Gemini 3 Flash Preview

google/gemini-3-flash-preview-20251217

Google Gemini 3 Flash Preview is a multimodal model that accepts text, image, file, audio, and video inputs and produces text output. It supports tool usage and reasoning, offers a context length of 1,048,576 tokens, and is priced at $0.5 per million input tokens and $3 per million output tokens. The model, released on December 17 2025, does not have open weights.

tool use
structured outputs
reasoning

At a glance

providergoogle

releasedDec 17, 2025

context1.0M

input / M$0.50

Specifications

What the API gives you

Context window: 1.0M tokens
Max output: 66K tokens
Input price: $0.50 / 1M tokens
Output price: $3 / 1M tokens
Cache read: $0.050 / 1M tokens
Modalities: text, image, file, audio, video → text
Knowledge cutoff: —
Released: Dec 17, 2025

Measured evidence

Public benchmark record

Design Arena Coding: 1220 Elo2026-07-28
Design Arena Coding: 1220 Elo2026-07-27
Design Arena Coding: 1220 Elo2026-07-30
Design Arena Coding: 1220 Elo2026-07-29
Design Arena Coding: 1220 Elo2026-07-31
Design Arena Coding: 1219 Elo2026-08-02
Design Arena Coding: 1218 Elo2026-08-05
Design Arena Coding: 1219 Elo2026-08-01
Design Arena Coding: 1217 Elo2026-08-09
Design Arena Coding: 1219 Elo2026-08-03
Design Arena Coding: 1218 Elo2026-08-04
Design Arena Coding: 1214 Elo2026-08-14
Design Arena Coding: 1218 Elo2026-08-06
Design Arena Coding: 1217 Elo2026-08-10
Design Arena Coding: 1218 Elo2026-08-07
Design Arena Coding: 1208 Elo2026-08-18
Design Arena Coding: 1217 Elo2026-08-08
Design Arena Coding: 1209 Elo2026-08-15
Design Arena Coding: 1217 Elo2026-08-11
Design Arena Coding: 1216 Elo2026-08-12
Design Arena Coding: 1214 Elo2026-08-13
Design Arena Coding: 1207 Elo2026-08-19
Design Arena Coding: 1214 Elo2026-08-27
Design Arena Coding: 1214 Elo2026-08-21
Design Arena Coding: 1207 Elo2026-08-20
Design Arena Coding: 1208 Elo2026-08-16
Design Arena Coding: 1208 Elo2026-08-17
Design Arena Coding: 1214 Elo2026-08-22
Design Arena Coding: 1214 Elo2026-08-23
Design Arena Coding: 1213 Elo2026-08-28
Design Arena Coding: 1214 Elo2026-08-24
Design Arena Coding: 1214 Elo2026-08-25
Design Arena Coding: 1214 Elo2026-08-26
Design Arena Coding: 1213 Elo2026-08-29
Design Arena Coding: 1213 Elo2026-08-30
Design Arena Coding: 1213 Elo2026-08-31
Design Arena Coding: 1213 Elo2026-09-01
Design Arena Coding: 1212 Elo2026-09-02
Design Arena Coding: 1210 Elo2026-09-03
Design Arena Coding: 1209 Elo2026-09-04
Design Arena Full-stack Agent: 1109 Elo2026-07-28
Design Arena Full-stack Agent: 1111 Elo2026-07-27
Design Arena Full-stack Agent: 1102 Elo2026-07-30
Design Arena Full-stack Agent: 1104 Elo2026-07-29
Design Arena Full-stack Agent: 1103 Elo2026-07-31
Design Arena Full-stack Agent: 1106 Elo2026-08-02
Design Arena Full-stack Agent: 1105 Elo2026-08-05
Design Arena Full-stack Agent: 1104 Elo2026-08-01
Design Arena Full-stack Agent: 1096 Elo2026-08-09
Design Arena Full-stack Agent: 1106 Elo2026-08-03
Design Arena Full-stack Agent: 1105 Elo2026-08-04
Design Arena Full-stack Agent: 1096 Elo2026-08-14
Design Arena Full-stack Agent: 1104 Elo2026-08-06
Design Arena Full-stack Agent: 1094 Elo2026-08-10
Design Arena Full-stack Agent: 1104 Elo2026-08-07
Design Arena Full-stack Agent: 1093 Elo2026-08-18
Design Arena Full-stack Agent: 1104 Elo2026-08-08
Design Arena Full-stack Agent: 1097 Elo2026-08-11
Design Arena Full-stack Agent: 1099 Elo2026-08-15
Design Arena Full-stack Agent: 1098 Elo2026-08-12
Design Arena Full-stack Agent: 1096 Elo2026-08-13
Design Arena Full-stack Agent: 1093 Elo2026-08-19
Design Arena Full-stack Agent: 1087 Elo2026-08-27
Design Arena Full-stack Agent: 1093 Elo2026-08-20
Design Arena Full-stack Agent: 1099 Elo2026-08-16
Design Arena Full-stack Agent: 1098 Elo2026-08-17
Design Arena Full-stack Agent: 1097 Elo2026-08-21
Design Arena Full-stack Agent: 1097 Elo2026-08-22
Design Arena Full-stack Agent: 1096 Elo2026-08-23
Design Arena Full-stack Agent: 1086 Elo2026-08-28
Design Arena Full-stack Agent: 1084 Elo2026-08-24
Design Arena Full-stack Agent: 1087 Elo2026-08-25
Design Arena Full-stack Agent: 1087 Elo2026-08-26
Design Arena Full-stack Agent: 1087 Elo2026-08-29
Design Arena Full-stack Agent: 1088 Elo2026-08-30
Design Arena Full-stack Agent: 1087 Elo2026-08-31
Design Arena Full-stack Agent: 1087 Elo2026-09-01
Design Arena Full-stack Agent: 1088 Elo2026-09-02
Design Arena Full-stack Agent: 1088 Elo2026-09-03
Design Arena Full-stack Agent: 1088 Elo2026-09-04
Design Arena Web-app Agent: 1168 Elo2026-07-28
Design Arena Web-app Agent: 1168 Elo2026-07-27
Design Arena Web-app Agent: 1167 Elo2026-07-30
Design Arena Web-app Agent: 1167 Elo2026-07-29
Design Arena Web-app Agent: 1167 Elo2026-07-31
Design Arena Web-app Agent: 1168 Elo2026-08-02
Design Arena Web-app Agent: 1168 Elo2026-08-01
Design Arena Web-app Agent: 1160 Elo2026-08-05
Design Arena Web-app Agent: 1155 Elo2026-08-09
Design Arena Web-app Agent: 1168 Elo2026-08-03
Design Arena Web-app Agent: 1168 Elo2026-08-04
Design Arena Web-app Agent: 1149 Elo2026-08-14
Design Arena Web-app Agent: 1160 Elo2026-08-06
Design Arena Web-app Agent: 1152 Elo2026-08-10
Design Arena Web-app Agent: 1160 Elo2026-08-07
Design Arena Web-app Agent: 1158 Elo2026-08-18
Design Arena Web-app Agent: 1161 Elo2026-08-08
Design Arena Web-app Agent: 1151 Elo2026-08-11
Design Arena Web-app Agent: 1161 Elo2026-08-15
Design Arena Web-app Agent: 1152 Elo2026-08-12
Design Arena Web-app Agent: 1151 Elo2026-08-13
Design Arena Web-app Agent: 1158 Elo2026-08-19
Design Arena Web-app Agent: 1142 Elo2026-08-27
Design Arena Web-app Agent: 1158 Elo2026-08-20
Design Arena Web-app Agent: 1161 Elo2026-08-16
Design Arena Web-app Agent: 1162 Elo2026-08-17
Design Arena Web-app Agent: 1147 Elo2026-08-21
Design Arena Web-app Agent: 1148 Elo2026-08-22
Design Arena Web-app Agent: 1148 Elo2026-08-23
Design Arena Web-app Agent: 1143 Elo2026-08-28
Design Arena Web-app Agent: 1143 Elo2026-08-24
Design Arena Web-app Agent: 1144 Elo2026-08-25
Design Arena Web-app Agent: 1144 Elo2026-08-26
Design Arena Web-app Agent: 1142 Elo2026-08-29
Design Arena Web-app Agent: 1141 Elo2026-08-30
Design Arena Web-app Agent: 1141 Elo2026-08-31
Design Arena Web-app Agent: 1141 Elo2026-09-01
Design Arena Web-app Agent: 1141 Elo2026-09-02
Design Arena Web-app Agent: 1141 Elo2026-09-03
Design Arena Web-app Agent: 1141 Elo2026-09-04
Design Arena Website: 1221 Elo2026-07-28
Design Arena Website: 1221 Elo2026-07-30
Design Arena Website: 1221 Elo2026-07-27
Design Arena Website: 1221 Elo2026-07-29
Design Arena Website: 1220 Elo2026-07-31
Design Arena Website: 1220 Elo2026-08-02
Design Arena Website: 1220 Elo2026-08-01
Design Arena Website: 1219 Elo2026-08-05
Design Arena Website: 1220 Elo2026-08-03
Design Arena Website: 1218 Elo2026-08-09
Design Arena Website: 1220 Elo2026-08-04
Design Arena Website: 1216 Elo2026-08-14
Design Arena Website: 1219 Elo2026-08-06
Design Arena Website: 1219 Elo2026-08-07
Design Arena Website: 1218 Elo2026-08-10
Design Arena Website: 1218 Elo2026-08-08
Design Arena Website: 1207 Elo2026-08-18
Design Arena Website: 1218 Elo2026-08-11
Design Arena Website: 1207 Elo2026-08-15
Design Arena Website: 1217 Elo2026-08-12
Design Arena Website: 1216 Elo2026-08-13
Design Arena Website: 1207 Elo2026-08-19
Design Arena Website: 1207 Elo2026-08-16
Design Arena Website: 1207 Elo2026-08-20
Design Arena Website: 1216 Elo2026-08-27
Design Arena Website: 1207 Elo2026-08-17
Design Arena Website: 1216 Elo2026-08-21
Design Arena Website: 1216 Elo2026-08-22
Design Arena Website: 1216 Elo2026-08-23
Design Arena Website: 1216 Elo2026-08-24
Design Arena Website: 1216 Elo2026-08-28
Design Arena Website: 1216 Elo2026-08-25
Design Arena Website: 1216 Elo2026-08-26
Design Arena Website: 1215 Elo2026-08-29
Design Arena Website: 1215 Elo2026-08-30
Design Arena Website: 1215 Elo2026-08-31
Design Arena Website: 1215 Elo2026-09-01
Design Arena Website: 1214 Elo2026-09-02
Design Arena Website: 1212 Elo2026-09-03
Design Arena Website: 1211 Elo2026-09-04
LMArena Agent: -8.52026-07-13
LMArena Agent: -8.32026-07-20
LMArena Agent: -8.72026-07-27
LMArena Agent: -8.62026-07-21
LMArena Agent: -8.82026-07-28
LMArena Agent: -8.82026-08-03
LMArena Agent: -8.62026-08-12
LMArena Agent: -8.52026-08-13
LMArena Agent: -8.92026-08-06
LMArena Agent: -8.62026-08-11
LMArena Agent: -10.32026-08-24
LMArena Agent: -10.72026-08-27
LMArena Agent: -11.22026-08-31
LMArena Creative Writing: 1458 Elo2026-07-21
LMArena Creative Writing: 1459 Elo2026-07-27
LMArena Creative Writing: 1459 Elo2026-07-30
LMArena Creative Writing: 1458 Elo2026-08-02
LMArena Creative Writing: 1458 Elo2026-08-06
LMArena Creative Writing: 1458 Elo2026-08-03
LMArena Creative Writing: 1459 Elo2026-08-12
LMArena Creative Writing: 1458 Elo2026-08-21
LMArena Creative Writing: 1458 Elo2026-08-27
LMArena Creative Writing: 1458 Elo2026-09-01
LMArena Instruction Following: 1437 Elo2026-07-21
LMArena Instruction Following: 1438 Elo2026-07-27
LMArena Instruction Following: 1438 Elo2026-07-30
LMArena Instruction Following: 1437 Elo2026-08-02
LMArena Instruction Following: 1437 Elo2026-08-03
LMArena Instruction Following: 1437 Elo2026-08-06
LMArena Instruction Following: 1438 Elo2026-08-12
LMArena Instruction Following: 1438 Elo2026-08-21
LMArena Instruction Following: 1438 Elo2026-08-27
LMArena Instruction Following: 1438 Elo2026-09-01
LMArena Long Query: 1452 Elo2026-07-21
LMArena Long Query: 1452 Elo2026-07-27
LMArena Long Query: 1452 Elo2026-07-30
LMArena Long Query: 1452 Elo2026-08-02
LMArena Long Query: 1452 Elo2026-08-03
LMArena Long Query: 1452 Elo2026-08-06
LMArena Long Query: 1452 Elo2026-08-12
LMArena Long Query: 1452 Elo2026-08-21
LMArena Long Query: 1453 Elo2026-08-27
LMArena Long Query: 1452 Elo2026-09-01
LMArena Math: 1474 Elo2026-07-21
LMArena Math: 1474 Elo2026-07-27
LMArena Math: 1474 Elo2026-07-30
LMArena Math: 1474 Elo2026-08-02
LMArena Math: 1474 Elo2026-08-03
LMArena Math: 1474 Elo2026-08-06
LMArena Math: 1474 Elo2026-08-12
LMArena Math: 1474 Elo2026-08-21
LMArena Math: 1474 Elo2026-08-27
LMArena Math: 1473 Elo2026-09-01
LMArena Text: 1466 Elo2026-07-16
LMArena Text: 1473 Elo2026-07-21
LMArena Text: 1473 Elo2026-07-27
LMArena Text: 1473 Elo2026-07-30
LMArena Text: 1473 Elo2026-08-02
LMArena Text: 1473 Elo2026-08-06
LMArena Text: 1473 Elo2026-08-03
LMArena Text: 1473 Elo2026-08-10
LMArena Text: 1473 Elo2026-08-21
LMArena Text: 1473 Elo2026-08-12
LMArena Text: 1474 Elo2026-08-27
LMArena Text: 1474 Elo2026-09-01
LMArena Vision: 1284 Elo2026-07-12
LMArena Vision: 1269 Elo2026-07-21
LMArena Vision: 1271 Elo2026-07-26
LMArena Vision: 1271 Elo2026-07-30
LMArena Vision: 1271 Elo2026-08-02
LMArena Vision: 1271 Elo2026-08-06
LMArena Vision: 1271 Elo2026-08-21
LMArena Vision: 1272 Elo2026-08-27
LMArena WebDev: 1437 Elo2026-07-16
LMArena WebDev: 1437 Elo2026-07-21
LMArena WebDev: 1437 Elo2026-07-20
LMArena WebDev: 1438 Elo2026-07-27
LMArena WebDev: 1438 Elo2026-07-24
LMArena WebDev: 1438 Elo2026-07-28
LMArena WebDev: 1438 Elo2026-07-30
LMArena WebDev: 1438 Elo2026-08-01
LMArena WebDev: 1438 Elo2026-07-31
LMArena WebDev: 1438 Elo2026-08-06
LMArena WebDev: 1438 Elo2026-08-02
LMArena WebDev: 1438 Elo2026-08-12
LMArena WebDev: 1438 Elo2026-08-10
LMArena WebDev: 1438 Elo2026-08-14
LMArena WebDev: 1438 Elo2026-08-21
LMArena WebDev: 1438 Elo2026-08-30
LMArena WebDev: 1438 Elo2026-09-01
SWE-rebench^‡: 53.0% ± 0.42026-03-01tools

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
70% of intended weighted task evidence across 2 independent sources. 5 of 5 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 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 CodingProvisional evidence
58% of intended weighted task evidence across 3 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Debugging & Code ReviewProvisional evidence
55% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 configured evaluation feeds currently have results.
Best LLM for Image UnderstandingProvisional evidence
55% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Reasoning or VLMEvalKit tasks. 3 of 4 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 Agentic CodingProvisional evidence
50% of intended weighted task evidence across 3 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 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 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 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 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 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 LLM for Autonomous AgentsProvisional evidence
37% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Frontier-Bench or LiveBench Agentic Coding. 7 of 7 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 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 AI AgentsProvisional evidence
32% of intended weighted task evidence across 2 independent sources; broader independent confirmation is still missing from Berkeley Function Calling 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 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 JSON & Schema OutputProvisional evidence
17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.
Best LLM for Structured Data ExtractionProvisional evidence
17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 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 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.