Advertise here
#27

GPT-6.1 Terra

OpenAI Release: 2026-10-26 Tested on: 2026-10-26 22:28 openai/gpt-6.1-terra::max
~1T total (~60B active)MoEClosedEstimated
(max) (xhigh) (high) (medium) (low) (none)

Summary

GPT-6.1 Terra scores 9.4 on AI BENCHY and ranks #27. It has 10.0 reliability, a 89.9% pass rate, $2.209 total cost, and 66.42s average response time.

What makes GPT-6.1 Terra unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Model facts

Researched on 2026-10-26

Estimated
Parameters
~1T total (~60B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. OpenAI does not disclose this checkpoint’s parameter counts or architecture. The low-confidence estimates carry forward the previous GPT-5.6 Terra catalog entry; the vendor announcement establishes identity and API availability, not those estimates.

Parameter source Availability source

Score

9.4

Consistency

9.0

Reliability

10.0

Total Cost (Current Price)

$2.209

Total Output Tokens

391,441

Total Input Tokens

250,989

Input Price

$1.000 / 1M

Output Price

$5.000 / 1M

Cache Read Price

$0.050 / 1M

Cache Write Price

$1.250 / 1M

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 4

Attempt pass rate: 89.9%

Flaky tests

3

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

66.42s

Response Time (max): 723.45s

Response Time (total): 1527.58s

Wrong answer: 2 Did not follow instructions: 1 No answer: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#27 GPT-6.1 Terra

max
Cost
$0.183
Time
406.4s
Tokens
36,629 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

GPT-6.1 TerramaxvsClaude Opus 5.5lowGPT-6.1 TerramaxvsClaude Opus 5.5highGPT-6.1 TerramaxvsGPT-5.5lowGPT-6.1 TerramaxvsGemini 3.7 FlashlowGPT-6.1 TerramaxvsGPT-5.6 SolhighGPT-6.1 TerramaxvsClaude Opus 5highGPT-6.1 TerramaxvsGPT-6 AstramediumGPT-6.1 TerramaxvsClaude Opus 5mediumGPT-6.1 TerramaxvsGPT-6.1 TerrahighGPT-6.1 TerramaxvsGPT-6.1 Terraxhigh

Category Breakdown

Category Score Consistency Tests Correct
Agentic 10.0 10.0
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 7.7 10.0
General Intelligence 10.0 10.0
Instructions following 8.5 6.8
Puzzle Solving 8.2 7.2
Tool Calling 10.0 10.0
Trivia 2.8 1.6

Compared models