AI BENCHY
Advertise here
#47

GPT-5.6 Terra

OpenAI Release: 2026-07-09 Tested on: 2026-07-09 21:16 openai/gpt-5.6-terra::low
~1T total (~60B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

GPT-5.6 Terra scores 7.7 on AI BENCHY and ranks #47. It has 10.0 reliability, a 74.6% pass rate, $0.343 total cost, and 4.88s average response time.

What makes GPT-5.6 Terra unique: It stands out most in Instructions following, where it ranks #1, while Coding is its weakest area at #16. It is notably fast compared with similar models.

Model facts

Researched on 2026-08-12

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

Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose the architecture or count.

Parameter source Availability source

Score

7.7

Consistency

8.1

Reliability

10.0

Total Cost (Current Price)

$0.343

Total Output Tokens

17,144

Total Input Tokens

34,226

Input Price

$2.500 / 1M

Output Price

$15.000 / 1M

Tests Correct

Wrong Tests: 8

Attempt pass rate: 74.6%

Flaky tests

5

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

Response Time (avg)

4.88s

Response Time (max): 19.85s

Response Time (total): 102.53s

Wrong answer: 8

Hamster playing table tennis

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

#47 GPT-5.6 Terra

low
Cost
$0.034
Time
16.8s
Tokens
2,348 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:23 Re-test 7.5 10.0 $0.210 ↓ Compare
2026-07-16 22:39 New test added 7.5 10.0 $0.519 Compare
2026-07-09 21:16 Initial run 7.7 10.0 $0.343 Current run

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-07-09 21:18 $2.500 / 1M $15.000 / 1M

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-5.6 TerralowvsGPT-5.4 NanomediumGPT-5.6 TerralowvsMiniMax M3mediumGPT-5.6 TerralowvsClaude Opus 5noneGPT-5.6 TerralowvsGPT 5.3 ChatnoneGPT-5.6 TerralowvsNemotron 3 UltramediumFree AvailableGPT-5.6 TerralowvsQwen3.5 Plus 2026-02-15mediumGPT-5.6 TerralowvsSolar Pro 4xhighGPT-5.6 TerralowvsQwen3.5-27BmediumGPT-5.6 TerralowvsGPT-5.6 LunahighGPT-5.6 TerralowvsGPT-5.4 Minimedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 6.6 4.6
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 7.2
General Intelligence 4.8 3.2
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 4.7 1.6
Trivia 3.0 10.0

Compared models