Gemini 3.1 Pro Preview

google/gemini-3.1-pro-preview-20260219

Google's Gemini 3.1 Pro Preview, released on 2026-02-19, accepts audio, file, image, text, and video inputs and produces text output. It supports tools and reasoning, provides a context window of 1,048,576 tokens, and is priced at $2 per million input tokens and $12 per million output tokens. The model is not open weights.

tool use
structured outputs
reasoning

At a glance

providergoogle

releasedFeb 18, 2026

context1.0M

input / M$2

Specifications

What the API gives you

Context window: 1.0M tokens
Max output: 66K tokens
Input price: $2 / 1M tokens
Output price: $12 / 1M tokens
Cache read: $0.20 / 1M tokens
Modalities: audio, file, image, text, video → text
Knowledge cutoff: —
Released: Feb 18, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1260 Elo2026-07-28
Design Arena Coding: 1260 Elo2026-07-27
Design Arena Coding: 1260 Elo2026-07-30
Design Arena Coding: 1260 Elo2026-07-29
Design Arena Coding: 1259 Elo2026-07-31
Design Arena Coding: 1259 Elo2026-08-02
Design Arena Coding: 1259 Elo2026-08-05
Design Arena Coding: 1259 Elo2026-08-01
Design Arena Coding: 1258 Elo2026-08-09
Design Arena Coding: 1259 Elo2026-08-03
Design Arena Coding: 1259 Elo2026-08-04
Design Arena Coding: 1255 Elo2026-08-14
Design Arena Coding: 1259 Elo2026-08-06
Design Arena Coding: 1258 Elo2026-08-10
Design Arena Coding: 1259 Elo2026-08-07
Design Arena Coding: 1249 Elo2026-08-18
Design Arena Coding: 1258 Elo2026-08-08
Design Arena Coding: 1250 Elo2026-08-15
Design Arena Coding: 1258 Elo2026-08-11
Design Arena Coding: 1257 Elo2026-08-12
Design Arena Coding: 1255 Elo2026-08-13
Design Arena Coding: 1248 Elo2026-08-19
Design Arena Coding: 1255 Elo2026-08-21
Design Arena Coding: 1255 Elo2026-08-27
Design Arena Coding: 1248 Elo2026-08-20
Design Arena Coding: 1250 Elo2026-08-16
Design Arena Coding: 1247 Elo2026-09-05
Design Arena Coding: 1249 Elo2026-08-17
Design Arena Coding: 1255 Elo2026-08-22
Design Arena Coding: 1255 Elo2026-08-23
Design Arena Coding: 1255 Elo2026-08-28
Design Arena Coding: 1255 Elo2026-08-24
Design Arena Coding: 1255 Elo2026-08-25
Design Arena Coding: 1255 Elo2026-08-26
Design Arena Coding: 1247 Elo2026-09-06
Design Arena Coding: 1254 Elo2026-08-29
Design Arena Coding: 1254 Elo2026-08-30
Design Arena Coding: 1254 Elo2026-08-31
Design Arena Coding: 1255 Elo2026-09-01
Design Arena Coding: 1253 Elo2026-09-02
Design Arena Coding: 1251 Elo2026-09-03
Design Arena Coding: 1250 Elo2026-09-04
Design Arena Full-stack Agent: 1114 Elo2026-07-28
Design Arena Full-stack Agent: 1115 Elo2026-07-27
Design Arena Full-stack Agent: 1107 Elo2026-07-30
Design Arena Full-stack Agent: 1109 Elo2026-07-29
Design Arena Full-stack Agent: 1108 Elo2026-07-31
Design Arena Full-stack Agent: 1111 Elo2026-08-02
Design Arena Full-stack Agent: 1110 Elo2026-08-05
Design Arena Full-stack Agent: 1110 Elo2026-08-01
Design Arena Full-stack Agent: 1102 Elo2026-08-09
Design Arena Full-stack Agent: 1112 Elo2026-08-03
Design Arena Full-stack Agent: 1110 Elo2026-08-04
Design Arena Full-stack Agent: 1101 Elo2026-08-14
Design Arena Full-stack Agent: 1110 Elo2026-08-06
Design Arena Full-stack Agent: 1100 Elo2026-08-10
Design Arena Full-stack Agent: 1109 Elo2026-08-07
Design Arena Full-stack Agent: 1099 Elo2026-08-18
Design Arena Full-stack Agent: 1109 Elo2026-08-08
Design Arena Full-stack Agent: 1103 Elo2026-08-11
Design Arena Full-stack Agent: 1104 Elo2026-08-15
Design Arena Full-stack Agent: 1104 Elo2026-08-12
Design Arena Full-stack Agent: 1102 Elo2026-08-13
Design Arena Full-stack Agent: 1100 Elo2026-08-19
Design Arena Full-stack Agent: 1094 Elo2026-08-27
Design Arena Full-stack Agent: 1100 Elo2026-08-20
Design Arena Full-stack Agent: 1105 Elo2026-08-16
Design Arena Full-stack Agent: 1084 Elo2026-09-05
Design Arena Full-stack Agent: 1105 Elo2026-08-17
Design Arena Full-stack Agent: 1103 Elo2026-08-21
Design Arena Full-stack Agent: 1103 Elo2026-08-22
Design Arena Full-stack Agent: 1103 Elo2026-08-23
Design Arena Full-stack Agent: 1093 Elo2026-08-28
Design Arena Full-stack Agent: 1091 Elo2026-08-24
Design Arena Full-stack Agent: 1094 Elo2026-08-25
Design Arena Full-stack Agent: 1095 Elo2026-08-26
Design Arena Full-stack Agent: 1081 Elo2026-09-06
Design Arena Full-stack Agent: 1094 Elo2026-08-29
Design Arena Full-stack Agent: 1095 Elo2026-08-30
Design Arena Full-stack Agent: 1094 Elo2026-08-31
Design Arena Full-stack Agent: 1094 Elo2026-09-01
Design Arena Full-stack Agent: 1095 Elo2026-09-02
Design Arena Full-stack Agent: 1095 Elo2026-09-03
Design Arena Full-stack Agent: 1095 Elo2026-09-04
Design Arena UI: 1266 Elo2026-07-28
Design Arena UI: 1266 Elo2026-07-27
Design Arena UI: 1265 Elo2026-07-30
Design Arena UI: 1266 Elo2026-07-29
Design Arena UI: 1264 Elo2026-07-31
Design Arena UI: 1264 Elo2026-08-02
Design Arena UI: 1264 Elo2026-08-01
Design Arena UI: 1263 Elo2026-08-05
Design Arena UI: 1260 Elo2026-08-09
Design Arena UI: 1263 Elo2026-08-03
Design Arena UI: 1264 Elo2026-08-04
Design Arena UI: 1258 Elo2026-08-14
Design Arena UI: 1263 Elo2026-08-06
Design Arena UI: 1263 Elo2026-08-07
Design Arena UI: 1260 Elo2026-08-10
Design Arena UI: 1260 Elo2026-08-08
Design Arena UI: 1256 Elo2026-08-18
Design Arena UI: 1259 Elo2026-08-11
Design Arena UI: 1257 Elo2026-08-15
Design Arena UI: 1260 Elo2026-08-12
Design Arena UI: 1260 Elo2026-08-13
Design Arena UI: 1256 Elo2026-08-19
Design Arena UI: 1254 Elo2026-08-27
Design Arena UI: 1257 Elo2026-08-16
Design Arena UI: 1256 Elo2026-08-20
Design Arena UI: 1256 Elo2026-08-17
Design Arena UI: 1250 Elo2026-09-05
Design Arena UI: 1254 Elo2026-08-21
Design Arena UI: 1255 Elo2026-08-22
Design Arena UI: 1255 Elo2026-08-23
Design Arena UI: 1254 Elo2026-08-28
Design Arena UI: 1255 Elo2026-08-24
Design Arena UI: 1256 Elo2026-08-25
Design Arena UI: 1256 Elo2026-08-26
Design Arena UI: 1251 Elo2026-09-06
Design Arena UI: 1254 Elo2026-08-29
Design Arena UI: 1254 Elo2026-08-30
Design Arena UI: 1255 Elo2026-08-31
Design Arena UI: 1254 Elo2026-09-01
Design Arena UI: 1253 Elo2026-09-02
Design Arena UI: 1251 Elo2026-09-03
Design Arena UI: 1249 Elo2026-09-04
Design Arena Web-app Agent: 1179 Elo2026-07-28
Design Arena Web-app Agent: 1179 Elo2026-07-27
Design Arena Web-app Agent: 1178 Elo2026-07-30
Design Arena Web-app Agent: 1178 Elo2026-07-29
Design Arena Web-app Agent: 1178 Elo2026-07-31
Design Arena Web-app Agent: 1179 Elo2026-08-02
Design Arena Web-app Agent: 1179 Elo2026-08-01
Design Arena Web-app Agent: 1173 Elo2026-08-05
Design Arena Web-app Agent: 1168 Elo2026-08-09
Design Arena Web-app Agent: 1179 Elo2026-08-03
Design Arena Web-app Agent: 1179 Elo2026-08-04
Design Arena Web-app Agent: 1164 Elo2026-08-14
Design Arena Web-app Agent: 1173 Elo2026-08-06
Design Arena Web-app Agent: 1165 Elo2026-08-10
Design Arena Web-app Agent: 1173 Elo2026-08-07
Design Arena Web-app Agent: 1169 Elo2026-08-18
Design Arena Web-app Agent: 1174 Elo2026-08-08
Design Arena Web-app Agent: 1165 Elo2026-08-11
Design Arena Web-app Agent: 1170 Elo2026-08-15
Design Arena Web-app Agent: 1166 Elo2026-08-12
Design Arena Web-app Agent: 1165 Elo2026-08-13
Design Arena Web-app Agent: 1169 Elo2026-08-19
Design Arena Web-app Agent: 1157 Elo2026-08-27
Design Arena Web-app Agent: 1169 Elo2026-08-20
Design Arena Web-app Agent: 1172 Elo2026-08-16
Design Arena Web-app Agent: 1155 Elo2026-09-05
Design Arena Web-app Agent: 1172 Elo2026-08-17
Design Arena Web-app Agent: 1162 Elo2026-08-21
Design Arena Web-app Agent: 1163 Elo2026-08-22
Design Arena Web-app Agent: 1163 Elo2026-08-23
Design Arena Web-app Agent: 1157 Elo2026-08-28
Design Arena Web-app Agent: 1157 Elo2026-08-24
Design Arena Web-app Agent: 1158 Elo2026-08-25
Design Arena Web-app Agent: 1158 Elo2026-08-26
Design Arena Web-app Agent: 1155 Elo2026-09-06
Design Arena Web-app Agent: 1157 Elo2026-08-29
Design Arena Web-app Agent: 1155 Elo2026-08-30
Design Arena Web-app Agent: 1156 Elo2026-08-31
Design Arena Web-app Agent: 1155 Elo2026-09-01
Design Arena Web-app Agent: 1155 Elo2026-09-02
Design Arena Web-app Agent: 1155 Elo2026-09-03
Design Arena Web-app Agent: 1155 Elo2026-09-04
Design Arena Website: 1257 Elo2026-07-28
Design Arena Website: 1257 Elo2026-07-30
Design Arena Website: 1257 Elo2026-07-27
Design Arena Website: 1257 Elo2026-07-29
Design Arena Website: 1257 Elo2026-07-31
Design Arena Website: 1257 Elo2026-08-02
Design Arena Website: 1256 Elo2026-08-01
Design Arena Website: 1256 Elo2026-08-05
Design Arena Website: 1257 Elo2026-08-03
Design Arena Website: 1255 Elo2026-08-09
Design Arena Website: 1257 Elo2026-08-04
Design Arena Website: 1253 Elo2026-08-14
Design Arena Website: 1256 Elo2026-08-06
Design Arena Website: 1256 Elo2026-08-07
Design Arena Website: 1255 Elo2026-08-10
Design Arena Website: 1255 Elo2026-08-08
Design Arena Website: 1245 Elo2026-08-18
Design Arena Website: 1255 Elo2026-08-11
Design Arena Website: 1245 Elo2026-08-15
Design Arena Website: 1255 Elo2026-08-12
Design Arena Website: 1253 Elo2026-08-13
Design Arena Website: 1245 Elo2026-08-19
Design Arena Website: 1244 Elo2026-08-16
Design Arena Website: 1245 Elo2026-08-20
Design Arena Website: 1252 Elo2026-08-27
Design Arena Website: 1245 Elo2026-08-17
Design Arena Website: 1249 Elo2026-09-05
Design Arena Website: 1252 Elo2026-08-21
Design Arena Website: 1252 Elo2026-08-22
Design Arena Website: 1252 Elo2026-08-23
Design Arena Website: 1252 Elo2026-08-24
Design Arena Website: 1253 Elo2026-08-28
Design Arena Website: 1253 Elo2026-08-25
Design Arena Website: 1253 Elo2026-08-26
Design Arena Website: 1247 Elo2026-09-06
Design Arena Website: 1252 Elo2026-08-29
Design Arena Website: 1252 Elo2026-08-30
Design Arena Website: 1252 Elo2026-08-31
Design Arena Website: 1252 Elo2026-09-01
Design Arena Website: 1251 Elo2026-09-02
Design Arena Website: 1249 Elo2026-09-03
Design Arena Website: 1248 Elo2026-09-04
LiveBench Agentic Coding: 44.1%2026-06-25
LiveBench Coding: 76.5%2026-06-25
LiveBench Data Analysis: 78.5%2026-06-25
LiveBench Instruction Following: 79.1%2026-06-25
LiveBench Language: 85.4%2026-06-25
LiveBench Math: 91.0%2026-06-25
LiveBench Reasoning: 84%2026-06-25
LMArena Agent: -0.72026-07-13
LMArena Agent: -0.22026-07-20
LMArena Agent: -0.32026-07-27
LMArena Agent: -0.52026-07-21
LMArena Agent: -0.52026-07-28
LMArena Agent: -0.52026-08-03
LMArena Agent: -0.52026-08-12
LMArena Agent: -0.52026-08-06
LMArena Agent: -0.62026-08-11
LMArena Agent: -0.42026-08-13
LMArena Agent: -2.42026-08-24
LMArena Agent: -3.12026-08-31
LMArena Agent: -3.72026-09-05
LMArena Agent: -2.62026-08-27
LMArena Creative Writing: 1480 Elo2026-07-21
LMArena Creative Writing: 1482 Elo2026-07-27
LMArena Creative Writing: 1482 Elo2026-07-30
LMArena Creative Writing: 1481 Elo2026-08-02
LMArena Creative Writing: 1481 Elo2026-08-03
LMArena Creative Writing: 1483 Elo2026-08-06
LMArena Creative Writing: 1483 Elo2026-08-12
LMArena Creative Writing: 1482 Elo2026-08-21
LMArena Creative Writing: 1480 Elo2026-09-02
LMArena Creative Writing: 1481 Elo2026-08-27
LMArena Creative Writing: 1480 Elo2026-09-01
LMArena Instruction Following: 1468 Elo2026-07-21
LMArena Instruction Following: 1467 Elo2026-07-27
LMArena Instruction Following: 1467 Elo2026-07-30
LMArena Instruction Following: 1466 Elo2026-08-02
LMArena Instruction Following: 1466 Elo2026-08-03
LMArena Instruction Following: 1467 Elo2026-08-06
LMArena Instruction Following: 1466 Elo2026-08-12
LMArena Instruction Following: 1466 Elo2026-08-21
LMArena Instruction Following: 1467 Elo2026-09-02
LMArena Instruction Following: 1467 Elo2026-08-27
LMArena Instruction Following: 1466 Elo2026-09-01
LMArena Long Query: 1482 Elo2026-07-21
LMArena Long Query: 1482 Elo2026-07-27
LMArena Long Query: 1482 Elo2026-07-30
LMArena Long Query: 1482 Elo2026-08-02
LMArena Long Query: 1482 Elo2026-08-03
LMArena Long Query: 1483 Elo2026-08-06
LMArena Long Query: 1483 Elo2026-08-12
LMArena Long Query: 1483 Elo2026-08-21
LMArena Long Query: 1483 Elo2026-09-02
LMArena Long Query: 1484 Elo2026-08-27
LMArena Long Query: 1483 Elo2026-09-01
LMArena Math: 1488 Elo2026-07-21
LMArena Math: 1489 Elo2026-07-27
LMArena Math: 1489 Elo2026-07-30
LMArena Math: 1489 Elo2026-08-02
LMArena Math: 1489 Elo2026-08-03
LMArena Math: 1488 Elo2026-08-06
LMArena Math: 1487 Elo2026-08-12
LMArena Math: 1487 Elo2026-08-21
LMArena Math: 1485 Elo2026-09-01
LMArena Math: 1486 Elo2026-08-27
LMArena Text: 1479 Elo2026-07-16
LMArena Text: 1489 Elo2026-07-20
LMArena Text: 1486 Elo2026-07-21
LMArena Text: 1486 Elo2026-07-27
LMArena Text: 1486 Elo2026-07-30
LMArena Text: 1485 Elo2026-08-02
LMArena Text: 1487 Elo2026-08-06
LMArena Text: 1485 Elo2026-08-03
LMArena Text: 1486 Elo2026-08-12
LMArena Text: 1486 Elo2026-08-10
LMArena Text: 1486 Elo2026-08-21
LMArena Text: 1487 Elo2026-09-01
LMArena Text: 1487 Elo2026-09-02
LMArena Text: 1487 Elo2026-08-27
LMArena Vision: 1296 Elo2026-07-12
LMArena Vision: 1277 Elo2026-07-21
LMArena Vision: 1278 Elo2026-07-26
LMArena Vision: 1278 Elo2026-07-30
LMArena Vision: 1278 Elo2026-08-02
LMArena Vision: 1277 Elo2026-08-06
LMArena Vision: 1277 Elo2026-08-21
LMArena Vision: 1278 Elo2026-08-27
LMArena WebDev: 1444 Elo2026-07-16
LMArena WebDev: 1444 Elo2026-07-21
LMArena WebDev: 1444 Elo2026-07-20
LMArena WebDev: 1446 Elo2026-07-27
LMArena WebDev: 1446 Elo2026-07-24
LMArena WebDev: 1446 Elo2026-07-28
LMArena WebDev: 1446 Elo2026-07-30
LMArena WebDev: 1447 Elo2026-08-01
LMArena WebDev: 1447 Elo2026-07-31
LMArena WebDev: 1446 Elo2026-08-06
LMArena WebDev: 1447 Elo2026-08-02
LMArena WebDev: 1447 Elo2026-08-12
LMArena WebDev: 1447 Elo2026-08-10
LMArena WebDev: 1447 Elo2026-08-14
LMArena WebDev: 1446 Elo2026-09-01
LMArena WebDev: 1446 Elo2026-09-05
LMArena WebDev: 1446 Elo2026-08-21
LMArena WebDev: 1446 Elo2026-08-30
SWE-rebench^‡: 54.9% ± 0.92026-05-15tools
Terminal-Bench 2.1^‡: 65.8% ± 1.72026-05-05high 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 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 Agentic CodingEstablished evidence
86% of intended weighted task evidence across 5 independent sources. 8 of 8 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 Autonomous AgentsEstablished evidence
77% of intended weighted task evidence across 4 independent sources. 7 of 7 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 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 AI AgentsProvisional evidence
60% of intended weighted task evidence across 4 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 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 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 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 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 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 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

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.