GLM 5.2

z-ai/glm-5.2-20260616

Z.ai: GLM 5.2 is a text‑only model from z‑ai that supports reasoning and tool usage. It provides an open‑weight architecture with a context window of up to 1,048,576 tokens. Pricing is $0.8246 per million input tokens and $2.5916 per million output tokens.

tool use
structured outputs
reasoning
open-weight

At a glance

providerz-ai

releasedJun 13, 2026

context1.0M

input / M$0.97

Specifications

What the API gives you

Context window: 1.0M tokens
Max output: 131K tokens
Input price: $0.97 / 1M tokens
Output price: $3.04 / 1M tokens
Cache read: $0.19 / 1M tokens
Modalities: text → text
Knowledge cutoff: —
Released: Jun 13, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1346 Elo2026-07-28
Design Arena Coding: 1346 Elo2026-07-27
Design Arena Coding: 1346 Elo2026-07-30
Design Arena Coding: 1346 Elo2026-07-29
Design Arena Coding: 1346 Elo2026-07-31
Design Arena Coding: 1343 Elo2026-08-02
Design Arena Coding: 1343 Elo2026-08-05
Design Arena Coding: 1344 Elo2026-08-01
Design Arena Coding: 1341 Elo2026-08-09
Design Arena Coding: 1344 Elo2026-08-03
Design Arena Coding: 1343 Elo2026-08-04
Design Arena Coding: 1335 Elo2026-08-14
Design Arena Coding: 1343 Elo2026-08-06
Design Arena Coding: 1341 Elo2026-08-10
Design Arena Coding: 1342 Elo2026-08-07
Design Arena Coding: 1326 Elo2026-08-18
Design Arena Coding: 1341 Elo2026-08-08
Design Arena Coding: 1332 Elo2026-08-21
Design Arena Coding: 1330 Elo2026-08-15
Design Arena Coding: 1340 Elo2026-08-11
Design Arena Coding: 1338 Elo2026-08-12
Design Arena Coding: 1325 Elo2026-08-19
Design Arena Coding: 1336 Elo2026-08-13
Design Arena Coding: 1329 Elo2026-08-27
Design Arena Coding: 1318 Elo2026-09-05
Design Arena Coding: 1325 Elo2026-08-20
Design Arena Coding: 1329 Elo2026-08-16
Design Arena Coding: 1326 Elo2026-08-17
Design Arena Coding: 1332 Elo2026-08-22
Design Arena Coding: 1331 Elo2026-08-23
Design Arena Coding: 1328 Elo2026-08-28
Design Arena Coding: 1331 Elo2026-08-24
Design Arena Coding: 1331 Elo2026-08-25
Design Arena Coding: 1331 Elo2026-08-26
Design Arena Coding: 1317 Elo2026-09-06
Design Arena Coding: 1328 Elo2026-08-29
Design Arena Coding: 1327 Elo2026-08-30
Design Arena Coding: 1327 Elo2026-08-31
Design Arena Coding: 1327 Elo2026-09-01
Design Arena Coding: 1325 Elo2026-09-02
Design Arena Coding: 1323 Elo2026-09-03
Design Arena Coding: 1321 Elo2026-09-04
Design Arena Full-stack Agent: 1278 Elo2026-07-28
Design Arena Full-stack Agent: 1279 Elo2026-07-27
Design Arena Full-stack Agent: 1271 Elo2026-07-30
Design Arena Full-stack Agent: 1273 Elo2026-07-29
Design Arena Full-stack Agent: 1272 Elo2026-07-31
Design Arena Full-stack Agent: 1275 Elo2026-08-02
Design Arena Full-stack Agent: 1276 Elo2026-08-05
Design Arena Full-stack Agent: 1273 Elo2026-08-01
Design Arena Full-stack Agent: 1267 Elo2026-08-09
Design Arena Full-stack Agent: 1275 Elo2026-08-03
Design Arena Full-stack Agent: 1275 Elo2026-08-04
Design Arena Full-stack Agent: 1268 Elo2026-08-14
Design Arena Full-stack Agent: 1275 Elo2026-08-06
Design Arena Full-stack Agent: 1264 Elo2026-08-10
Design Arena Full-stack Agent: 1275 Elo2026-08-07
Design Arena Full-stack Agent: 1264 Elo2026-08-18
Design Arena Full-stack Agent: 1275 Elo2026-08-08
Design Arena Full-stack Agent: 1270 Elo2026-08-15
Design Arena Full-stack Agent: 1266 Elo2026-08-11
Design Arena Full-stack Agent: 1268 Elo2026-08-12
Design Arena Full-stack Agent: 1267 Elo2026-08-13
Design Arena Full-stack Agent: 1264 Elo2026-08-19
Design Arena Full-stack Agent: 1262 Elo2026-08-27
Design Arena Full-stack Agent: 1264 Elo2026-08-20
Design Arena Full-stack Agent: 1271 Elo2026-08-16
Design Arena Full-stack Agent: 1252 Elo2026-09-05
Design Arena Full-stack Agent: 1271 Elo2026-08-17
Design Arena Full-stack Agent: 1269 Elo2026-08-21
Design Arena Full-stack Agent: 1269 Elo2026-08-22
Design Arena Full-stack Agent: 1269 Elo2026-08-23
Design Arena Full-stack Agent: 1262 Elo2026-08-28
Design Arena Full-stack Agent: 1258 Elo2026-08-24
Design Arena Full-stack Agent: 1262 Elo2026-08-25
Design Arena Full-stack Agent: 1262 Elo2026-08-26
Design Arena Full-stack Agent: 1250 Elo2026-09-06
Design Arena Full-stack Agent: 1262 Elo2026-08-29
Design Arena Full-stack Agent: 1263 Elo2026-08-30
Design Arena Full-stack Agent: 1262 Elo2026-08-31
Design Arena Full-stack Agent: 1262 Elo2026-09-01
Design Arena Full-stack Agent: 1262 Elo2026-09-02
Design Arena Full-stack Agent: 1263 Elo2026-09-03
Design Arena Full-stack Agent: 1263 Elo2026-09-04
Design Arena UI: 1331 Elo2026-07-28
Design Arena UI: 1333 Elo2026-07-27
Design Arena UI: 1333 Elo2026-07-30
Design Arena UI: 1332 Elo2026-07-29
Design Arena UI: 1334 Elo2026-07-31
Design Arena UI: 1330 Elo2026-08-02
Design Arena UI: 1331 Elo2026-08-01
Design Arena UI: 1337 Elo2026-08-05
Design Arena UI: 1339 Elo2026-08-09
Design Arena UI: 1331 Elo2026-08-03
Design Arena UI: 1337 Elo2026-08-04
Design Arena UI: 1334 Elo2026-08-14
Design Arena UI: 1337 Elo2026-08-06
Design Arena UI: 1339 Elo2026-08-07
Design Arena UI: 1339 Elo2026-08-10
Design Arena UI: 1339 Elo2026-08-08
Design Arena UI: 1334 Elo2026-08-18
Design Arena UI: 1338 Elo2026-08-11
Design Arena UI: 1334 Elo2026-08-15
Design Arena UI: 1337 Elo2026-08-12
Design Arena UI: 1337 Elo2026-08-13
Design Arena UI: 1334 Elo2026-08-19
Design Arena UI: 1324 Elo2026-08-27
Design Arena UI: 1334 Elo2026-08-16
Design Arena UI: 1334 Elo2026-08-20
Design Arena UI: 1334 Elo2026-08-17
Design Arena UI: 1319 Elo2026-09-05
Design Arena UI: 1326 Elo2026-08-21
Design Arena UI: 1328 Elo2026-08-22
Design Arena UI: 1329 Elo2026-08-23
Design Arena UI: 1322 Elo2026-08-28
Design Arena UI: 1328 Elo2026-08-24
Design Arena UI: 1327 Elo2026-08-25
Design Arena UI: 1327 Elo2026-08-26
Design Arena UI: 1319 Elo2026-09-06
Design Arena UI: 1323 Elo2026-08-29
Design Arena UI: 1323 Elo2026-08-30
Design Arena UI: 1322 Elo2026-08-31
Design Arena UI: 1323 Elo2026-09-01
Design Arena UI: 1322 Elo2026-09-02
Design Arena UI: 1321 Elo2026-09-03
Design Arena UI: 1319 Elo2026-09-04
Design Arena Web-app Agent: 1270 Elo2026-07-28
Design Arena Web-app Agent: 1270 Elo2026-07-27
Design Arena Web-app Agent: 1269 Elo2026-07-30
Design Arena Web-app Agent: 1269 Elo2026-07-29
Design Arena Web-app Agent: 1270 Elo2026-07-31
Design Arena Web-app Agent: 1270 Elo2026-08-02
Design Arena Web-app Agent: 1270 Elo2026-08-01
Design Arena Web-app Agent: 1268 Elo2026-08-05
Design Arena Web-app Agent: 1261 Elo2026-08-09
Design Arena Web-app Agent: 1270 Elo2026-08-03
Design Arena Web-app Agent: 1270 Elo2026-08-04
Design Arena Web-app Agent: 1257 Elo2026-08-14
Design Arena Web-app Agent: 1268 Elo2026-08-06
Design Arena Web-app Agent: 1259 Elo2026-08-10
Design Arena Web-app Agent: 1268 Elo2026-08-07
Design Arena Web-app Agent: 1258 Elo2026-08-18
Design Arena Web-app Agent: 1268 Elo2026-08-08
Design Arena Web-app Agent: 1258 Elo2026-08-11
Design Arena Web-app Agent: 1260 Elo2026-08-15
Design Arena Web-app Agent: 1259 Elo2026-08-12
Design Arena Web-app Agent: 1258 Elo2026-08-13
Design Arena Web-app Agent: 1258 Elo2026-08-19
Design Arena Web-app Agent: 1251 Elo2026-08-27
Design Arena Web-app Agent: 1258 Elo2026-08-20
Design Arena Web-app Agent: 1261 Elo2026-08-16
Design Arena Web-app Agent: 1251 Elo2026-09-05
Design Arena Web-app Agent: 1261 Elo2026-08-17
Design Arena Web-app Agent: 1255 Elo2026-08-21
Design Arena Web-app Agent: 1256 Elo2026-08-22
Design Arena Web-app Agent: 1256 Elo2026-08-23
Design Arena Web-app Agent: 1252 Elo2026-08-28
Design Arena Web-app Agent: 1251 Elo2026-08-24
Design Arena Web-app Agent: 1252 Elo2026-08-25
Design Arena Web-app Agent: 1252 Elo2026-08-26
Design Arena Web-app Agent: 1251 Elo2026-09-06
Design Arena Web-app Agent: 1252 Elo2026-08-29
Design Arena Web-app Agent: 1251 Elo2026-08-30
Design Arena Web-app Agent: 1251 Elo2026-08-31
Design Arena Web-app Agent: 1251 Elo2026-09-01
Design Arena Web-app Agent: 1251 Elo2026-09-02
Design Arena Web-app Agent: 1251 Elo2026-09-03
Design Arena Web-app Agent: 1251 Elo2026-09-04
Design Arena Website: 1341 Elo2026-07-28
Design Arena Website: 1341 Elo2026-07-27
Design Arena Website: 1340 Elo2026-07-30
Design Arena Website: 1340 Elo2026-07-29
Design Arena Website: 1339 Elo2026-07-31
Design Arena Website: 1337 Elo2026-08-02
Design Arena Website: 1338 Elo2026-08-01
Design Arena Website: 1339 Elo2026-08-05
Design Arena Website: 1338 Elo2026-08-03
Design Arena Website: 1336 Elo2026-08-09
Design Arena Website: 1339 Elo2026-08-04
Design Arena Website: 1329 Elo2026-08-14
Design Arena Website: 1338 Elo2026-08-06
Design Arena Website: 1337 Elo2026-08-07
Design Arena Website: 1336 Elo2026-08-10
Design Arena Website: 1336 Elo2026-08-08
Design Arena Website: 1319 Elo2026-08-18
Design Arena Website: 1335 Elo2026-08-11
Design Arena Website: 1321 Elo2026-08-15
Design Arena Website: 1333 Elo2026-08-12
Design Arena Website: 1331 Elo2026-08-13
Design Arena Website: 1319 Elo2026-08-19
Design Arena Website: 1320 Elo2026-08-16
Design Arena Website: 1319 Elo2026-08-20
Design Arena Website: 1323 Elo2026-08-27
Design Arena Website: 1320 Elo2026-08-17
Design Arena Website: 1315 Elo2026-09-05
Design Arena Website: 1327 Elo2026-08-21
Design Arena Website: 1327 Elo2026-08-22
Design Arena Website: 1327 Elo2026-08-23
Design Arena Website: 1326 Elo2026-08-24
Design Arena Website: 1323 Elo2026-08-28
Design Arena Website: 1326 Elo2026-08-25
Design Arena Website: 1325 Elo2026-08-26
Design Arena Website: 1313 Elo2026-09-06
Design Arena Website: 1322 Elo2026-08-29
Design Arena Website: 1321 Elo2026-08-30
Design Arena Website: 1321 Elo2026-08-31
Design Arena Website: 1321 Elo2026-09-01
Design Arena Website: 1320 Elo2026-09-02
Design Arena Website: 1318 Elo2026-09-03
Design Arena Website: 1316 Elo2026-09-04
Frontier-Bench^‡: 4.6% ± 1.02026-07-19Claude Code, max effort
LiveBench Agentic Coding: 51.8%2026-06-25
LiveBench Coding: 79.7%2026-06-25
LiveBench Data Analysis: 73.7%2026-06-25
LiveBench Instruction Following: 62.3%2026-06-25
LiveBench Language: 76.2%2026-06-25
LiveBench Math: 89.8%2026-06-25
LiveBench Reasoning: 78.6%2026-06-25
LMArena Agent: 7.12026-07-27
LMArena Agent: 6.52026-07-21
LMArena Agent: 7.12026-07-28
LMArena Agent: 6.72026-08-03
LMArena Agent: 6.72026-08-12
LMArena Agent: 6.82026-08-06
LMArena Agent: 6.72026-08-11
LMArena Agent: 6.72026-08-13
LMArena Agent: 5.92026-08-24
LMArena Agent: 6.12026-08-31
LMArena Agent: 62026-09-05
LMArena Agent: 5.92026-08-27
LMArena Creative Writing: 1456 Elo2026-07-27
LMArena Creative Writing: 1456 Elo2026-07-30
LMArena Creative Writing: 1456 Elo2026-08-02
LMArena Creative Writing: 1456 Elo2026-08-03
LMArena Creative Writing: 1458 Elo2026-08-06
LMArena Creative Writing: 1461 Elo2026-08-12
LMArena Creative Writing: 1461 Elo2026-08-21
LMArena Creative Writing: 1462 Elo2026-09-02
LMArena Creative Writing: 1463 Elo2026-08-27
LMArena Creative Writing: 1463 Elo2026-09-01
LMArena Instruction Following: 1454 Elo2026-07-27
LMArena Instruction Following: 1454 Elo2026-07-30
LMArena Instruction Following: 1455 Elo2026-08-02
LMArena Instruction Following: 1455 Elo2026-08-03
LMArena Instruction Following: 1456 Elo2026-08-06
LMArena Instruction Following: 1455 Elo2026-08-12
LMArena Instruction Following: 1453 Elo2026-08-21
LMArena Instruction Following: 1458 Elo2026-09-02
LMArena Instruction Following: 1455 Elo2026-08-27
LMArena Instruction Following: 1458 Elo2026-09-01
LMArena Long Query: 1469 Elo2026-07-27
LMArena Long Query: 1469 Elo2026-07-30
LMArena Long Query: 1468 Elo2026-08-02
LMArena Long Query: 1468 Elo2026-08-03
LMArena Long Query: 1469 Elo2026-08-06
LMArena Long Query: 1469 Elo2026-08-12
LMArena Long Query: 1468 Elo2026-08-21
LMArena Long Query: 1472 Elo2026-09-02
LMArena Long Query: 1472 Elo2026-08-27
LMArena Long Query: 1472 Elo2026-09-01
LMArena Math: 1471 Elo2026-07-27
LMArena Math: 1471 Elo2026-07-30
LMArena Math: 1471 Elo2026-08-02
LMArena Math: 1471 Elo2026-08-03
LMArena Math: 1470 Elo2026-08-06
LMArena Math: 1470 Elo2026-08-12
LMArena Math: 1470 Elo2026-08-21
LMArena Math: 1471 Elo2026-09-01
LMArena Math: 1470 Elo2026-08-27
LMArena Text: 1469 Elo2026-07-27
LMArena Text: 1469 Elo2026-07-30
LMArena Text: 1469 Elo2026-08-02
LMArena Text: 1471 Elo2026-08-06
LMArena Text: 1469 Elo2026-08-03
LMArena Text: 1470 Elo2026-08-10
LMArena Text: 1470 Elo2026-08-21
LMArena Text: 1471 Elo2026-08-12
LMArena Text: 1472 Elo2026-09-01
LMArena Text: 1472 Elo2026-09-02
LMArena Text: 1472 Elo2026-08-27
LMArena WebDev: 1592 Elo2026-07-21
LMArena WebDev: 1587 Elo2026-07-27
LMArena WebDev: 1588 Elo2026-07-24
LMArena WebDev: 1588 Elo2026-07-28
LMArena WebDev: 1588 Elo2026-07-30
LMArena WebDev: 1586 Elo2026-08-01
LMArena WebDev: 1587 Elo2026-07-31
LMArena WebDev: 1588 Elo2026-08-06
LMArena WebDev: 1586 Elo2026-08-02
LMArena WebDev: 1588 Elo2026-08-10
LMArena WebDev: 1587 Elo2026-08-12
LMArena WebDev: 1585 Elo2026-08-14
LMArena WebDev: 1585 Elo2026-09-01
LMArena WebDev: 1587 Elo2026-09-05
LMArena WebDev: 1582 Elo2026-08-21
LMArena WebDev: 1585 Elo2026-08-30
SWE-rebench^‡: 51.1% ± 1.12026-05-15tools
SWE-rebench^‡: 57.0% ± 0.92026-07-01tools

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.

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 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 LLM for Agentic CodingEstablished evidence
78% of intended weighted task evidence across 5 independent sources. 8 of 8 configured evaluation feeds currently have results.
Best LLM for CodingEstablished evidence
74% of intended weighted task evidence across 4 independent sources. 8 of 8 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 LLM for Autonomous AgentsEstablished evidence
67% of intended weighted task evidence across 4 independent sources. 7 of 7 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 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 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 Hermes AgentProvisional evidence
45% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsProvisional evidence
45% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseProvisional evidence
45% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawProvisional evidence
45% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for AI AgentsProvisional evidence
42% 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 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.