AI BENCHY
Advertise here
#37

GPT-5.6 Terra

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

Summary

GPT-5.6 Terra scores 7.8 on AI BENCHY and ranks #37. It has 10.0 reliability, a 68.3% pass rate, $0.496 total cost, and 6.69s average response time.

What makes GPT-5.6 Terra unique: 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

7.8

Consistency

9.2

Reliability

10.0

Total Cost (Current Price)

$0.496

Total Output Tokens

27,352

Total Input Tokens

34,218

Input Price

$2.500 / 1M

Output Price

$15.000 / 1M

Tests Correct

Wrong Tests: 8

Attempt pass rate: 68.3%

Flaky tests

2

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

Response Time (avg)

6.69s

Response Time (max): 41.68s

Response Time (total): 140.49s

Wrong answer: 8

Hamster playing table tennis

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

#37 GPT-5.6 Terra

medium
Cost
$0.035
Time
16.3s
Tokens
2,418 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:24 Re-test 7.8 10.0 $0.262 ↓ Compare
2026-07-16 22:39 New test added 7.8 10.0 $0.676 Compare
2026-07-09 21:16 Initial run 7.8 10.0 $0.496 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 TerramediumvsGLM 5.2mediumGPT-5.6 TerramediumvsClaude Sonnet 4.6mediumGPT-5.6 TerramediumvsGemini 3.5 Flash LitemediumGPT-5.6 TerramediumvsQwen3.8 27BmediumGPT-5.6 TerramediumvsQwen3.6 PlusmediumGPT-5.6 TerramediumvsSeed-2.0-LitemediumGPT-5.6 TerramediumvsQwen3.7 PlusmediumGPT-5.6 TerramediumvsClaude Opus 4.8lowGPT-5.6 TerramediumvsQwen3.8 27BlowGPT-5.6 TerramediumvsQwen3.7 Flashhigh

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 6.1 7.2
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 5.5 10.0
Instructions following 10.0 10.0
Puzzle Solving 8.4 7.4
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models