7 results Clear filters
Ranked by raw score for FrontierMath - . Versions are kept separate, and incompatible results are never combined.
GPT-5.6 Solby OpenAI
2026-07-09
openai/gpt-5.6-sol

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

T Reasoning Tools Structured output Weight access not listed
Context
1.05M
Input
$5/M
Output
$30/M
GPT-5.6 Terraby OpenAI
2026-07-09
openai/gpt-5.6-terra

Balanced GPT-5.6 model for capable, cost-efficient everyday work

T Reasoning Tools Structured output Weight access not listed
Context
1.05M
Input
$2.5/M
Output
$15/M
GPT-5.6 Lunaby OpenAI
2026-07-09
openai/gpt-5.6-luna

Cost-efficient GPT-5.6 model for fast, high-volume workloads

T Reasoning Tools Structured output Weight access not listed
Context
1.05M
Input
$1/M
Output
$6/M
GPT-5.5 Proby OpenAI
2026-04-23
openai/gpt-5.5-pro

Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding

T Reasoning Tools Structured output Weight access not listed
Context
1.05M
Input
$30/M
Output
$180/M
GPT-5.4 Proby OpenAI
2026-03-05
openai/gpt-5.4-pro

More exact GPT-5.4 tier for demanding professional reasoning and agent tasks

T Reasoning Tools Weight access not listed
Context
1.05M
Input
$30/M
Output
$180/M
GPT-5.5by OpenAI
2026-04-23
openai/gpt-5.5

Default frontier GPT for coding, computer use, research, and knowledge work

T Reasoning Tools Structured output Weight access not listed
Context
1.05M
Input
$5/M
Output
$30/M
GPT-5.4by OpenAI
2026-03-05
openai/gpt-5.4

Agent-ready GPT for coding and computer-use workflows at a lower cost

T Reasoning Tools Structured output Weight access not listed
Context
1.05M
Input
$2.5/M
Output
$15/M