Claude Sonnet 4.5

anthropic/claude-4.5-sonnet-20250929

Claude Sonnet 4.5, released on 2025‑09‑29 by Anthropic, accepts text, image, and file inputs and produces text output. It supports tool usage and reasoning, and operates with a context window of up to 1,000,000 tokens. Pricing is 3 units per 1 M input tokens and 15 units per 1 M output tokens; the model’s weights are

tool use
structured outputs
reasoning

At a glance

provideranthropic

releasedJan 15, 2025

context1M

input / M$3

Specifications

What the API gives you

Context window: 1M tokens
Max output: 64K tokens
Input price: $3 / 1M tokens
Output price: $15 / 1M tokens
Cache read: $0.30 / 1M tokens
Modalities: text, image, file → text
Knowledge cutoff: Jan 31, 2025
Released: Jan 15, 2025

Measured evidence

Public benchmark record

BFCL: 73.2%2026-07-28
BFCL: 73.2%2026-07-27
BFCL: 73.2%2026-07-29
BFCL: 73.2%2026-07-31
BFCL: 73.2%2026-07-30
BFCL: 73.2%2026-08-02
BFCL: 73.2%2026-08-01
BFCL: 73.2%2026-08-05
BFCL: 73.2%2026-08-03
BFCL: 73.2%2026-08-09
BFCL: 73.2%2026-08-04
BFCL: 73.2%2026-08-06
BFCL: 73.2%2026-08-07
BFCL: 73.2%2026-08-14
BFCL: 73.2%2026-08-10
BFCL: 73.2%2026-08-08
BFCL: 73.2%2026-08-18
BFCL: 73.2%2026-08-11
BFCL: 73.2%2026-08-15
BFCL: 73.2%2026-08-12
BFCL: 73.2%2026-08-13
BFCL: 73.2%2026-08-19
BFCL: 73.2%2026-08-16
BFCL: 73.2%2026-08-20
BFCL: 73.2%2026-08-27
BFCL: 73.2%2026-08-17
BFCL: 73.2%2026-08-21
BFCL: 73.2%2026-08-22
BFCL: 73.2%2026-08-23
BFCL: 73.2%2026-08-24
BFCL: 73.2%2026-09-05
BFCL: 73.2%2026-08-28
BFCL: 73.2%2026-08-25
BFCL: 73.2%2026-08-26
BFCL: 73.2%2026-09-06
BFCL: 73.2%2026-08-29
BFCL: 73.2%2026-08-30
BFCL: 73.2%2026-08-31
BFCL: 73.2%2026-09-01
BFCL: 73.2%2026-09-02
BFCL: 73.2%2026-09-03
BFCL: 73.2%2026-09-04
Design Arena Coding: 1213 Elo2026-07-28
Design Arena Coding: 1213 Elo2026-07-27
Design Arena Coding: 1213 Elo2026-07-30
Design Arena Coding: 1213 Elo2026-07-29
Design Arena Coding: 1213 Elo2026-07-31
Design Arena Coding: 1212 Elo2026-08-02
Design Arena Coding: 1211 Elo2026-08-05
Design Arena Coding: 1212 Elo2026-08-01
Design Arena Coding: 1210 Elo2026-08-09
Design Arena Coding: 1212 Elo2026-08-03
Design Arena Coding: 1212 Elo2026-08-04
Design Arena Coding: 1207 Elo2026-08-14
Design Arena Coding: 1211 Elo2026-08-06
Design Arena Coding: 1210 Elo2026-08-10
Design Arena Coding: 1211 Elo2026-08-07
Design Arena Coding: 1201 Elo2026-08-18
Design Arena Coding: 1210 Elo2026-08-08
Design Arena Coding: 1201 Elo2026-08-15
Design Arena Coding: 1210 Elo2026-08-11
Design Arena Coding: 1209 Elo2026-08-12
Design Arena Coding: 1207 Elo2026-08-13
Design Arena Coding: 1200 Elo2026-08-19
Design Arena Coding: 1206 Elo2026-08-27
Design Arena Coding: 1207 Elo2026-08-21
Design Arena Coding: 1200 Elo2026-08-20
Design Arena Coding: 1201 Elo2026-08-16
Design Arena Coding: 1199 Elo2026-09-05
Design Arena Coding: 1201 Elo2026-08-17
Design Arena Coding: 1207 Elo2026-08-22
Design Arena Coding: 1207 Elo2026-08-23
Design Arena Coding: 1206 Elo2026-08-28
Design Arena Coding: 1207 Elo2026-08-24
Design Arena Coding: 1207 Elo2026-08-25
Design Arena Coding: 1207 Elo2026-08-26
Design Arena Coding: 1198 Elo2026-09-06
Design Arena Coding: 1206 Elo2026-08-29
Design Arena Coding: 1206 Elo2026-08-30
Design Arena Coding: 1206 Elo2026-08-31
Design Arena Coding: 1206 Elo2026-09-01
Design Arena Coding: 1205 Elo2026-09-02
Design Arena Coding: 1203 Elo2026-09-03
Design Arena Coding: 1201 Elo2026-09-04
Design Arena Full-stack Agent: 1099 Elo2026-07-28
Design Arena Full-stack Agent: 1101 Elo2026-07-27
Design Arena Full-stack Agent: 1092 Elo2026-07-30
Design Arena Full-stack Agent: 1092 Elo2026-07-29
Design Arena Full-stack Agent: 1092 Elo2026-07-31
Design Arena Full-stack Agent: 1096 Elo2026-08-02
Design Arena Full-stack Agent: 1096 Elo2026-08-05
Design Arena Full-stack Agent: 1094 Elo2026-08-01
Design Arena Full-stack Agent: 1086 Elo2026-08-09
Design Arena Full-stack Agent: 1096 Elo2026-08-03
Design Arena Full-stack Agent: 1096 Elo2026-08-04
Design Arena Full-stack Agent: 1086 Elo2026-08-14
Design Arena Full-stack Agent: 1095 Elo2026-08-06
Design Arena Full-stack Agent: 1084 Elo2026-08-10
Design Arena Full-stack Agent: 1095 Elo2026-08-07
Design Arena Full-stack Agent: 1083 Elo2026-08-18
Design Arena Full-stack Agent: 1095 Elo2026-08-08
Design Arena Full-stack Agent: 1087 Elo2026-08-11
Design Arena Full-stack Agent: 1089 Elo2026-08-15
Design Arena Full-stack Agent: 1087 Elo2026-08-12
Design Arena Full-stack Agent: 1087 Elo2026-08-13
Design Arena Full-stack Agent: 1083 Elo2026-08-19
Design Arena Full-stack Agent: 1074 Elo2026-08-27
Design Arena Full-stack Agent: 1083 Elo2026-08-20
Design Arena Full-stack Agent: 1088 Elo2026-08-16
Design Arena Full-stack Agent: 1064 Elo2026-09-05
Design Arena Full-stack Agent: 1089 Elo2026-08-17
Design Arena Full-stack Agent: 1085 Elo2026-08-21
Design Arena Full-stack Agent: 1084 Elo2026-08-22
Design Arena Full-stack Agent: 1084 Elo2026-08-23
Design Arena Full-stack Agent: 1074 Elo2026-08-28
Design Arena Full-stack Agent: 1071 Elo2026-08-24
Design Arena Full-stack Agent: 1074 Elo2026-08-25
Design Arena Full-stack Agent: 1074 Elo2026-08-26
Design Arena Full-stack Agent: 1062 Elo2026-09-06
Design Arena Full-stack Agent: 1074 Elo2026-08-29
Design Arena Full-stack Agent: 1074 Elo2026-08-30
Design Arena Full-stack Agent: 1074 Elo2026-08-31
Design Arena Full-stack Agent: 1074 Elo2026-09-01
Design Arena Full-stack Agent: 1075 Elo2026-09-02
Design Arena Full-stack Agent: 1075 Elo2026-09-03
Design Arena Full-stack Agent: 1075 Elo2026-09-04
Design Arena UI: 1197 Elo2026-07-28
Design Arena UI: 1197 Elo2026-07-27
Design Arena UI: 1198 Elo2026-07-30
Design Arena UI: 1198 Elo2026-07-29
Design Arena UI: 1198 Elo2026-07-31
Design Arena UI: 1199 Elo2026-08-02
Design Arena UI: 1199 Elo2026-08-01
Design Arena UI: 1198 Elo2026-08-05
Design Arena UI: 1195 Elo2026-08-09
Design Arena UI: 1199 Elo2026-08-03
Design Arena UI: 1199 Elo2026-08-04
Design Arena UI: 1193 Elo2026-08-14
Design Arena UI: 1198 Elo2026-08-06
Design Arena UI: 1197 Elo2026-08-07
Design Arena UI: 1195 Elo2026-08-10
Design Arena UI: 1196 Elo2026-08-08
Design Arena UI: 1189 Elo2026-08-18
Design Arena UI: 1195 Elo2026-08-11
Design Arena UI: 1190 Elo2026-08-15
Design Arena UI: 1195 Elo2026-08-12
Design Arena UI: 1195 Elo2026-08-13
Design Arena UI: 1189 Elo2026-08-19
Design Arena UI: 1189 Elo2026-08-16
Design Arena UI: 1189 Elo2026-08-20
Design Arena UI: 1187 Elo2026-08-27
Design Arena UI: 1189 Elo2026-08-17
Design Arena UI: 1184 Elo2026-09-05
Design Arena UI: 1188 Elo2026-08-21
Design Arena UI: 1188 Elo2026-08-22
Design Arena UI: 1188 Elo2026-08-23
Design Arena UI: 1188 Elo2026-08-24
Design Arena UI: 1187 Elo2026-08-28
Design Arena UI: 1188 Elo2026-08-25
Design Arena UI: 1188 Elo2026-08-26
Design Arena UI: 1184 Elo2026-09-06
Design Arena UI: 1188 Elo2026-08-29
Design Arena UI: 1188 Elo2026-08-30
Design Arena UI: 1188 Elo2026-08-31
Design Arena UI: 1187 Elo2026-09-01
Design Arena UI: 1187 Elo2026-09-02
Design Arena UI: 1185 Elo2026-09-03
Design Arena UI: 1183 Elo2026-09-04
Design Arena Web-app Agent: 1126 Elo2026-07-28
Design Arena Web-app Agent: 1126 Elo2026-07-27
Design Arena Web-app Agent: 1124 Elo2026-07-30
Design Arena Web-app Agent: 1124 Elo2026-07-29
Design Arena Web-app Agent: 1124 Elo2026-07-31
Design Arena Web-app Agent: 1125 Elo2026-08-02
Design Arena Web-app Agent: 1125 Elo2026-08-01
Design Arena Web-app Agent: 1112 Elo2026-08-05
Design Arena Web-app Agent: 1106 Elo2026-08-09
Design Arena Web-app Agent: 1125 Elo2026-08-03
Design Arena Web-app Agent: 1125 Elo2026-08-04
Design Arena Web-app Agent: 1101 Elo2026-08-14
Design Arena Web-app Agent: 1112 Elo2026-08-06
Design Arena Web-app Agent: 1104 Elo2026-08-10
Design Arena Web-app Agent: 1112 Elo2026-08-07
Design Arena Web-app Agent: 1100 Elo2026-08-18
Design Arena Web-app Agent: 1112 Elo2026-08-08
Design Arena Web-app Agent: 1104 Elo2026-08-11
Design Arena Web-app Agent: 1103 Elo2026-08-15
Design Arena Web-app Agent: 1104 Elo2026-08-12
Design Arena Web-app Agent: 1104 Elo2026-08-13
Design Arena Web-app Agent: 1100 Elo2026-08-19
Design Arena Web-app Agent: 1091 Elo2026-08-27
Design Arena Web-app Agent: 1100 Elo2026-08-20
Design Arena Web-app Agent: 1103 Elo2026-08-16
Design Arena Web-app Agent: 1104 Elo2026-08-17
Design Arena Web-app Agent: 1090 Elo2026-09-05
Design Arena Web-app Agent: 1096 Elo2026-08-21
Design Arena Web-app Agent: 1097 Elo2026-08-22
Design Arena Web-app Agent: 1097 Elo2026-08-23
Design Arena Web-app Agent: 1091 Elo2026-08-28
Design Arena Web-app Agent: 1092 Elo2026-08-24
Design Arena Web-app Agent: 1093 Elo2026-08-25
Design Arena Web-app Agent: 1093 Elo2026-08-26
Design Arena Web-app Agent: 1090 Elo2026-09-06
Design Arena Web-app Agent: 1091 Elo2026-08-29
Design Arena Web-app Agent: 1091 Elo2026-08-30
Design Arena Web-app Agent: 1090 Elo2026-08-31
Design Arena Web-app Agent: 1090 Elo2026-09-01
Design Arena Web-app Agent: 1090 Elo2026-09-02
Design Arena Web-app Agent: 1090 Elo2026-09-03
Design Arena Web-app Agent: 1090 Elo2026-09-04
Design Arena Website: 1214 Elo2026-07-28
Design Arena Website: 1214 Elo2026-07-30
Design Arena Website: 1214 Elo2026-07-27
Design Arena Website: 1214 Elo2026-07-29
Design Arena Website: 1214 Elo2026-07-31
Design Arena Website: 1213 Elo2026-08-02
Design Arena Website: 1213 Elo2026-08-01
Design Arena Website: 1213 Elo2026-08-05
Design Arena Website: 1213 Elo2026-08-03
Design Arena Website: 1212 Elo2026-08-09
Design Arena Website: 1213 Elo2026-08-04
Design Arena Website: 1209 Elo2026-08-14
Design Arena Website: 1213 Elo2026-08-06
Design Arena Website: 1213 Elo2026-08-07
Design Arena Website: 1212 Elo2026-08-10
Design Arena Website: 1212 Elo2026-08-08
Design Arena Website: 1201 Elo2026-08-18
Design Arena Website: 1212 Elo2026-08-11
Design Arena Website: 1200 Elo2026-08-15
Design Arena Website: 1211 Elo2026-08-12
Design Arena Website: 1209 Elo2026-08-13
Design Arena Website: 1201 Elo2026-08-19
Design Arena Website: 1200 Elo2026-08-16
Design Arena Website: 1201 Elo2026-08-20
Design Arena Website: 1209 Elo2026-08-27
Design Arena Website: 1200 Elo2026-08-17
Design Arena Website: 1205 Elo2026-09-05
Design Arena Website: 1209 Elo2026-08-21
Design Arena Website: 1209 Elo2026-08-22
Design Arena Website: 1209 Elo2026-08-23
Design Arena Website: 1209 Elo2026-08-24
Design Arena Website: 1209 Elo2026-08-28
Design Arena Website: 1210 Elo2026-08-25
Design Arena Website: 1210 Elo2026-08-26
Design Arena Website: 1203 Elo2026-09-06
Design Arena Website: 1209 Elo2026-08-29
Design Arena Website: 1208 Elo2026-08-30
Design Arena Website: 1209 Elo2026-08-31
Design Arena Website: 1209 Elo2026-09-01
Design Arena Website: 1208 Elo2026-09-02
Design Arena Website: 1206 Elo2026-09-03
Design Arena Website: 1205 Elo2026-09-04
LMArena Creative Writing: 1441 Elo2026-07-21
LMArena Creative Writing: 1441 Elo2026-07-27
LMArena Creative Writing: 1441 Elo2026-07-30
LMArena Creative Writing: 1441 Elo2026-08-02
LMArena Creative Writing: 1441 Elo2026-08-03
LMArena Creative Writing: 1441 Elo2026-08-06
LMArena Creative Writing: 1441 Elo2026-08-12
LMArena Creative Writing: 1441 Elo2026-08-21
LMArena Creative Writing: 1441 Elo2026-09-02
LMArena Creative Writing: 1441 Elo2026-08-27
LMArena Creative Writing: 1441 Elo2026-09-01
LMArena Instruction Following: 1459 Elo2026-07-21
LMArena Instruction Following: 1459 Elo2026-07-27
LMArena Instruction Following: 1459 Elo2026-07-30
LMArena Instruction Following: 1459 Elo2026-08-02
LMArena Instruction Following: 1459 Elo2026-08-03
LMArena Instruction Following: 1459 Elo2026-08-06
LMArena Instruction Following: 1459 Elo2026-08-12
LMArena Instruction Following: 1459 Elo2026-08-21
LMArena Instruction Following: 1459 Elo2026-09-02
LMArena Instruction Following: 1459 Elo2026-08-27
LMArena Instruction Following: 1459 Elo2026-09-01
LMArena Long Query: 1476 Elo2026-07-21
LMArena Long Query: 1476 Elo2026-07-27
LMArena Long Query: 1476 Elo2026-07-30
LMArena Long Query: 1476 Elo2026-08-02
LMArena Long Query: 1476 Elo2026-08-03
LMArena Long Query: 1476 Elo2026-08-06
LMArena Long Query: 1476 Elo2026-08-12
LMArena Long Query: 1476 Elo2026-08-21
LMArena Long Query: 1476 Elo2026-09-02
LMArena Long Query: 1476 Elo2026-08-27
LMArena Long Query: 1476 Elo2026-09-01
LMArena Math: 1422 Elo2026-07-21
LMArena Math: 1448 Elo2026-07-27
LMArena Math: 1448 Elo2026-07-30
LMArena Math: 1448 Elo2026-08-02
LMArena Math: 1448 Elo2026-08-03
LMArena Math: 1448 Elo2026-08-06
LMArena Math: 1448 Elo2026-08-12
LMArena Math: 1448 Elo2026-08-21
LMArena Math: 1448 Elo2026-09-01
LMArena Math: 1448 Elo2026-08-27
LMArena Text: 1438 Elo2026-07-16
LMArena Text: 1455 Elo2026-07-21
LMArena Text: 1456 Elo2026-08-02
LMArena Text: 1456 Elo2026-07-27
LMArena Text: 1456 Elo2026-07-30
LMArena Text: 1456 Elo2026-08-10
LMArena Text: 1456 Elo2026-08-06
LMArena Text: 1456 Elo2026-08-03
LMArena Text: 1456 Elo2026-08-21
LMArena Text: 1456 Elo2026-08-12
LMArena Text: 1456 Elo2026-09-01
LMArena Text: 1456 Elo2026-09-02
LMArena Text: 1456 Elo2026-08-27
LMArena WebDev: 1386 Elo2026-07-16
LMArena WebDev: 1388 Elo2026-07-21
LMArena WebDev: 1386 Elo2026-07-20
LMArena WebDev: 1392 Elo2026-07-27
LMArena WebDev: 1392 Elo2026-07-24
LMArena WebDev: 1392 Elo2026-07-28
LMArena WebDev: 1392 Elo2026-07-30
LMArena WebDev: 1392 Elo2026-08-01
LMArena WebDev: 1392 Elo2026-07-31
LMArena WebDev: 1392 Elo2026-08-06
LMArena WebDev: 1392 Elo2026-08-02
LMArena WebDev: 1392 Elo2026-08-12
LMArena WebDev: 1392 Elo2026-08-10
LMArena WebDev: 1392 Elo2026-08-14
LMArena WebDev: 1393 Elo2026-09-01
LMArena WebDev: 1392 Elo2026-09-05
LMArena WebDev: 1392 Elo2026-08-21
LMArena WebDev: 1392 Elo2026-08-30
SWE-bench Verified: 74.8%2025-11-03
SWE-rebench^‡: 52.4% ± 0.82026-03-01tools

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.

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
90% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Debugging & Code ReviewEstablished evidence
65% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.
Best LLM for CodingEstablished evidence
64% of intended weighted task evidence across 4 independent sources. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Business WritingProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Marketing CopyProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Chat & RoleplayProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Roleplay & CharacterProvisional evidence
70% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Tool & Function CallingProvisional evidence
65% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Search. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Creative WritingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for WritingProvisional evidence
60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Hermes AgentProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenHandsProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for GooseProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 configured evaluation feeds currently have results.
Best LLM for OpenClawProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LMArena Agent or Terminal-Bench 2.1. 5 of 5 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 LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Logic & Problem SolvingProvisional evidence
50% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 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 AI AgentsProvisional evidence
50% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 7 of 7 configured evaluation feeds currently have results.
Best LLM for Code CompletionProvisional evidence
44% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.
Best LLM for Agentic CodingProvisional evidence
41% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Document SummarizationProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
Best LLM for Competition MathProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best LLM for SummarizationProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.
Best LLM for Math & ReasoningProvisional evidence
40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.
Best Local LLM for CodingProvisional evidence
40% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.
Best Value LLMProvisional evidence
36% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for RAG & Long ContextProvisional evidence
35% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Search. 4 of 6 configured evaluation feeds currently have results.
Best LLM for JSON & Schema OutputProvisional evidence
33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Structured Data ExtractionProvisional evidence
33% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Structured-output eval. 4 of 5 configured evaluation feeds currently have results.
Best Open-Weight LLM for Self-HostingProvisional evidence
33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for OCR & DocumentsProvisional evidence
30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Vision & DocumentsProvisional evidence
30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Charts & DiagramsProvisional evidence
30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Document ParsingProvisional evidence
30% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Vision or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.
Best LLM for Autonomous AgentsProvisional evidence
29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 configured evaluation feeds currently have results.
Best LLM for Fast SummariesProvisional evidence
29% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Literary TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Best Cheap LLM for High VolumeProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Everyday TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Cheapest Capable LLMProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 3 of 4 configured evaluation feeds currently have results.
Best LLM for TranslationProvisional evidence
25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Computer & Browser UseProvisional evidence
20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 4 of 4 configured evaluation feeds currently have results.
Best LLM for High-Volume ExtractionProvisional evidence
13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Data Analysis or Route reliability. 2 of 4 configured evaluation feeds currently have results.
Best LLM for Image UnderstandingProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Reasoning or LMArena Vision. 3 of 4 configured evaluation feeds currently have results.
Best LLM for Grounded RAGProvisional evidence
10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from CRAG or FACTS Grounding. 2 of 5 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

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