GPT-5 Mini

openai/gpt-5-mini-2025-08-07

OpenAI's GPT-5 Mini, released on 2025-01-01, accepts text, image, and file inputs and produces text output. It offers a context length of 400 000 tokens, supports tool use and reasoning, and is priced at $0.25 per million input tokens and $2 per million output tokens. The model’s weights are not publicly released.

  • tool use
  • structured outputs
  • reasoning

At a glance

provideropenai
releasedJan 1, 2025
context400K
input / M$0.25

Specifications

What the API gives you

Context window
400K tokens
Max output
128K tokens
Input price
$0.25 / 1M tokens
Output price
$2 / 1M tokens
Cache read
$0.025 / 1M tokens
Modalities
text, image, file → text
Knowledge cutoff
May 31, 2024
Released
Jan 1, 2025

Measured evidence

Public benchmark record

BFCL
55.5%2026-07-28
BFCL
55.5%2026-07-27
BFCL
55.5%2026-07-29
BFCL
55.5%2026-07-31
BFCL
55.5%2026-07-30
BFCL
55.5%2026-08-02
BFCL
55.5%2026-08-01
BFCL
55.5%2026-08-05
BFCL
55.5%2026-08-03
BFCL
55.5%2026-08-09
BFCL
55.5%2026-08-04
BFCL
55.5%2026-08-06
BFCL
55.5%2026-08-07
BFCL
55.5%2026-08-14
BFCL
55.5%2026-08-10
BFCL
55.5%2026-08-08
BFCL
55.5%2026-08-18
BFCL
55.5%2026-08-11
BFCL
55.5%2026-08-15
BFCL
55.5%2026-08-12
BFCL
55.5%2026-08-13
BFCL
55.5%2026-08-19
BFCL
55.5%2026-08-16
BFCL
55.5%2026-08-20
BFCL
55.5%2026-08-27
BFCL
55.5%2026-08-17
BFCL
55.5%2026-08-21
BFCL
55.5%2026-08-22
BFCL
55.5%2026-08-23
BFCL
55.5%2026-08-24
BFCL
55.5%2026-08-28
BFCL
55.5%2026-08-25
BFCL
55.5%2026-08-26
BFCL
55.5%2026-08-29
BFCL
55.5%2026-08-30
BFCL
55.5%2026-08-31
BFCL
55.5%2026-09-01
BFCL
55.5%2026-09-02
BFCL
55.5%2026-09-03
BFCL
55.5%2026-09-04
Design Arena Coding
1145 Elo2026-07-28
Design Arena Coding
1145 Elo2026-07-27
Design Arena Coding
1145 Elo2026-07-30
Design Arena Coding
1145 Elo2026-07-29
Design Arena Coding
1145 Elo2026-07-31
Design Arena Coding
1144 Elo2026-08-02
Design Arena Coding
1143 Elo2026-08-05
Design Arena Coding
1144 Elo2026-08-01
Design Arena Coding
1142 Elo2026-08-09
Design Arena Coding
1144 Elo2026-08-03
Design Arena Coding
1144 Elo2026-08-04
Design Arena Coding
1140 Elo2026-08-14
Design Arena Coding
1144 Elo2026-08-06
Design Arena Coding
1142 Elo2026-08-10
Design Arena Coding
1144 Elo2026-08-07
Design Arena Coding
1134 Elo2026-08-18
Design Arena Coding
1143 Elo2026-08-08
Design Arena Coding
1134 Elo2026-08-15
Design Arena Coding
1142 Elo2026-08-11
Design Arena Coding
1142 Elo2026-08-12
Design Arena Coding
1140 Elo2026-08-13
Design Arena Coding
1133 Elo2026-08-19
Design Arena Coding
1139 Elo2026-08-27
Design Arena Coding
1133 Elo2026-08-20
Design Arena Coding
1134 Elo2026-08-16
Design Arena Coding
1134 Elo2026-08-17
Design Arena Coding
1139 Elo2026-08-21
Design Arena Coding
1140 Elo2026-08-22
Design Arena Coding
1140 Elo2026-08-23
Design Arena Coding
1139 Elo2026-08-28
Design Arena Coding
1140 Elo2026-08-24
Design Arena Coding
1140 Elo2026-08-25
Design Arena Coding
1140 Elo2026-08-26
Design Arena Coding
1139 Elo2026-08-29
Design Arena Coding
1139 Elo2026-08-30
Design Arena Coding
1139 Elo2026-08-31
Design Arena Coding
1139 Elo2026-09-01
Design Arena Coding
1137 Elo2026-09-02
Design Arena Coding
1135 Elo2026-09-03
Design Arena Coding
1134 Elo2026-09-04
Design Arena UI
1142 Elo2026-07-28
Design Arena UI
1142 Elo2026-07-27
Design Arena UI
1142 Elo2026-07-30
Design Arena UI
1142 Elo2026-07-29
Design Arena UI
1142 Elo2026-07-31
Design Arena UI
1142 Elo2026-08-02
Design Arena UI
1142 Elo2026-08-01
Design Arena UI
1141 Elo2026-08-05
Design Arena UI
1139 Elo2026-08-09
Design Arena UI
1142 Elo2026-08-03
Design Arena UI
1142 Elo2026-08-04
Design Arena UI
1137 Elo2026-08-14
Design Arena UI
1141 Elo2026-08-06
Design Arena UI
1141 Elo2026-08-07
Design Arena UI
1139 Elo2026-08-10
Design Arena UI
1139 Elo2026-08-08
Design Arena UI
1134 Elo2026-08-18
Design Arena UI
1139 Elo2026-08-11
Design Arena UI
1135 Elo2026-08-15
Design Arena UI
1139 Elo2026-08-12
Design Arena UI
1140 Elo2026-08-13
Design Arena UI
1134 Elo2026-08-19
Design Arena UI
1135 Elo2026-08-16
Design Arena UI
1134 Elo2026-08-20
Design Arena UI
1132 Elo2026-08-27
Design Arena UI
1134 Elo2026-08-17
Design Arena UI
1133 Elo2026-08-21
Design Arena UI
1133 Elo2026-08-22
Design Arena UI
1133 Elo2026-08-23
Design Arena UI
1133 Elo2026-08-24
Design Arena UI
1132 Elo2026-08-28
Design Arena UI
1133 Elo2026-08-25
Design Arena UI
1133 Elo2026-08-26
Design Arena UI
1132 Elo2026-08-29
Design Arena UI
1133 Elo2026-08-30
Design Arena UI
1132 Elo2026-08-31
Design Arena UI
1132 Elo2026-09-01
Design Arena UI
1132 Elo2026-09-02
Design Arena UI
1130 Elo2026-09-03
Design Arena UI
1128 Elo2026-09-04
Design Arena Website
1150 Elo2026-07-28
Design Arena Website
1150 Elo2026-07-30
Design Arena Website
1150 Elo2026-07-27
Design Arena Website
1150 Elo2026-07-29
Design Arena Website
1149 Elo2026-07-31
Design Arena Website
1149 Elo2026-08-02
Design Arena Website
1149 Elo2026-08-01
Design Arena Website
1148 Elo2026-08-05
Design Arena Website
1149 Elo2026-08-03
Design Arena Website
1147 Elo2026-08-09
Design Arena Website
1148 Elo2026-08-04
Design Arena Website
1145 Elo2026-08-14
Design Arena Website
1148 Elo2026-08-06
Design Arena Website
1148 Elo2026-08-07
Design Arena Website
1147 Elo2026-08-10
Design Arena Website
1147 Elo2026-08-08
Design Arena Website
1136 Elo2026-08-18
Design Arena Website
1147 Elo2026-08-11
Design Arena Website
1136 Elo2026-08-15
Design Arena Website
1146 Elo2026-08-12
Design Arena Website
1145 Elo2026-08-13
Design Arena Website
1136 Elo2026-08-19
Design Arena Website
1136 Elo2026-08-16
Design Arena Website
1136 Elo2026-08-20
Design Arena Website
1145 Elo2026-08-27
Design Arena Website
1136 Elo2026-08-17
Design Arena Website
1145 Elo2026-08-21
Design Arena Website
1145 Elo2026-08-22
Design Arena Website
1145 Elo2026-08-23
Design Arena Website
1145 Elo2026-08-24
Design Arena Website
1145 Elo2026-08-28
Design Arena Website
1145 Elo2026-08-25
Design Arena Website
1145 Elo2026-08-26
Design Arena Website
1144 Elo2026-08-29
Design Arena Website
1144 Elo2026-08-30
Design Arena Website
1144 Elo2026-08-31
Design Arena Website
1144 Elo2026-09-01
Design Arena Website
1143 Elo2026-09-02
Design Arena Website
1141 Elo2026-09-03
Design Arena Website
1140 Elo2026-09-04
LMArena Creative Writing
1327 Elo2026-07-21
LMArena Creative Writing
1327 Elo2026-07-27
LMArena Creative Writing
1327 Elo2026-07-30
LMArena Creative Writing
1327 Elo2026-08-02
LMArena Creative Writing
1327 Elo2026-08-03
LMArena Creative Writing
1327 Elo2026-08-06
LMArena Creative Writing
1325 Elo2026-08-12
LMArena Creative Writing
1325 Elo2026-08-21
LMArena Creative Writing
1325 Elo2026-08-27
LMArena Creative Writing
1325 Elo2026-09-01
LMArena Long Query
1356 Elo2026-07-21
LMArena Long Query
1356 Elo2026-07-27
LMArena Long Query
1356 Elo2026-07-30
LMArena Long Query
1356 Elo2026-08-02
LMArena Long Query
1356 Elo2026-08-06
LMArena Long Query
1356 Elo2026-08-03
LMArena Long Query
1355 Elo2026-08-12
LMArena Long Query
1355 Elo2026-08-21
LMArena Long Query
1354 Elo2026-08-27
LMArena Long Query
1354 Elo2026-09-01
LMArena Math
1376 Elo2026-07-21
LMArena Math
1377 Elo2026-07-27
LMArena Math
1377 Elo2026-07-30
LMArena Math
1377 Elo2026-08-02
LMArena Math
1377 Elo2026-08-03
LMArena Math
1376 Elo2026-08-06
LMArena Math
1376 Elo2026-08-12
LMArena Math
1376 Elo2026-08-21
LMArena Math
1376 Elo2026-08-27
LMArena Math
1377 Elo2026-09-01
LMArena Text
1390 Elo2026-07-21
LMArena Text
1390 Elo2026-07-27
LMArena Text
1390 Elo2026-07-30
LMArena Text
1390 Elo2026-08-10
LMArena Text
1390 Elo2026-08-02
LMArena Text
1390 Elo2026-08-06
LMArena Text
1390 Elo2026-08-03
LMArena Text
1390 Elo2026-08-21
LMArena Text
1390 Elo2026-08-12
LMArena Text
1389 Elo2026-08-27
LMArena Text
1389 Elo2026-09-01
LMArena Vision
1202 Elo2026-07-12
LMArena Vision
1182 Elo2026-07-21
LMArena Vision
1183 Elo2026-07-26
LMArena Vision
1183 Elo2026-07-30
LMArena Vision
1183 Elo2026-08-02
LMArena Vision
1183 Elo2026-08-06
LMArena Vision
1183 Elo2026-08-21
LMArena Vision
1182 Elo2026-08-27
SWE-rebench
39.6% ± 0.32026-02-01tools

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 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.

  • 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.

  • 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 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 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.

  • 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.

  • 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.

  • 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 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.

  • 40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 6 of 6 configured evaluation feeds currently have results.

  • Best 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. 8 of 8 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 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 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.

  • 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.

  • 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.

  • 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 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.

  • 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.

  • 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 Massive ContextProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for OCR & DocumentsProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • 25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Charts & DiagramsProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Document ParsingProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or Structured-output eval. 3 of 5 configured evaluation feeds currently have results.

  • Best LLM for Agentic CodingProvisional evidence

    23% of intended weighted task evidence across 1 independent source; 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.

  • 20% 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 SummarizationProvisional evidence

    20% 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.

  • 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 Local LLM for CodingProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Aider Polyglot or LiveBench Coding. 5 of 5 configured evaluation feeds currently have results.

  • 18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FACTS Grounding or LMArena Document. 4 of 6 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.

  • 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

  1. #7Best LLM for Tool & Function Calling

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