Mistral Medium 3

mistralai/mistral-medium-3

Mistral Medium 3 is a model from mistralai that processes text, image, and file inputs to generate text outputs. It supports a 131,072 token context window and tool usage. It is a proprietary model released on May 7, 2025.

  • tool use
  • structured outputs

At a glance

providermistralai
releasedMay 7, 2025
context131K
input / M$0.40

Specifications

What the API gives you

Context window
131K tokens
Max output
105K tokens
Input price
$0.40 / 1M tokens
Output price
$2 / 1M tokens
Cache read
$0.040 / 1M tokens
Modalities
text, image, file → text
Knowledge cutoff
Mar 31, 2025
Released
May 7, 2025

Measured evidence

Public benchmark record

Design Arena Coding
1100 Elo2026-07-28
Design Arena Coding
1100 Elo2026-07-27
Design Arena Coding
1100 Elo2026-07-30
Design Arena Coding
1100 Elo2026-07-29
Design Arena Coding
1099 Elo2026-07-31
Design Arena Coding
1099 Elo2026-08-02
Design Arena Coding
1098 Elo2026-08-05
Design Arena Coding
1099 Elo2026-08-01
Design Arena Coding
1097 Elo2026-08-09
Design Arena Coding
1099 Elo2026-08-03
Design Arena Coding
1098 Elo2026-08-04
Design Arena Coding
1094 Elo2026-08-14
Design Arena Coding
1098 Elo2026-08-06
Design Arena Coding
1097 Elo2026-08-10
Design Arena Coding
1098 Elo2026-08-07
Design Arena Coding
1088 Elo2026-08-18
Design Arena Coding
1097 Elo2026-08-08
Design Arena Coding
1088 Elo2026-08-15
Design Arena Coding
1097 Elo2026-08-11
Design Arena Coding
1096 Elo2026-08-12
Design Arena Coding
1094 Elo2026-08-13
Design Arena Coding
1087 Elo2026-08-19
Design Arena Coding
1093 Elo2026-08-27
Design Arena Coding
1087 Elo2026-08-20
Design Arena Coding
1088 Elo2026-08-16
Design Arena Coding
1088 Elo2026-08-17
Design Arena Coding
1093 Elo2026-08-21
Design Arena Coding
1094 Elo2026-08-22
Design Arena Coding
1094 Elo2026-08-23
Design Arena Coding
1093 Elo2026-08-28
Design Arena Coding
1094 Elo2026-08-24
Design Arena Coding
1094 Elo2026-08-25
Design Arena Coding
1094 Elo2026-08-26
Design Arena Coding
1093 Elo2026-08-29
Design Arena Coding
1093 Elo2026-08-30
Design Arena Coding
1093 Elo2026-08-31
Design Arena Coding
1093 Elo2026-09-01
Design Arena Coding
1091 Elo2026-09-02
Design Arena Coding
1089 Elo2026-09-03
Design Arena Coding
1088 Elo2026-09-04
Design Arena UI
1063 Elo2026-07-28
Design Arena UI
1064 Elo2026-07-27
Design Arena UI
1063 Elo2026-07-30
Design Arena UI
1063 Elo2026-07-29
Design Arena UI
1063 Elo2026-07-31
Design Arena UI
1063 Elo2026-08-02
Design Arena UI
1063 Elo2026-08-01
Design Arena UI
1061 Elo2026-08-05
Design Arena UI
1063 Elo2026-08-03
Design Arena UI
1058 Elo2026-08-09
Design Arena UI
1061 Elo2026-08-04
Design Arena UI
1056 Elo2026-08-14
Design Arena UI
1061 Elo2026-08-06
Design Arena UI
1060 Elo2026-08-07
Design Arena UI
1058 Elo2026-08-10
Design Arena UI
1059 Elo2026-08-08
Design Arena UI
1052 Elo2026-08-18
Design Arena UI
1059 Elo2026-08-11
Design Arena UI
1053 Elo2026-08-15
Design Arena UI
1059 Elo2026-08-12
Design Arena UI
1059 Elo2026-08-13
Design Arena UI
1052 Elo2026-08-19
Design Arena UI
1053 Elo2026-08-16
Design Arena UI
1052 Elo2026-08-20
Design Arena UI
1050 Elo2026-08-27
Design Arena UI
1052 Elo2026-08-17
Design Arena UI
1051 Elo2026-08-21
Design Arena UI
1051 Elo2026-08-22
Design Arena UI
1051 Elo2026-08-23
Design Arena UI
1051 Elo2026-08-24
Design Arena UI
1051 Elo2026-08-28
Design Arena UI
1052 Elo2026-08-25
Design Arena UI
1052 Elo2026-08-26
Design Arena UI
1051 Elo2026-08-29
Design Arena UI
1051 Elo2026-08-30
Design Arena UI
1051 Elo2026-08-31
Design Arena UI
1050 Elo2026-09-01
Design Arena UI
1050 Elo2026-09-02
Design Arena UI
1048 Elo2026-09-03
Design Arena UI
1046 Elo2026-09-04
Design Arena Website
1104 Elo2026-07-28
Design Arena Website
1104 Elo2026-07-30
Design Arena Website
1104 Elo2026-07-27
Design Arena Website
1104 Elo2026-07-29
Design Arena Website
1103 Elo2026-07-31
Design Arena Website
1103 Elo2026-08-02
Design Arena Website
1103 Elo2026-08-01
Design Arena Website
1102 Elo2026-08-05
Design Arena Website
1103 Elo2026-08-03
Design Arena Website
1101 Elo2026-08-09
Design Arena Website
1102 Elo2026-08-04
Design Arena Website
1099 Elo2026-08-14
Design Arena Website
1102 Elo2026-08-06
Design Arena Website
1102 Elo2026-08-07
Design Arena Website
1101 Elo2026-08-10
Design Arena Website
1101 Elo2026-08-08
Design Arena Website
1090 Elo2026-08-18
Design Arena Website
1101 Elo2026-08-11
Design Arena Website
1090 Elo2026-08-15
Design Arena Website
1100 Elo2026-08-12
Design Arena Website
1099 Elo2026-08-13
Design Arena Website
1090 Elo2026-08-19
Design Arena Website
1090 Elo2026-08-16
Design Arena Website
1090 Elo2026-08-20
Design Arena Website
1098 Elo2026-08-27
Design Arena Website
1090 Elo2026-08-17
Design Arena Website
1099 Elo2026-08-21
Design Arena Website
1099 Elo2026-08-22
Design Arena Website
1099 Elo2026-08-23
Design Arena Website
1099 Elo2026-08-24
Design Arena Website
1099 Elo2026-08-28
Design Arena Website
1099 Elo2026-08-25
Design Arena Website
1099 Elo2026-08-26
Design Arena Website
1098 Elo2026-08-29
Design Arena Website
1098 Elo2026-08-30
Design Arena Website
1098 Elo2026-08-31
Design Arena Website
1098 Elo2026-09-01
Design Arena Website
1097 Elo2026-09-02
Design Arena Website
1095 Elo2026-09-03
Design Arena Website
1094 Elo2026-09-04

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.

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 & UIProvisional evidence

    60% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for CodingProvisional evidence

    24% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 8 of 8 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    17% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    17% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesProvisional evidence

    14% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    14% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • 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 Code CompletionProvisional evidence

    13% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 4 of 4 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; 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 TranslationProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 5 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LiveBench Instruction Following. 4 of 6 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 5 configured evaluation feeds currently have results.

  • Best LLM for Business WritingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Creative Writing. 5 of 5 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; 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 Marketing CopyProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Creative Writing. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for SummarizationProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; 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 Chat & RoleplayProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; 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

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 5 of 5 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • 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.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; 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 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.

  • 10% of intended weighted task evidence across 0 independent sources; 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 Charts & DiagramsProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Vision. 3 of 5 configured evaluation feeds currently have results.

  • 10% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • 8% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Instruction Following or LMArena Text. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LMArena Document or LMArena Long Query. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • 6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LMArena Agent. 5 of 5 configured evaluation feeds currently have results.

  • 6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.

  • 6% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Berkeley Function Calling or LiveBench Data Analysis. 4 of 5 configured evaluation feeds currently have results.

  • Best Local LLM for CodingProvisional evidence

    6% of intended weighted task evidence across 0 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 Competition MathProvisional evidence

    5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

    5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from Design Arena Full-stack or Design Arena Web-apps. 8 of 8 configured evaluation feeds currently have results.

  • Best LLM for Autonomous AgentsProvisional evidence

    5% of intended weighted task evidence across 0 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 LLM for Math & ReasoningProvisional evidence

    5% of intended weighted task evidence across 0 independent sources; broader independent confirmation is still missing from LiveBench Mathematics or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    5% of intended weighted task evidence across 0 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.

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.