GPT Terra Latest

Compatibility alias that routes to GPT 5.6 Terra, the latest supported GPT Terra model.

Reasoning
Vision
Native PDF input
Tool Calling
Structured Output

Added Sep 11, 2026

Pricing

Auto routing · per 1M tokens

Input: $2.00
Output: $12.00
Cache read: $0.20

Compare provider prices

Specifications

Context window: 1.1M
Max output: 128K
Avg output (7d): 253 tokens; Longer than 18% of models

Benchmarks

Artificial Analysis

LMArena

Sourced from Artificial Analysis.

Intelligence Index

30.1

Better than 83% of models compared

Coding Index

64.7

Better than 77% of models compared

Agentic Index

30.4

Better than 75% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

33.5%

Better than 52% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

1039 Elo

Better than 52% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

1255 Elo

Better than 66% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

17.0%

Better than 61% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

74.0%

Better than 71% of models compared

MLCR-AA

Medical long-context reasoning

12.2%

Better than 38% of models compared

Reasoning

HLE

Humanity's Last Exam

33.3%

Better than 80% of models compared

IFBench

Instruction-following benchmark

62.2%

Better than 73% of models compared

CritPt

Research-level physics reasoning

17.4%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

1.0%

Better than 42% of models compared

SciCode

Python programming for scientific computing

50.5%

Better than 56% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

44.6%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

89.8%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

87.2%

Better than 83% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

72.8%

Better than 65% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

74.0%

Better than 71% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

37.7%

Last updated Oct 1, 2026