Kimi K2.7 Code

moonshotai/kimi-k2.7-code-20260612

MoonshotAI: Kimi K2.7 Code is a model from moonshotai that accepts text and image inputs and provides text outputs. It features a 262,144 token context window, supports tool use and reasoning, and is released as open weights.

tool use
structured outputs
reasoning
open-weight

At a glance

providermoonshotai

releasedJun 12, 2026

context262K

input / M$0.66

Specifications

What the API gives you

Context window: 262K tokens
Max output: 236K tokens
Input price: $0.66 / 1M tokens
Output price: $3.40 / 1M tokens
Cache read: $0.18 / 1M tokens
Modalities: text, image → text
Knowledge cutoff: —
Released: Jun 12, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1290 Elo2026-07-28
Design Arena Coding: 1290 Elo2026-07-27
Design Arena Coding: 1291 Elo2026-07-30
Design Arena Coding: 1290 Elo2026-07-29
Design Arena Coding: 1291 Elo2026-07-31
Design Arena Coding: 1290 Elo2026-08-02
Design Arena Coding: 1289 Elo2026-08-05
Design Arena Coding: 1291 Elo2026-08-01
Design Arena Coding: 1287 Elo2026-08-09
Design Arena Coding: 1290 Elo2026-08-03
Design Arena Coding: 1290 Elo2026-08-04
Design Arena Coding: 1284 Elo2026-08-14
Design Arena Coding: 1289 Elo2026-08-06
Design Arena Coding: 1287 Elo2026-08-10
Design Arena Coding: 1289 Elo2026-08-07
Design Arena Coding: 1277 Elo2026-08-18
Design Arena Coding: 1287 Elo2026-08-08
Design Arena Coding: 1279 Elo2026-08-15
Design Arena Coding: 1287 Elo2026-08-11
Design Arena Coding: 1286 Elo2026-08-12
Design Arena Coding: 1283 Elo2026-08-21
Design Arena Coding: 1284 Elo2026-08-13
Design Arena Coding: 1276 Elo2026-08-19
Design Arena Coding: 1282 Elo2026-08-27
Design Arena Coding: 1276 Elo2026-08-20
Design Arena Coding: 1278 Elo2026-08-16
Design Arena Coding: 1272 Elo2026-09-05
Design Arena Coding: 1278 Elo2026-08-17
Design Arena Coding: 1283 Elo2026-08-22
Design Arena Coding: 1283 Elo2026-08-23
Design Arena Coding: 1281 Elo2026-08-28
Design Arena Coding: 1283 Elo2026-08-24
Design Arena Coding: 1283 Elo2026-08-25
Design Arena Coding: 1283 Elo2026-08-26
Design Arena Coding: 1272 Elo2026-09-06
Design Arena Coding: 1281 Elo2026-08-29
Design Arena Coding: 1281 Elo2026-08-30
Design Arena Coding: 1281 Elo2026-08-31
Design Arena Coding: 1280 Elo2026-09-01
Design Arena Coding: 1279 Elo2026-09-02
Design Arena Coding: 1277 Elo2026-09-03
Design Arena Coding: 1275 Elo2026-09-04
Design Arena Full-stack Agent: 1223 Elo2026-07-28
Design Arena Full-stack Agent: 1224 Elo2026-07-27
Design Arena Full-stack Agent: 1216 Elo2026-07-30
Design Arena Full-stack Agent: 1217 Elo2026-07-29
Design Arena Full-stack Agent: 1217 Elo2026-07-31
Design Arena Full-stack Agent: 1220 Elo2026-08-02
Design Arena Full-stack Agent: 1220 Elo2026-08-05
Design Arena Full-stack Agent: 1219 Elo2026-08-01
Design Arena Full-stack Agent: 1209 Elo2026-08-09
Design Arena Full-stack Agent: 1220 Elo2026-08-03
Design Arena Full-stack Agent: 1220 Elo2026-08-04
Design Arena Full-stack Agent: 1209 Elo2026-08-14
Design Arena Full-stack Agent: 1219 Elo2026-08-06
Design Arena Full-stack Agent: 1205 Elo2026-08-10
Design Arena Full-stack Agent: 1219 Elo2026-08-07
Design Arena Full-stack Agent: 1206 Elo2026-08-18
Design Arena Full-stack Agent: 1218 Elo2026-08-08
Design Arena Full-stack Agent: 1212 Elo2026-08-15
Design Arena Full-stack Agent: 1209 Elo2026-08-11
Design Arena Full-stack Agent: 1210 Elo2026-08-12
Design Arena Full-stack Agent: 1208 Elo2026-08-13
Design Arena Full-stack Agent: 1206 Elo2026-08-19
Design Arena Full-stack Agent: 1198 Elo2026-08-27
Design Arena Full-stack Agent: 1206 Elo2026-08-20
Design Arena Full-stack Agent: 1212 Elo2026-08-16
Design Arena Full-stack Agent: 1188 Elo2026-09-05
Design Arena Full-stack Agent: 1211 Elo2026-08-17
Design Arena Full-stack Agent: 1210 Elo2026-08-21
Design Arena Full-stack Agent: 1210 Elo2026-08-22
Design Arena Full-stack Agent: 1209 Elo2026-08-23
Design Arena Full-stack Agent: 1198 Elo2026-08-28
Design Arena Full-stack Agent: 1196 Elo2026-08-24
Design Arena Full-stack Agent: 1199 Elo2026-08-25
Design Arena Full-stack Agent: 1199 Elo2026-08-26
Design Arena Full-stack Agent: 1186 Elo2026-09-06
Design Arena Full-stack Agent: 1198 Elo2026-08-29
Design Arena Full-stack Agent: 1199 Elo2026-08-30
Design Arena Full-stack Agent: 1198 Elo2026-08-31
Design Arena Full-stack Agent: 1199 Elo2026-09-01
Design Arena Full-stack Agent: 1199 Elo2026-09-02
Design Arena Full-stack Agent: 1199 Elo2026-09-03
Design Arena Full-stack Agent: 1199 Elo2026-09-04
Design Arena UI: 1297 Elo2026-07-28
Design Arena UI: 1296 Elo2026-07-27
Design Arena UI: 1297 Elo2026-07-30
Design Arena UI: 1297 Elo2026-07-29
Design Arena UI: 1294 Elo2026-07-31
Design Arena UI: 1298 Elo2026-08-02
Design Arena UI: 1296 Elo2026-08-01
Design Arena UI: 1295 Elo2026-08-05
Design Arena UI: 1294 Elo2026-08-09
Design Arena UI: 1297 Elo2026-08-03
Design Arena UI: 1295 Elo2026-08-04
Design Arena UI: 1293 Elo2026-08-14
Design Arena UI: 1293 Elo2026-08-06
Design Arena UI: 1295 Elo2026-08-07
Design Arena UI: 1295 Elo2026-08-10
Design Arena UI: 1294 Elo2026-08-08
Design Arena UI: 1292 Elo2026-08-18
Design Arena UI: 1294 Elo2026-08-11
Design Arena UI: 1291 Elo2026-08-15
Design Arena UI: 1293 Elo2026-08-12
Design Arena UI: 1294 Elo2026-08-13
Design Arena UI: 1292 Elo2026-08-19
Design Arena UI: 1292 Elo2026-08-27
Design Arena UI: 1290 Elo2026-08-16
Design Arena UI: 1292 Elo2026-08-20
Design Arena UI: 1288 Elo2026-08-17
Design Arena UI: 1289 Elo2026-09-05
Design Arena UI: 1291 Elo2026-08-21
Design Arena UI: 1291 Elo2026-08-22
Design Arena UI: 1290 Elo2026-08-23
Design Arena UI: 1291 Elo2026-08-28
Design Arena UI: 1292 Elo2026-08-24
Design Arena UI: 1292 Elo2026-08-25
Design Arena UI: 1292 Elo2026-08-26
Design Arena UI: 1288 Elo2026-09-06
Design Arena UI: 1292 Elo2026-08-29
Design Arena UI: 1292 Elo2026-08-30
Design Arena UI: 1290 Elo2026-08-31
Design Arena UI: 1290 Elo2026-09-01
Design Arena UI: 1289 Elo2026-09-02
Design Arena UI: 1288 Elo2026-09-03
Design Arena UI: 1288 Elo2026-09-04
Design Arena Web-app Agent: 1227 Elo2026-07-28
Design Arena Web-app Agent: 1228 Elo2026-07-27
Design Arena Web-app Agent: 1229 Elo2026-07-30
Design Arena Web-app Agent: 1229 Elo2026-07-29
Design Arena Web-app Agent: 1229 Elo2026-07-31
Design Arena Web-app Agent: 1230 Elo2026-08-02
Design Arena Web-app Agent: 1229 Elo2026-08-01
Design Arena Web-app Agent: 1227 Elo2026-08-05
Design Arena Web-app Agent: 1221 Elo2026-08-09
Design Arena Web-app Agent: 1230 Elo2026-08-03
Design Arena Web-app Agent: 1230 Elo2026-08-04
Design Arena Web-app Agent: 1214 Elo2026-08-14
Design Arena Web-app Agent: 1227 Elo2026-08-06
Design Arena Web-app Agent: 1218 Elo2026-08-10
Design Arena Web-app Agent: 1227 Elo2026-08-07
Design Arena Web-app Agent: 1213 Elo2026-08-18
Design Arena Web-app Agent: 1228 Elo2026-08-08
Design Arena Web-app Agent: 1216 Elo2026-08-11
Design Arena Web-app Agent: 1214 Elo2026-08-15
Design Arena Web-app Agent: 1216 Elo2026-08-12
Design Arena Web-app Agent: 1214 Elo2026-08-13
Design Arena Web-app Agent: 1213 Elo2026-08-19
Design Arena Web-app Agent: 1205 Elo2026-08-27
Design Arena Web-app Agent: 1213 Elo2026-08-20
Design Arena Web-app Agent: 1216 Elo2026-08-16
Design Arena Web-app Agent: 1205 Elo2026-09-05
Design Arena Web-app Agent: 1216 Elo2026-08-17
Design Arena Web-app Agent: 1211 Elo2026-08-21
Design Arena Web-app Agent: 1212 Elo2026-08-22
Design Arena Web-app Agent: 1212 Elo2026-08-23
Design Arena Web-app Agent: 1206 Elo2026-08-28
Design Arena Web-app Agent: 1206 Elo2026-08-24
Design Arena Web-app Agent: 1207 Elo2026-08-25
Design Arena Web-app Agent: 1207 Elo2026-08-26
Design Arena Web-app Agent: 1205 Elo2026-09-06
Design Arena Web-app Agent: 1206 Elo2026-08-29
Design Arena Web-app Agent: 1205 Elo2026-08-30
Design Arena Web-app Agent: 1205 Elo2026-08-31
Design Arena Web-app Agent: 1205 Elo2026-09-01
Design Arena Web-app Agent: 1205 Elo2026-09-02
Design Arena Web-app Agent: 1205 Elo2026-09-03
Design Arena Web-app Agent: 1205 Elo2026-09-04
Design Arena Website: 1300 Elo2026-07-28
Design Arena Website: 1302 Elo2026-07-30
Design Arena Website: 1300 Elo2026-07-27
Design Arena Website: 1301 Elo2026-07-29
Design Arena Website: 1301 Elo2026-07-31
Design Arena Website: 1300 Elo2026-08-02
Design Arena Website: 1300 Elo2026-08-01
Design Arena Website: 1298 Elo2026-08-05
Design Arena Website: 1300 Elo2026-08-03
Design Arena Website: 1296 Elo2026-08-09
Design Arena Website: 1299 Elo2026-08-04
Design Arena Website: 1292 Elo2026-08-14
Design Arena Website: 1298 Elo2026-08-06
Design Arena Website: 1298 Elo2026-08-07
Design Arena Website: 1296 Elo2026-08-10
Design Arena Website: 1297 Elo2026-08-08
Design Arena Website: 1284 Elo2026-08-18
Design Arena Website: 1296 Elo2026-08-11
Design Arena Website: 1285 Elo2026-08-15
Design Arena Website: 1295 Elo2026-08-12
Design Arena Website: 1293 Elo2026-08-13
Design Arena Website: 1284 Elo2026-08-19
Design Arena Website: 1284 Elo2026-08-16
Design Arena Website: 1284 Elo2026-08-20
Design Arena Website: 1290 Elo2026-08-27
Design Arena Website: 1284 Elo2026-08-17
Design Arena Website: 1283 Elo2026-09-05
Design Arena Website: 1292 Elo2026-08-21
Design Arena Website: 1292 Elo2026-08-22
Design Arena Website: 1292 Elo2026-08-23
Design Arena Website: 1292 Elo2026-08-24
Design Arena Website: 1290 Elo2026-08-28
Design Arena Website: 1292 Elo2026-08-25
Design Arena Website: 1292 Elo2026-08-26
Design Arena Website: 1281 Elo2026-09-06
Design Arena Website: 1290 Elo2026-08-29
Design Arena Website: 1290 Elo2026-08-30
Design Arena Website: 1290 Elo2026-08-31
Design Arena Website: 1289 Elo2026-09-01
Design Arena Website: 1287 Elo2026-09-02
Design Arena Website: 1285 Elo2026-09-03
Design Arena Website: 1284 Elo2026-09-04
LiveBench Agentic Coding: 45.7%2026-06-25
LiveBench Coding: 74.0%2026-06-25
LiveBench Data Analysis: 62.7%2026-06-25
LiveBench Instruction Following: 56.3%2026-06-25
LiveBench Language: 77.9%2026-06-25
LiveBench Math: 79.6%2026-06-25
LiveBench Reasoning: 82.8%2026-06-25
LMArena Agent: -0.82026-07-13
LMArena Agent: -0.72026-07-20
LMArena Agent: 0.42026-07-27
LMArena Agent: -12026-07-21
LMArena Agent: 0.42026-07-28
LMArena Agent: 0.32026-08-03
LMArena Agent: 12026-08-12
LMArena Agent: 0.72026-08-06
LMArena Agent: 12026-08-11
LMArena Agent: 1.12026-08-13
LMArena Agent: 22026-08-24
LMArena Agent: 1.42026-08-31
LMArena Agent: 0.72026-09-05
LMArena Agent: 1.72026-08-27
LMArena WebDev: 1470 Elo2026-07-16
LMArena WebDev: 1470 Elo2026-07-21
LMArena WebDev: 1470 Elo2026-07-20
LMArena WebDev: 1473 Elo2026-07-27
LMArena WebDev: 1474 Elo2026-07-24
LMArena WebDev: 1473 Elo2026-07-28
LMArena WebDev: 1473 Elo2026-07-30
LMArena WebDev: 1473 Elo2026-08-01
LMArena WebDev: 1473 Elo2026-07-31
LMArena WebDev: 1473 Elo2026-08-06
LMArena WebDev: 1473 Elo2026-08-02
LMArena WebDev: 1473 Elo2026-08-12
LMArena WebDev: 1474 Elo2026-08-10
LMArena WebDev: 1473 Elo2026-08-14
LMArena WebDev: 1473 Elo2026-09-01
LMArena WebDev: 1472 Elo2026-09-05
LMArena WebDev: 1473 Elo2026-08-21
LMArena WebDev: 1473 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.

Open-weight model on Hugging Face.

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 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 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 MathProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Instruction Following or LMArena Math. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Math & ReasoningProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Instruction Following or LMArena Math. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Logic & Problem SolvingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Instruction Following or LMArena Math. 5 of 5 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 a General AssistantProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Instruction Following or LMArena Text. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Creative WritingProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Creative Writing or LMArena Text. 5 of 5 configured evaluation feeds currently have results.
Best LLM for WritingProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Creative Writing or LMArena Text. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Fast SummariesProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Text or 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 Value LLMProvisional evidence
43% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Text or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best Cheap LLM for High VolumeProvisional evidence
42% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Text or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Cheapest Capable LLMProvisional evidence
42% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Text or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best Open-Weight LLM for Self-HostingProvisional evidence
42% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Text or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Literary TranslationProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Text or WMT translation. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Everyday TranslationProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Text or WMT translation. 4 of 5 configured evaluation feeds currently have results.
Best LLM for TranslationProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Text or WMT translation. 4 of 5 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 Business WritingProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Creative Writing or LMArena Instruction Following. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Marketing CopyProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Creative Writing or LMArena Instruction Following. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Chat & RoleplayProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Creative Writing or LMArena Text. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Roleplay & CharacterProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Creative Writing or LMArena Text. 5 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 Document SummarizationProvisional evidence
30% 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 SummarizationProvisional evidence
30% 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 JSON & Schema OutputProvisional evidence
28% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Text. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Structured Data ExtractionProvisional evidence
28% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Text. 4 of 5 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 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 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.
Best LLM for Massive ContextProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Long Query. 3 of 4 configured evaluation feeds currently have results.
Best LLM for RAG & Long ContextProvisional evidence
6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 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.