GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-6.1 Terra

AI model Released Oct 26, 2026

Context window: 1,050,000 tokens
Maximum output: 128,000 tokens
Open weights: No

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

GPT-6.1 Terra 168.1^* GPT-6.1 Terra · 95% interval 164.9–172.9

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

GPT-6.1 Terra

Tested configuration Radar task score

79.1^* / 100

4/4 core tests · experimental v1

7 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

GPT-6.1 Terra 94.3^*% Approx. 95% interval: 91.4–97.2% · 2026-10-26

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

GPT-6.1 Terra 74.0^*% Approx. 95% interval: 65.4–82.6% · 2026-10-26

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

GPT-6.1 Terra 90.9^*% Approx. 95% interval: 87.5–94.2% · 2026-10-26

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

GPT-6.1 Terra 57.3^*% Approx. 95% interval: 54.2–60.4% · 2026-10-26

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

GPT-6.1 Terra 100.0^*% Uncertainty not available · 2026-10-26

Research mathematics

FrontierMath Tier 4 v2 · Separate result

The hardest private FrontierMath problems, corrected v2 set, with Python tools. Separate from Tiers 1-3 in the core score.

GPT-6.1 Terra 92.7^*% Approx. 95% interval: 84.6–100.0% · 2026-10-26

Visual spatial reasoning

Furniture Assembly · Separate result

Assembly-error detection from photos and manuals, with zoom and Python tools. Uses model-assisted grading; not a general vision score.

GPT-6.1 Terra 79.2^*% Approx. 95% interval: 69.2–89.1% · 2026-10-26

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Run it locally

Inference · memory estimate

GPT-6.1 Terra

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

GPT-6.1 Terra

Provider offer

GPT-6.1 Terra / Pricing tiers 6

Provider / scope	Rate	Currency	Amount / unit
OpenAIgpt-6.1-terraBatch long_context	Cached input	USD	0.05 / 1M tokens
	Input	USD	1 / 1M tokens
	Output	USD	3.75 / 1M tokens
OpenAIgpt-6.1-terraBatch	Cached input	USD	0.025 / 1M tokens
	Input	USD	0.5 / 1M tokens
	Output	USD	2.5 / 1M tokens
OpenAIgpt-6.1-terraPriority	Cached input	USD	0.1 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	10 / 1M tokens
OpenAIgpt-6.1-terraPriority long_context	Cached input	USD	0.2 / 1M tokens
	Input	USD	4 / 1M tokens
	Output	USD	15 / 1M tokens
OpenAIgpt-6.1-terraStandard	Cached input	USD	0.05 / 1M tokens
	Input	USD	1 / 1M tokens
	Output	USD	5 / 1M tokens
OpenAIgpt-6.1-terraStandard long_context	Cached input	USD	0.1 / 1M tokens
	Input	USD	2 / 1M tokens
	Output	USD	7.5 / 1M tokens

Capabilities

Context window: 1,050,000 tokens
Maximum output: 128,000 tokens
Reasoning: Yes
Tool calling: Yes
Open weights: No
Knowledge cutoff: 2026-06-01

Input modalities

text
image
pdf

Output modalities

text

* Provisional data