MiniMax M3

minimax/minimax-m3-20260531

MiniMax M3 is an AI model from minimax that processes text, image, and video inputs and produces text output. It supports tool usage and reasoning, offers a context length of 1,048,576 tokens, provides open weights, and is priced at $0.3 per million input tokens and $1.2 per million output tokens. The model was released on 2026‑06‑01.

tool use
structured outputs
reasoning
open-weight

At a glance

providerminimax

releasedMay 31, 2026

context1.0M

input / M$0.30

Specifications

What the API gives you

Context window: 1.0M tokens
Max output: 512K tokens
Input price: $0.30 / 1M tokens
Output price: $1.20 / 1M tokens
Cache read: $0.060 / 1M tokens
Modalities: text, image, video → text
Knowledge cutoff: —
Released: May 31, 2026

Measured evidence

Public benchmark record

Design Arena Coding: 1285 Elo2026-07-28
Design Arena Coding: 1285 Elo2026-07-27
Design Arena Coding: 1285 Elo2026-07-30
Design Arena Coding: 1285 Elo2026-07-29
Design Arena Coding: 1285 Elo2026-07-31
Design Arena Coding: 1284 Elo2026-08-02
Design Arena Coding: 1284 Elo2026-08-05
Design Arena Coding: 1284 Elo2026-08-01
Design Arena Coding: 1283 Elo2026-08-09
Design Arena Coding: 1285 Elo2026-08-03
Design Arena Coding: 1284 Elo2026-08-04
Design Arena Coding: 1277 Elo2026-08-14
Design Arena Coding: 1284 Elo2026-08-06
Design Arena Coding: 1283 Elo2026-08-10
Design Arena Coding: 1284 Elo2026-08-07
Design Arena Coding: 1271 Elo2026-08-18
Design Arena Coding: 1283 Elo2026-08-08
Design Arena Coding: 1272 Elo2026-08-15
Design Arena Coding: 1283 Elo2026-08-11
Design Arena Coding: 1280 Elo2026-08-12
Design Arena Coding: 1275 Elo2026-08-21
Design Arena Coding: 1278 Elo2026-08-13
Design Arena Coding: 1269 Elo2026-08-19
Design Arena Coding: 1275 Elo2026-08-27
Design Arena Coding: 1269 Elo2026-08-20
Design Arena Coding: 1271 Elo2026-08-16
Design Arena Coding: 1271 Elo2026-08-17
Design Arena Coding: 1275 Elo2026-08-22
Design Arena Coding: 1275 Elo2026-08-23
Design Arena Coding: 1274 Elo2026-08-28
Design Arena Coding: 1275 Elo2026-08-24
Design Arena Coding: 1275 Elo2026-08-25
Design Arena Coding: 1275 Elo2026-08-26
Design Arena Coding: 1274 Elo2026-08-29
Design Arena Coding: 1274 Elo2026-08-30
Design Arena Coding: 1274 Elo2026-08-31
Design Arena Coding: 1274 Elo2026-09-01
Design Arena Coding: 1273 Elo2026-09-02
Design Arena Coding: 1270 Elo2026-09-03
Design Arena Coding: 1269 Elo2026-09-04
Design Arena Full-stack Agent: 1250 Elo2026-07-28
Design Arena Full-stack Agent: 1250 Elo2026-07-27
Design Arena Full-stack Agent: 1250 Elo2026-07-30
Design Arena Full-stack Agent: 1250 Elo2026-07-29
Design Arena Full-stack Agent: 1250 Elo2026-07-31
Design Arena Full-stack Agent: 1221 Elo2026-08-02
Design Arena Full-stack Agent: 1223 Elo2026-08-05
Design Arena Full-stack Agent: 1250 Elo2026-08-01
Design Arena Full-stack Agent: 1215 Elo2026-08-09
Design Arena Full-stack Agent: 1222 Elo2026-08-03
Design Arena Full-stack Agent: 1223 Elo2026-08-04
Design Arena Full-stack Agent: 1220 Elo2026-08-14
Design Arena Full-stack Agent: 1225 Elo2026-08-06
Design Arena Full-stack Agent: 1210 Elo2026-08-10
Design Arena Full-stack Agent: 1224 Elo2026-08-07
Design Arena Full-stack Agent: 1220 Elo2026-08-18
Design Arena Full-stack Agent: 1227 Elo2026-08-08
Design Arena Full-stack Agent: 1224 Elo2026-08-15
Design Arena Full-stack Agent: 1218 Elo2026-08-11
Design Arena Full-stack Agent: 1222 Elo2026-08-12
Design Arena Full-stack Agent: 1219 Elo2026-08-13
Design Arena Full-stack Agent: 1220 Elo2026-08-19
Design Arena Full-stack Agent: 1227 Elo2026-08-27
Design Arena Full-stack Agent: 1220 Elo2026-08-20
Design Arena Full-stack Agent: 1224 Elo2026-08-16
Design Arena Full-stack Agent: 1224 Elo2026-08-17
Design Arena Full-stack Agent: 1228 Elo2026-08-21
Design Arena Full-stack Agent: 1229 Elo2026-08-22
Design Arena Full-stack Agent: 1231 Elo2026-08-23
Design Arena Full-stack Agent: 1224 Elo2026-08-28
Design Arena Full-stack Agent: 1222 Elo2026-08-24
Design Arena Full-stack Agent: 1225 Elo2026-08-25
Design Arena Full-stack Agent: 1227 Elo2026-08-26
Design Arena Full-stack Agent: 1224 Elo2026-08-29
Design Arena Full-stack Agent: 1225 Elo2026-08-30
Design Arena Full-stack Agent: 1226 Elo2026-08-31
Design Arena Full-stack Agent: 1223 Elo2026-09-01
Design Arena Full-stack Agent: 1224 Elo2026-09-02
Design Arena Full-stack Agent: 1224 Elo2026-09-03
Design Arena Full-stack Agent: 1223 Elo2026-09-04
Design Arena UI: 1279 Elo2026-07-28
Design Arena UI: 1278 Elo2026-07-27
Design Arena UI: 1281 Elo2026-07-30
Design Arena UI: 1282 Elo2026-07-29
Design Arena UI: 1282 Elo2026-07-31
Design Arena UI: 1283 Elo2026-08-02
Design Arena UI: 1282 Elo2026-08-01
Design Arena UI: 1283 Elo2026-08-05
Design Arena UI: 1284 Elo2026-08-09
Design Arena UI: 1285 Elo2026-08-03
Design Arena UI: 1284 Elo2026-08-04
Design Arena UI: 1277 Elo2026-08-14
Design Arena UI: 1283 Elo2026-08-06
Design Arena UI: 1285 Elo2026-08-07
Design Arena UI: 1280 Elo2026-08-10
Design Arena UI: 1283 Elo2026-08-08
Design Arena UI: 1273 Elo2026-08-18
Design Arena UI: 1280 Elo2026-08-11
Design Arena UI: 1275 Elo2026-08-15
Design Arena UI: 1279 Elo2026-08-12
Design Arena UI: 1279 Elo2026-08-13
Design Arena UI: 1273 Elo2026-08-19
Design Arena UI: 1274 Elo2026-08-16
Design Arena UI: 1273 Elo2026-08-20
Design Arena UI: 1274 Elo2026-08-27
Design Arena UI: 1273 Elo2026-08-17
Design Arena UI: 1273 Elo2026-08-21
Design Arena UI: 1273 Elo2026-08-22
Design Arena UI: 1273 Elo2026-08-23
Design Arena UI: 1274 Elo2026-08-28
Design Arena UI: 1274 Elo2026-08-24
Design Arena UI: 1273 Elo2026-08-25
Design Arena UI: 1275 Elo2026-08-26
Design Arena UI: 1274 Elo2026-08-29
Design Arena UI: 1274 Elo2026-08-30
Design Arena UI: 1272 Elo2026-08-31
Design Arena UI: 1271 Elo2026-09-01
Design Arena UI: 1270 Elo2026-09-02
Design Arena UI: 1268 Elo2026-09-03
Design Arena UI: 1266 Elo2026-09-04
Design Arena Web-app Agent: 1246 Elo2026-07-28
Design Arena Web-app Agent: 1246 Elo2026-07-27
Design Arena Web-app Agent: 1247 Elo2026-07-30
Design Arena Web-app Agent: 1246 Elo2026-07-29
Design Arena Web-app Agent: 1249 Elo2026-07-31
Design Arena Web-app Agent: 1253 Elo2026-08-02
Design Arena Web-app Agent: 1250 Elo2026-08-01
Design Arena Web-app Agent: 1251 Elo2026-08-05
Design Arena Web-app Agent: 1238 Elo2026-08-09
Design Arena Web-app Agent: 1253 Elo2026-08-03
Design Arena Web-app Agent: 1254 Elo2026-08-04
Design Arena Web-app Agent: 1236 Elo2026-08-14
Design Arena Web-app Agent: 1252 Elo2026-08-06
Design Arena Web-app Agent: 1236 Elo2026-08-10
Design Arena Web-app Agent: 1252 Elo2026-08-07
Design Arena Web-app Agent: 1234 Elo2026-08-18
Design Arena Web-app Agent: 1249 Elo2026-08-08
Design Arena Web-app Agent: 1236 Elo2026-08-11
Design Arena Web-app Agent: 1234 Elo2026-08-15
Design Arena Web-app Agent: 1239 Elo2026-08-12
Design Arena Web-app Agent: 1236 Elo2026-08-13
Design Arena Web-app Agent: 1234 Elo2026-08-19
Design Arena Web-app Agent: 1234 Elo2026-08-27
Design Arena Web-app Agent: 1234 Elo2026-08-20
Design Arena Web-app Agent: 1236 Elo2026-08-16
Design Arena Web-app Agent: 1237 Elo2026-08-17
Design Arena Web-app Agent: 1237 Elo2026-08-21
Design Arena Web-app Agent: 1236 Elo2026-08-22
Design Arena Web-app Agent: 1237 Elo2026-08-23
Design Arena Web-app Agent: 1232 Elo2026-08-28
Design Arena Web-app Agent: 1231 Elo2026-08-24
Design Arena Web-app Agent: 1230 Elo2026-08-25
Design Arena Web-app Agent: 1233 Elo2026-08-26
Design Arena Web-app Agent: 1233 Elo2026-08-29
Design Arena Web-app Agent: 1232 Elo2026-08-30
Design Arena Web-app Agent: 1231 Elo2026-08-31
Design Arena Web-app Agent: 1231 Elo2026-09-01
Design Arena Web-app Agent: 1231 Elo2026-09-02
Design Arena Web-app Agent: 1230 Elo2026-09-03
Design Arena Web-app Agent: 1230 Elo2026-09-04
Design Arena Website: 1285 Elo2026-07-28
Design Arena Website: 1285 Elo2026-07-30
Design Arena Website: 1286 Elo2026-07-27
Design Arena Website: 1285 Elo2026-07-29
Design Arena Website: 1285 Elo2026-07-31
Design Arena Website: 1285 Elo2026-08-02
Design Arena Website: 1284 Elo2026-08-01
Design Arena Website: 1285 Elo2026-08-05
Design Arena Website: 1285 Elo2026-08-03
Design Arena Website: 1284 Elo2026-08-09
Design Arena Website: 1285 Elo2026-08-04
Design Arena Website: 1280 Elo2026-08-14
Design Arena Website: 1285 Elo2026-08-06
Design Arena Website: 1285 Elo2026-08-07
Design Arena Website: 1284 Elo2026-08-10
Design Arena Website: 1284 Elo2026-08-08
Design Arena Website: 1272 Elo2026-08-18
Design Arena Website: 1284 Elo2026-08-11
Design Arena Website: 1272 Elo2026-08-15
Design Arena Website: 1283 Elo2026-08-12
Design Arena Website: 1281 Elo2026-08-13
Design Arena Website: 1272 Elo2026-08-19
Design Arena Website: 1272 Elo2026-08-16
Design Arena Website: 1272 Elo2026-08-20
Design Arena Website: 1279 Elo2026-08-27
Design Arena Website: 1272 Elo2026-08-17
Design Arena Website: 1279 Elo2026-08-21
Design Arena Website: 1279 Elo2026-08-22
Design Arena Website: 1279 Elo2026-08-23
Design Arena Website: 1279 Elo2026-08-24
Design Arena Website: 1279 Elo2026-08-28
Design Arena Website: 1280 Elo2026-08-25
Design Arena Website: 1280 Elo2026-08-26
Design Arena Website: 1278 Elo2026-08-29
Design Arena Website: 1278 Elo2026-08-30
Design Arena Website: 1278 Elo2026-08-31
Design Arena Website: 1278 Elo2026-09-01
Design Arena Website: 1277 Elo2026-09-02
Design Arena Website: 1275 Elo2026-09-03
Design Arena Website: 1274 Elo2026-09-04
LiveBench Agentic Coding: 40.7%2026-06-25
LiveBench Coding: 68.2%2026-06-25
LiveBench Data Analysis: 76.2%2026-06-25
LiveBench Instruction Following: 57.5%2026-06-25
LiveBench Language: 76.8%2026-06-25
LiveBench Math: 77.0%2026-06-25
LiveBench Reasoning: 74.5%2026-06-25
LMArena Agent: -3.22026-07-13
LMArena Agent: -2.72026-07-20
LMArena Agent: -2.52026-07-27
LMArena Agent: -3.12026-07-21
LMArena Agent: -2.62026-07-28
LMArena Agent: -2.32026-08-03
LMArena Agent: -2.52026-08-12
LMArena Agent: -2.52026-08-13
LMArena Agent: -2.52026-08-06
LMArena Agent: -2.52026-08-11
LMArena Agent: -3.12026-08-24
LMArena Agent: -2.82026-08-27
LMArena Agent: -3.62026-08-31
LMArena Creative Writing: 1405 Elo2026-07-21
LMArena Creative Writing: 1404 Elo2026-07-27
LMArena Creative Writing: 1404 Elo2026-07-30
LMArena Creative Writing: 1404 Elo2026-08-02
LMArena Creative Writing: 1404 Elo2026-08-03
LMArena Creative Writing: 1404 Elo2026-08-06
LMArena Creative Writing: 1407 Elo2026-08-12
LMArena Creative Writing: 1404 Elo2026-08-21
LMArena Creative Writing: 1403 Elo2026-08-27
LMArena Creative Writing: 1406 Elo2026-09-01
LMArena Instruction Following: 1433 Elo2026-07-21
LMArena Instruction Following: 1434 Elo2026-07-27
LMArena Instruction Following: 1434 Elo2026-07-30
LMArena Instruction Following: 1436 Elo2026-08-02
LMArena Instruction Following: 1436 Elo2026-08-03
LMArena Instruction Following: 1436 Elo2026-08-06
LMArena Instruction Following: 1435 Elo2026-08-12
LMArena Instruction Following: 1435 Elo2026-08-21
LMArena Instruction Following: 1433 Elo2026-08-27
LMArena Instruction Following: 1434 Elo2026-09-01
LMArena Long Query: 1445 Elo2026-07-21
LMArena Long Query: 1445 Elo2026-07-27
LMArena Long Query: 1445 Elo2026-07-30
LMArena Long Query: 1447 Elo2026-08-02
LMArena Long Query: 1447 Elo2026-08-03
LMArena Long Query: 1446 Elo2026-08-06
LMArena Long Query: 1447 Elo2026-08-12
LMArena Long Query: 1447 Elo2026-08-21
LMArena Long Query: 1446 Elo2026-08-27
LMArena Long Query: 1447 Elo2026-09-01
LMArena Math: 1441 Elo2026-07-21
LMArena Math: 1442 Elo2026-07-27
LMArena Math: 1442 Elo2026-07-30
LMArena Math: 1437 Elo2026-08-02
LMArena Math: 1437 Elo2026-08-03
LMArena Math: 1438 Elo2026-08-06
LMArena Math: 1438 Elo2026-08-12
LMArena Math: 1436 Elo2026-08-21
LMArena Math: 1434 Elo2026-08-27
LMArena Math: 1436 Elo2026-09-01
LMArena Text: 1437 Elo2026-07-16
LMArena Text: 1444 Elo2026-07-21
LMArena Text: 1445 Elo2026-08-02
LMArena Text: 1444 Elo2026-07-27
LMArena Text: 1444 Elo2026-07-30
LMArena Text: 1445 Elo2026-08-03
LMArena Text: 1443 Elo2026-08-10
LMArena Text: 1445 Elo2026-08-06
LMArena Text: 1443 Elo2026-08-21
LMArena Text: 1443 Elo2026-08-12
LMArena Text: 1442 Elo2026-08-27
LMArena Text: 1443 Elo2026-09-01
LMArena Vision: 1260 Elo2026-07-12
LMArena Vision: 1240 Elo2026-07-21
LMArena Vision: 1240 Elo2026-07-26
LMArena Vision: 1240 Elo2026-07-30
LMArena Vision: 1239 Elo2026-08-02
LMArena Vision: 1240 Elo2026-08-06
LMArena Vision: 1237 Elo2026-08-21
LMArena Vision: 1237 Elo2026-08-27
LMArena WebDev: 1493 Elo2026-07-16
LMArena WebDev: 1491 Elo2026-07-21
LMArena WebDev: 1492 Elo2026-07-20
LMArena WebDev: 1493 Elo2026-07-27
LMArena WebDev: 1493 Elo2026-07-24
LMArena WebDev: 1494 Elo2026-07-28
LMArena WebDev: 1494 Elo2026-07-30
LMArena WebDev: 1491 Elo2026-08-01
LMArena WebDev: 1492 Elo2026-07-31
LMArena WebDev: 1491 Elo2026-08-06
LMArena WebDev: 1491 Elo2026-08-02
LMArena WebDev: 1491 Elo2026-08-12
LMArena WebDev: 1491 Elo2026-08-10
LMArena WebDev: 1490 Elo2026-08-14
LMArena WebDev: 1488 Elo2026-08-21
LMArena WebDev: 1487 Elo2026-08-30
LMArena WebDev: 1487 Elo2026-09-01
OSWorld Verified^‡: 4.6%2026-06-24enabled effort
SWE-rebench^‡: 45.6% ± 1.32026-05-15tools
SWE-rebench^‡: 46.4% ± 0.92026-07-01tools

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

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

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

Best LLM for Competition MathEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Business WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Logic & Problem SolvingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Marketing CopyEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Chat & RoleplayEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Creative WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Frontend & UIEstablished evidence
100% of intended weighted task evidence across 3 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for WritingEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Roleplay & CharacterEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for Math & ReasoningEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for a General AssistantEstablished evidence
100% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.
Best LLM for 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 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 CodingEstablished evidence
74% of intended weighted task evidence across 4 independent sources. 8 of 8 configured evaluation feeds currently have results.
Best LLM for Debugging & Code ReviewEstablished evidence
70% of intended weighted task evidence across 3 independent sources. 6 of 6 configured evaluation feeds currently have results.
Best 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 Agentic CodingEstablished evidence
64% of intended weighted task evidence across 4 independent sources. 8 of 8 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 LLM for Autonomous AgentsProvisional evidence
54% of intended weighted task evidence across 4 independent sources; broader independent confirmation is still missing from Frontier-Bench or Terminal-Bench 2.1. 7 of 7 configured evaluation feeds currently have results.
Best LLM for AI AgentsProvisional evidence
52% of intended weighted task evidence across 4 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or Terminal-Bench 2.1. 7 of 7 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 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 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 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

#8Best LLM for Image Understanding

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