full-stack Agent: 1020 Elo2026-09-05
Design Arena Full-stack Agent: 1041 Elo2026-08-17
Design Arena Full-stack Agent: 1041 Elo2026-08-21
Design Arena Full-stack Agent: 1040 Elo2026-08-22
Design Arena Full-stack Agent: 1040 Elo2026-08-23
Design Arena Full-stack Agent: 1029 Elo2026-08-28
Design Arena Full-stack Agent: 1028 Elo2026-08-24
Design Arena Full-stack Agent: 1031 Elo2026-08-25
Design Arena Full-stack Agent: 1031 Elo2026-08-26
Design Arena Full-stack Agent: 1017 Elo2026-09-06
Design Arena Full-stack Agent: 1030 Elo2026-08-29
Design Arena Full-stack Agent: 1030 Elo2026-08-30
Design Arena Full-stack Agent: 1029 Elo2026-08-31
Design Arena Full-stack Agent: 1030 Elo2026-09-01
Design Arena Full-stack Agent: 1030 Elo2026-09-02
Design Arena Full-stack Agent: 1030 Elo2026-09-03
Design Arena Full-stack Agent: 1030 Elo2026-09-04
Design Arena UI: 1230 Elo2026-07-28
Design Arena UI: 1230 Elo2026-07-27
Design Arena UI: 1228 Elo2026-07-30
Design Arena UI: 1229 Elo2026-07-29
Design Arena UI: 1227 Elo2026-07-31
Design Arena UI: 1228 Elo2026-08-02
Design Arena UI: 1228 Elo2026-08-01
Design Arena UI: 1227 Elo2026-08-05
Design Arena UI: 1225 Elo2026-08-09
Design Arena UI: 1228 Elo2026-08-03
Design Arena UI: 1227 Elo2026-08-04
Design Arena UI: 1223 Elo2026-08-14
Design Arena UI: 1227 Elo2026-08-06
Design Arena UI: 1227 Elo2026-08-07
Design Arena UI: 1225 Elo2026-08-10
Design Arena UI: 1225 Elo2026-08-08
Design Arena UI: 1221 Elo2026-08-18
Design Arena UI: 1226 Elo2026-08-11
Design Arena UI: 1222 Elo2026-08-15
Design Arena UI: 1226 Elo2026-08-12
Design Arena UI: 1226 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: 1218 Elo2026-08-27
Design Arena UI: 1221 Elo2026-08-17
Design Arena UI: 1214 Elo2026-09-05
Design Arena UI: 1219 Elo2026-08-21
Design Arena UI: 1219 Elo2026-08-22
Design Arena UI: 1220 Elo2026-08-23
Design Arena UI: 1220 Elo2026-08-24
Design Arena UI: 1218 Elo2026-08-28
Design Arena UI: 1220 Elo2026-08-25
Design Arena UI: 1220 Elo2026-08-26
Design Arena UI: 1215 Elo2026-09-06
Design Arena UI: 1218 Elo2026-08-29
Design Arena UI: 1218 Elo2026-08-30
Design Arena UI: 1218 Elo2026-08-31
Design Arena UI: 1218 Elo2026-09-01
Design Arena UI: 1217 Elo2026-09-02
Design Arena UI: 1215 Elo2026-09-03
Design Arena UI: 1214 Elo2026-09-04
Design Arena Web-app Agent: 1175 Elo2026-07-28
Design Arena Web-app Agent: 1175 Elo2026-07-27
Design Arena Web-app Agent: 1174 Elo2026-07-30
Design Arena Web-app Agent: 1174 Elo2026-07-29
Design Arena Web-app Agent: 1174 Elo2026-07-31
Design Arena Web-app Agent: 1173 Elo2026-08-02
Design Arena Web-app Agent: 1174 Elo2026-08-01
Design Arena Web-app Agent: 1177 Elo2026-08-05
Design Arena Web-app Agent: 1171 Elo2026-08-09
Design Arena Web-app Agent: 1173 Elo2026-08-03
Design Arena Web-app Agent: 1173 Elo2026-08-04
Design Arena Web-app Agent: 1165 Elo2026-08-14
Design Arena Web-app Agent: 1177 Elo2026-08-06
Design Arena Web-app Agent: 1168 Elo2026-08-10
Design Arena Web-app Agent: 1177 Elo2026-08-07
Design Arena Web-app Agent: 1168 Elo2026-08-18
Design Arena Web-app Agent: 1178 Elo2026-08-08
Design Arena Web-app Agent: 1167 Elo2026-08-11
Design Arena Web-app Agent: 1170 Elo2026-08-15
Design Arena Web-app Agent: 1167 Elo2026-08-12
Design Arena Web-app Agent: 1167 Elo2026-08-13
Design Arena Web-app Agent: 1167 Elo2026-08-19
Design Arena Web-app Agent: 1160 Elo2026-08-27
Design Arena Web-app Agent: 1167 Elo2026-08-20
Design Arena Web-app Agent: 1171 Elo2026-08-16
Design Arena Web-app Agent: 1159 Elo2026-09-05
Design Arena Web-app Agent: 1171 Elo2026-08-17
Design Arena Web-app Agent: 1166 Elo2026-08-21
Design Arena Web-app Agent: 1166 Elo2026-08-22
Design Arena Web-app Agent: 1166 Elo2026-08-23
Design Arena Web-app Agent: 1161 Elo2026-08-28
Design Arena Web-app Agent: 1161 Elo2026-08-24
Design Arena Web-app Agent: 1162 Elo2026-08-25
Design Arena Web-app Agent: 1162 Elo2026-08-26
Design Arena Web-app Agent: 1160 Elo2026-09-06
Design Arena Web-app Agent: 1161 Elo2026-08-29
Design Arena Web-app Agent: 1160 Elo2026-08-30
Design Arena Web-app Agent: 1160 Elo2026-08-31
Design Arena Web-app Agent: 1160 Elo2026-09-01
Design Arena Web-app Agent: 1159 Elo2026-09-02
Design Arena Web-app Agent: 1159 Elo2026-09-03
Design Arena Web-app Agent: 1159 Elo2026-09-04
Design Arena Website: 1219 Elo2026-07-28
Design Arena Website: 1217 Elo2026-07-30
Design Arena Website: 1219 Elo2026-07-27
Design Arena Website: 1217 Elo2026-07-29
Design Arena Website: 1216 Elo2026-07-31
Design Arena Website: 1215 Elo2026-08-02
Design Arena Website: 1215 Elo2026-08-01
Design Arena Website: 1215 Elo2026-08-05
Design Arena Website: 1215 Elo2026-08-03
Design Arena Website: 1214 Elo2026-08-09
Design Arena Website: 1215 Elo2026-08-04
Design Arena Website: 1212 Elo2026-08-14
Design Arena Website: 1215 Elo2026-08-06
Design Arena Website: 1215 Elo2026-08-07
Design Arena Website: 1214 Elo2026-08-10
Design Arena Website: 1214 Elo2026-08-08
Design Arena Website: 1204 Elo2026-08-18
Design Arena Website: 1214 Elo2026-08-11
Design Arena Website: 1204 Elo2026-08-15
Design Arena Website: 1213 Elo2026-08-12
Design Arena Website: 1212 Elo2026-08-13
Design Arena Website: 1204 Elo2026-08-19
Design Arena Website: 1204 Elo2026-08-16
Design Arena Website: 1204 Elo2026-08-20
Design Arena Website: 1212 Elo2026-08-27
Design Arena Website: 1204 Elo2026-08-17
Design Arena Website: 1208 Elo2026-09-05
Design Arena Website: 1212 Elo2026-08-21
Design Arena Website: 1212 Elo2026-08-22
Design Arena Website: 1213 Elo2026-08-23
Design Arena Website: 1213 Elo2026-08-24
Design Arena Website: 1212 Elo2026-08-28
Design Arena Website: 1213 Elo2026-08-25
Design Arena Website: 1213 Elo2026-08-26
Design Arena Website: 1206 Elo2026-09-06
Design Arena Website: 1211 Elo2026-08-29
Design Arena Website: 1212 Elo2026-08-30
Design Arena Website: 1212 Elo2026-08-31
Design Arena Website: 1213 Elo2026-09-01
Design Arena Website: 1211 Elo2026-09-02
Design Arena Website: 1209 Elo2026-09-03
Design Arena Website: 1208 Elo2026-09-04
LiveBench Agentic Coding: 18.5%2026-06-25
LiveBench Coding: 69.9%2026-06-25
LiveBench Data Analysis: 55.8%2026-06-25
LiveBench Instruction Following: 62.8%2026-06-25
LiveBench Language: 73.6%2026-06-25
LiveBench Math: 84.3%2026-06-25
LiveBench Reasoning: 70.8%2026-06-25
LMArena Agent: -8.32026-07-13
LMArena Agent: -7.82026-07-20
LMArena Agent: -7.92026-07-27
LMArena Agent: -8.22026-07-21
LMArena Agent: -82026-07-28
LMArena Agent: -8.12026-08-03
LMArena Agent: -8.42026-08-12
LMArena Agent: -8.52026-08-13
LMArena Agent: -8.32026-08-06
LMArena Agent: -8.52026-08-11
LMArena Agent: -9.92026-08-24
LMArena Agent: -10.82026-08-31
LMArena Agent: -11.62026-09-05
LMArena Agent: -10.22026-08-27
LMArena Creative Writing: 1387 Elo2026-07-21
LMArena Creative Writing: 1388 Elo2026-07-27
LMArena Creative Writing: 1388 Elo2026-07-30
LMArena Creative Writing: 1387 Elo2026-08-02
LMArena Creative Writing: 1387 Elo2026-08-03
LMArena Creative Writing: 1387 Elo2026-08-06
LMArena Creative Writing: 1386 Elo2026-08-12
LMArena Creative Writing: 1386 Elo2026-08-21
LMArena Creative Writing: 1384 Elo2026-09-02
LMArena Creative Writing: 1384 Elo2026-08-27
LMArena Creative Writing: 1384 Elo2026-09-01
LMArena Instruction Following: 1368 Elo2026-07-21
LMArena Instruction Following: 1368 Elo2026-07-27
LMArena Instruction Following: 1368 Elo2026-07-30
LMArena Instruction Following: 1368 Elo2026-08-02
LMArena Instruction Following: 1368 Elo2026-08-03
LMArena Instruction Following: 1367 Elo2026-08-06
LMArena Instruction Following: 1367 Elo2026-08-12
LMArena Instruction Following: 1367 Elo2026-08-21
LMArena Instruction Following: 1367 Elo2026-09-02
LMArena Instruction Following: 1366 Elo2026-08-27
LMArena Instruction Following: 1366 Elo2026-09-01
LMArena Long Query: 1398 Elo2026-07-21
LMArena Long Query: 1398 Elo2026-07-27
LMArena Long Query: 1398 Elo2026-07-30
LMArena Long Query: 1398 Elo2026-08-02
LMArena Long Query: 1397 Elo2026-08-06
LMArena Long Query: 1398 Elo2026-08-03
LMArena Long Query: 1396 Elo2026-08-12
LMArena Long Query: 1396 Elo2026-08-21
LMArena Long Query: 1395 Elo2026-09-02
LMArena Long Query: 1395 Elo2026-08-27
LMArena Long Query: 1395 Elo2026-09-01
LMArena Math: 1390 Elo2026-07-21
LMArena Math: 1391 Elo2026-07-27
LMArena Math: 1391 Elo2026-07-30
LMArena Math: 1389 Elo2026-08-02
LMArena Math: 1389 Elo2026-08-03
LMArena Math: 1389 Elo2026-08-06
LMArena Math: 1388 Elo2026-08-12
LMArena Math: 1389 Elo2026-08-21
LMArena Math: 1389 Elo2026-09-01
LMArena Math: 1389 Elo2026-08-27
LMArena Text: 1442 Elo2026-07-21
LMArena Text: 1442 Elo2026-08-02
LMArena Text: 1443 Elo2026-07-27
LMArena Text: 1443 Elo2026-07-30
LMArena Text: 1442 Elo2026-08-10
LMArena Text: 1442 Elo2026-08-03
LMArena Text: 1442 Elo2026-08-06
LMArena Text: 1442 Elo2026-08-21
LMArena Text: 1441 Elo2026-08-12
LMArena Text: 1443 Elo2026-09-01
LMArena Text: 1442 Elo2026-08-27
LMArena Text: 1443 Elo2026-09-02
LMArena Vision: 1235 Elo2026-07-12
LMArena Vision: 1246 Elo2026-07-21
LMArena Vision: 1245 Elo2026-07-26
LMArena Vision: 1245 Elo2026-07-30
LMArena Vision: 1244 Elo2026-08-02
LMArena Vision: 1244 Elo2026-08-06
LMArena Vision: 1241 Elo2026-08-21
LMArena Vision: 1241 Elo2026-08-27
LMArena WebDev: 1360 Elo2026-07-16
LMArena WebDev: 1360 Elo2026-07-21
LMArena WebDev: 1361 Elo2026-07-20
LMArena WebDev: 1358 Elo2026-07-27
LMArena WebDev: 1359 Elo2026-07-24
LMArena WebDev: 1358 Elo2026-07-28
LMArena WebDev: 1358 Elo2026-07-30
LMArena WebDev: 1357 Elo2026-08-01
LMArena WebDev: 1357 Elo2026-07-31
LMArena WebDev: 1357 Elo2026-08-06
LMArena WebDev: 1357 Elo2026-08-02
LMArena WebDev: 1355 Elo2026-08-12
LMArena WebDev: 1355 Elo2026-08-10
LMArena WebDev: 1354 Elo2026-08-14
LMArena WebDev: 1356 Elo2026-09-01
LMArena WebDev: 1356 Elo2026-09-05
LMArena WebDev: 1357 Elo2026-08-21
LMArena WebDev: 1356 Elo2026-08-30

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 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 Code CompletionEstablished evidence
81% of intended weighted task evidence across 2 independent sources. 4 of 4 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 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 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 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 RAG & Long ContextProvisional evidence
29% 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 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 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.

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.