Claude Opus 4.8

anthropic/claude-4.8-opus-20260528

Claude Opus 4.8, from Anthropic, accepts text, image, and file inputs and generates text output. It provides a context length of 1,000,000 tokens, costs $5 per million input tokens and $25 per million output tokens, and supports both tool usage and reasoning. The model is not open‑weight and was released on 2026‑05‑28.

tool use
structured outputs
reasoning

At a glance

provideranthropic

releasedAug 26, 2025

context1M

input / M$5

Specifications

What the API gives you

Context window: 1M tokens
Max output: 128K tokens
Input price: $5 / 1M tokens
Output price: $25 / 1M tokens
Cache read: $0.50 / 1M tokens
Modalities: text, image, file → text
Knowledge cutoff: —
Released: Aug 26, 2025

Measured evidence

Public benchmark record

Design Arena Coding: 1270 Elo2026-07-28
Design Arena Coding: 1270 Elo2026-07-27
Design Arena Coding: 1271 Elo2026-07-30
Design Arena Coding: 1270 Elo2026-07-29
Design Arena Coding: 1270 Elo2026-07-31
Design Arena Coding: 1271 Elo2026-08-02
Design Arena Coding: 1270 Elo2026-08-05
Design Arena Coding: 1270 Elo2026-08-01
Design Arena Coding: 1271 Elo2026-08-09
Design Arena Coding: 1271 Elo2026-08-03
Design Arena Coding: 1271 Elo2026-08-04
Design Arena Coding: 1270 Elo2026-08-14
Design Arena Coding: 1271 Elo2026-08-06
Design Arena Coding: 1271 Elo2026-08-10
Design Arena Coding: 1271 Elo2026-08-07
Design Arena Coding: 1266 Elo2026-08-18
Design Arena Coding: 1271 Elo2026-08-08
Design Arena Coding: 1266 Elo2026-08-15
Design Arena Coding: 1272 Elo2026-08-11
Design Arena Coding: 1272 Elo2026-08-12
Design Arena Coding: 1272 Elo2026-08-21
Design Arena Coding: 1270 Elo2026-08-13
Design Arena Coding: 1265 Elo2026-08-19
Design Arena Coding: 1273 Elo2026-08-27
Design Arena Coding: 1265 Elo2026-08-20
Design Arena Coding: 1265 Elo2026-08-16
Design Arena Coding: 1266 Elo2026-09-05
Design Arena Coding: 1266 Elo2026-08-17
Design Arena Coding: 1272 Elo2026-08-22
Design Arena Coding: 1272 Elo2026-08-23
Design Arena Coding: 1273 Elo2026-08-28
Design Arena Coding: 1273 Elo2026-08-24
Design Arena Coding: 1273 Elo2026-08-25
Design Arena Coding: 1273 Elo2026-08-26
Design Arena Coding: 1266 Elo2026-09-06
Design Arena Coding: 1273 Elo2026-08-29
Design Arena Coding: 1273 Elo2026-08-30
Design Arena Coding: 1273 Elo2026-08-31
Design Arena Coding: 1273 Elo2026-09-01
Design Arena Coding: 1272 Elo2026-09-02
Design Arena Coding: 1269 Elo2026-09-03
Design Arena Coding: 1269 Elo2026-09-04
Design Arena Full-stack Agent: 1297 Elo2026-07-28
Design Arena Full-stack Agent: 1298 Elo2026-07-27
Design Arena Full-stack Agent: 1288 Elo2026-07-30
Design Arena Full-stack Agent: 1290 Elo2026-07-29
Design Arena Full-stack Agent: 1289 Elo2026-07-31
Design Arena Full-stack Agent: 1293 Elo2026-08-02
Design Arena Full-stack Agent: 1286 Elo2026-08-05
Design Arena Full-stack Agent: 1291 Elo2026-08-01
Design Arena Full-stack Agent: 1276 Elo2026-08-09
Design Arena Full-stack Agent: 1292 Elo2026-08-03
Design Arena Full-stack Agent: 1292 Elo2026-08-04
Design Arena Full-stack Agent: 1278 Elo2026-08-14
Design Arena Full-stack Agent: 1285 Elo2026-08-06
Design Arena Full-stack Agent: 1275 Elo2026-08-10
Design Arena Full-stack Agent: 1286 Elo2026-08-07
Design Arena Full-stack Agent: 1276 Elo2026-08-18
Design Arena Full-stack Agent: 1284 Elo2026-08-08
Design Arena Full-stack Agent: 1280 Elo2026-08-15
Design Arena Full-stack Agent: 1278 Elo2026-08-11
Design Arena Full-stack Agent: 1279 Elo2026-08-12
Design Arena Full-stack Agent: 1279 Elo2026-08-13
Design Arena Full-stack Agent: 1276 Elo2026-08-19
Design Arena Full-stack Agent: 1271 Elo2026-08-27
Design Arena Full-stack Agent: 1276 Elo2026-08-20
Design Arena Full-stack Agent: 1280 Elo2026-08-16
Design Arena Full-stack Agent: 1262 Elo2026-09-05
Design Arena Full-stack Agent: 1281 Elo2026-08-17
Design Arena Full-stack Agent: 1280 Elo2026-08-21
Design Arena Full-stack Agent: 1280 Elo2026-08-22
Design Arena Full-stack Agent: 1279 Elo2026-08-23
Design Arena Full-stack Agent: 1271 Elo2026-08-28
Design Arena Full-stack Agent: 1268 Elo2026-08-24
Design Arena Full-stack Agent: 1272 Elo2026-08-25
Design Arena Full-stack Agent: 1272 Elo2026-08-26
Design Arena Full-stack Agent: 1260 Elo2026-09-06
Design Arena Full-stack Agent: 1271 Elo2026-08-29
Design Arena Full-stack Agent: 1272 Elo2026-08-30
Design Arena Full-stack Agent: 1271 Elo2026-08-31
Design Arena Full-stack Agent: 1273 Elo2026-09-01
Design Arena Full-stack Agent: 1272 Elo2026-09-02
Design Arena Full-stack Agent: 1273 Elo2026-09-03
Design Arena Full-stack Agent: 1273 Elo2026-09-04
Design Arena UI: 1277 Elo2026-07-28
Design Arena UI: 1277 Elo2026-07-27
Design Arena UI: 1277 Elo2026-07-30
Design Arena UI: 1276 Elo2026-07-29
Design Arena UI: 1278 Elo2026-07-31
Design Arena UI: 1279 Elo2026-08-02
Design Arena UI: 1279 Elo2026-08-01
Design Arena UI: 1280 Elo2026-08-05
Design Arena UI: 1280 Elo2026-08-09
Design Arena UI: 1280 Elo2026-08-03
Design Arena UI: 1280 Elo2026-08-04
Design Arena UI: 1281 Elo2026-08-14
Design Arena UI: 1282 Elo2026-08-06
Design Arena UI: 1282 Elo2026-08-07
Design Arena UI: 1280 Elo2026-08-10
Design Arena UI: 1280 Elo2026-08-08
Design Arena UI: 1282 Elo2026-08-18
Design Arena UI: 1280 Elo2026-08-11
Design Arena UI: 1280 Elo2026-08-15
Design Arena UI: 1281 Elo2026-08-12
Design Arena UI: 1282 Elo2026-08-13
Design Arena UI: 1282 Elo2026-08-19
Design Arena UI: 1280 Elo2026-08-16
Design Arena UI: 1282 Elo2026-08-20
Design Arena UI: 1280 Elo2026-08-27
Design Arena UI: 1281 Elo2026-08-17
Design Arena UI: 1277 Elo2026-09-05
Design Arena UI: 1279 Elo2026-08-21
Design Arena UI: 1280 Elo2026-08-22
Design Arena UI: 1279 Elo2026-08-23
Design Arena UI: 1281 Elo2026-08-28
Design Arena UI: 1280 Elo2026-08-24
Design Arena UI: 1281 Elo2026-08-25
Design Arena UI: 1281 Elo2026-08-26
Design Arena UI: 1277 Elo2026-09-06
Design Arena UI: 1280 Elo2026-08-29
Design Arena UI: 1279 Elo2026-08-30
Design Arena UI: 1280 Elo2026-08-31
Design Arena UI: 1281 Elo2026-09-01
Design Arena UI: 1279 Elo2026-09-02
Design Arena UI: 1278 Elo2026-09-03
Design Arena UI: 1276 Elo2026-09-04
Design Arena Web-app Agent: 1271 Elo2026-07-28
Design Arena Web-app Agent: 1271 Elo2026-07-27
Design Arena Web-app Agent: 1271 Elo2026-07-30
Design Arena Web-app Agent: 1270 Elo2026-07-29
Design Arena Web-app Agent: 1271 Elo2026-07-31
Design Arena Web-app Agent: 1273 Elo2026-08-02
Design Arena Web-app Agent: 1271 Elo2026-08-01
Design Arena Web-app Agent: 1271 Elo2026-08-05
Design Arena Web-app Agent: 1265 Elo2026-08-09
Design Arena Web-app Agent: 1273 Elo2026-08-03
Design Arena Web-app Agent: 1273 Elo2026-08-04
Design Arena Web-app Agent: 1262 Elo2026-08-14
Design Arena Web-app Agent: 1271 Elo2026-08-06
Design Arena Web-app Agent: 1264 Elo2026-08-10
Design Arena Web-app Agent: 1271 Elo2026-08-07
Design Arena Web-app Agent: 1259 Elo2026-08-18
Design Arena Web-app Agent: 1272 Elo2026-08-08
Design Arena Web-app Agent: 1263 Elo2026-08-11
Design Arena Web-app Agent: 1262 Elo2026-08-15
Design Arena Web-app Agent: 1264 Elo2026-08-12
Design Arena Web-app Agent: 1263 Elo2026-08-13
Design Arena Web-app Agent: 1259 Elo2026-08-19
Design Arena Web-app Agent: 1255 Elo2026-08-27
Design Arena Web-app Agent: 1259 Elo2026-08-20
Design Arena Web-app Agent: 1263 Elo2026-08-16
Design Arena Web-app Agent: 1257 Elo2026-09-05
Design Arena Web-app Agent: 1263 Elo2026-08-17
Design Arena Web-app Agent: 1256 Elo2026-08-21
Design Arena Web-app Agent: 1257 Elo2026-08-22
Design Arena Web-app Agent: 1258 Elo2026-08-23
Design Arena Web-app Agent: 1257 Elo2026-08-28
Design Arena Web-app Agent: 1253 Elo2026-08-24
Design Arena Web-app Agent: 1255 Elo2026-08-25
Design Arena Web-app Agent: 1256 Elo2026-08-26
Design Arena Web-app Agent: 1257 Elo2026-09-06
Design Arena Web-app Agent: 1257 Elo2026-08-29
Design Arena Web-app Agent: 1256 Elo2026-08-30
Design Arena Web-app Agent: 1257 Elo2026-08-31
Design Arena Web-app Agent: 1257 Elo2026-09-01
Design Arena Web-app Agent: 1257 Elo2026-09-02
Design Arena Web-app Agent: 1257 Elo2026-09-03
Design Arena Web-app Agent: 1257 Elo2026-09-04
Design Arena Website: 1268 Elo2026-07-28
Design Arena Website: 1269 Elo2026-07-30
Design Arena Website: 1268 Elo2026-07-27
Design Arena Website: 1269 Elo2026-07-29
Design Arena Website: 1268 Elo2026-07-31
Design Arena Website: 1269 Elo2026-08-02
Design Arena Website: 1268 Elo2026-08-01
Design Arena Website: 1269 Elo2026-08-05
Design Arena Website: 1269 Elo2026-08-03
Design Arena Website: 1270 Elo2026-08-09
Design Arena Website: 1270 Elo2026-08-04
Design Arena Website: 1269 Elo2026-08-14
Design Arena Website: 1270 Elo2026-08-06
Design Arena Website: 1270 Elo2026-08-07
Design Arena Website: 1271 Elo2026-08-10
Design Arena Website: 1270 Elo2026-08-08
Design Arena Website: 1262 Elo2026-08-18
Design Arena Website: 1271 Elo2026-08-11
Design Arena Website: 1261 Elo2026-08-15
Design Arena Website: 1270 Elo2026-08-12
Design Arena Website: 1269 Elo2026-08-13
Design Arena Website: 1262 Elo2026-08-19
Design Arena Website: 1261 Elo2026-08-16
Design Arena Website: 1262 Elo2026-08-20
Design Arena Website: 1272 Elo2026-08-27
Design Arena Website: 1261 Elo2026-08-17
Design Arena Website: 1269 Elo2026-09-05
Design Arena Website: 1270 Elo2026-08-21
Design Arena Website: 1271 Elo2026-08-22
Design Arena Website: 1271 Elo2026-08-23
Design Arena Website: 1271 Elo2026-08-24
Design Arena Website: 1273 Elo2026-08-28
Design Arena Website: 1272 Elo2026-08-25
Design Arena Website: 1272 Elo2026-08-26
Design Arena Website: 1267 Elo2026-09-06
Design Arena Website: 1272 Elo2026-08-29
Design Arena Website: 1272 Elo2026-08-30
Design Arena Website: 1272 Elo2026-08-31
Design Arena Website: 1272 Elo2026-09-01
Design Arena Website: 1271 Elo2026-09-02
Design Arena Website: 1269 Elo2026-09-03
Design Arena Website: 1269 Elo2026-09-04
Frontier-Bench^‡: 21.1% ± 1.62026-07-12Claude Code, max effort
Frontier-Bench^‡: 23.6%2026-05-28Claude Code, max effort
LiveBench Agentic Coding: 50.5%2026-06-25
LiveBench Coding: 81.8%2026-06-25
LiveBench Data Analysis: 66.0%2026-06-25
LiveBench Instruction Following: 72.0%2026-06-25
LiveBench Language: 79.7%2026-06-25
LiveBench Math: 94.3%2026-06-25
LiveBench Reasoning: 89.2%2026-06-25
LMArena Agent: 9.32026-07-13
LMArena Agent: 102026-07-20
LMArena Agent: 9.52026-07-27
LMArena Agent: 9.72026-07-21
LMArena Agent: 9.42026-07-28
LMArena Agent: 9.42026-08-06
LMArena Agent: 9.22026-08-03
LMArena Agent: 9.62026-08-12
LMArena Agent: 9.52026-08-11
LMArena Agent: 9.82026-08-13
LMArena Agent: 102026-08-24
LMArena Agent: 9.52026-08-31
LMArena Agent: 9.22026-09-05
LMArena Agent: 9.92026-08-27
LMArena Creative Writing: 1447 Elo2026-07-21
LMArena Creative Writing: 1449 Elo2026-07-27
LMArena Creative Writing: 1449 Elo2026-07-30
LMArena Creative Writing: 1449 Elo2026-08-02
LMArena Creative Writing: 1449 Elo2026-08-03
LMArena Creative Writing: 1450 Elo2026-08-06
LMArena Creative Writing: 1452 Elo2026-08-12
LMArena Creative Writing: 1450 Elo2026-08-21
LMArena Creative Writing: 1448 Elo2026-09-02
LMArena Creative Writing: 1449 Elo2026-08-27
LMArena Creative Writing: 1448 Elo2026-09-01
LMArena Instruction Following: 1479 Elo2026-07-21
LMArena Instruction Following: 1479 Elo2026-07-27
LMArena Instruction Following: 1479 Elo2026-07-30
LMArena Instruction Following: 1479 Elo2026-08-02
LMArena Instruction Following: 1479 Elo2026-08-03
LMArena Instruction Following: 1480 Elo2026-08-06
LMArena Instruction Following: 1479 Elo2026-08-12
LMArena Instruction Following: 1479 Elo2026-08-21
LMArena Instruction Following: 1477 Elo2026-09-02
LMArena Instruction Following: 1478 Elo2026-08-27
LMArena Instruction Following: 1477 Elo2026-09-01
LMArena Long Query: 1486 Elo2026-07-21
LMArena Long Query: 1486 Elo2026-07-27
LMArena Long Query: 1486 Elo2026-07-30
LMArena Long Query: 1486 Elo2026-08-02
LMArena Long Query: 1486 Elo2026-08-03
LMArena Long Query: 1486 Elo2026-08-06
LMArena Long Query: 1485 Elo2026-08-12
LMArena Long Query: 1483 Elo2026-08-21
LMArena Long Query: 1482 Elo2026-09-02
LMArena Long Query: 1482 Elo2026-08-27
LMArena Long Query: 1482 Elo2026-09-01
LMArena Math: 1489 Elo2026-07-21
LMArena Math: 1486 Elo2026-07-27
LMArena Math: 1486 Elo2026-07-30
LMArena Math: 1485 Elo2026-08-02
LMArena Math: 1485 Elo2026-08-03
LMArena Math: 1483 Elo2026-08-06
LMArena Math: 1485 Elo2026-08-12
LMArena Math: 1485 Elo2026-08-21
LMArena Math: 1488 Elo2026-09-01
LMArena Math: 1486 Elo2026-08-27
LMArena Text: 1462 Elo2026-07-16
LMArena Text: 1472 Elo2026-07-20
LMArena Text: 1484 Elo2026-07-21
LMArena Text: 1484 Elo2026-07-27
LMArena Text: 1484 Elo2026-07-30
LMArena Text: 1484 Elo2026-08-02
LMArena Text: 1483 Elo2026-08-06
LMArena Text: 1484 Elo2026-08-03
LMArena Text: 1482 Elo2026-08-10
LMArena Text: 1482 Elo2026-08-21
LMArena Text: 1482 Elo2026-08-12
LMArena Text: 1482 Elo2026-09-01
LMArena Text: 1482 Elo2026-09-02
LMArena Text: 1481 Elo2026-08-27
LMArena Vision: 1295 Elo2026-07-12
LMArena Vision: 1286 Elo2026-07-21
LMArena Vision: 1286 Elo2026-07-26
LMArena Vision: 1286 Elo2026-07-30
LMArena Vision: 1286 Elo2026-08-02
LMArena Vision: 1284 Elo2026-08-06
LMArena Vision: 1285 Elo2026-08-21
LMArena Vision: 1285 Elo2026-08-27
LMArena WebDev: 1562 Elo2026-07-16
LMArena WebDev: 1565 Elo2026-07-21
LMArena WebDev: 1564 Elo2026-07-20
LMArena WebDev: 1568 Elo2026-07-27
LMArena WebDev: 1568 Elo2026-07-24
LMArena WebDev: 1568 Elo2026-07-28
LMArena WebDev: 1568 Elo2026-07-30
LMArena WebDev: 1566 Elo2026-08-01
LMArena WebDev: 1567 Elo2026-07-31
LMArena WebDev: 1565 Elo2026-08-06
LMArena WebDev: 1566 Elo2026-08-02
LMArena WebDev: 1564 Elo2026-08-10
LMArena WebDev: 1564 Elo2026-08-12
LMArena WebDev: 1564 Elo2026-08-14
LMArena WebDev: 1563 Elo2026-09-01
LMArena WebDev: 1563 Elo2026-09-05
LMArena WebDev: 1563 Elo2026-08-21
LMArena WebDev: 1563 Elo2026-08-30
OSWorld Verified^‡: 20.6%2026-06-24max effort
SWE-rebench^‡: 56.5% ± 1.22026-05-15tools
Terminal-Bench 2.1^‡: 78.9% ± 1.32026-07-09high effort
Terminal-Bench 2.1^‡: 23.6%2026-05-28max effort

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference. ‡ Submitted scaffold plus model result. Compare the harness and effort settings, not only the model name.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

Best LLM for Competition MathEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Business WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Agentic CodingEstablished evidence
100% of intended weighted task evidence across 6 independent sources. 8 of 8 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 Autonomous AgentsEstablished evidence
100% of intended weighted task evidence across 6 independent sources. 7 of 7 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 Computer & Browser UseEstablished evidence
90% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
Best LLM for CodingEstablished evidence
84% of intended weighted task evidence across 5 independent sources. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Code CompletionEstablished evidence
81% of intended weighted task evidence across 2 independent sources. 4 of 4 configured evaluation feeds currently have results.
Best LLM for 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 AI AgentsEstablished evidence
70% of intended weighted task evidence across 5 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 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 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 Hermes AgentEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawEstablished evidence
62% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Document SummarizationEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 4 of 6 configured evaluation feeds currently have results.
Best LLM for SummarizationEstablished evidence
60% of intended weighted task evidence across 2 independent sources. 4 of 6 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 Massive ContextProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LongBench v2. 3 of 4 configured evaluation feeds currently have results.
Best LLM for RAG & Long ContextProvisional evidence
47% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LongBench v2. 4 of 6 configured evaluation feeds currently have results.
Best LLM for OCR & DocumentsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Vision & DocumentsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Charts & DiagramsProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Document ParsingProvisional evidence
45% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Structured-output eval or VLMEvalKit tasks. 3 of 5 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 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.

Recommendation coverage

Where this model appears

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