Advertise here
#164

Inkling Small

Thinkingmachines Release: 2026-08-01 Tested on: 2026-08-01 13:00 thinkingmachines/inkling-small::low
276B total (12B active)MoEClosed
(high) (medium) (low) (none)

Summary

Inkling Small scores 5.7 on AI BENCHY and ranks #164. It has 10.0 reliability, a 50.0% pass rate, $0.059 total cost, and 2.08s average response time.

What makes Inkling Small unique: It stands out most in Instructions following, where it ranks #3, while Tool Calling is its weakest area at #16. It is notably fast compared with similar models.

Model facts

Researched on 2026-08-12

Reported
Parameters
276B total (12B active)
Architecture
MoE
Availability
Closed
License
-

Exact Small weights were still pending at research time.

Parameter source Availability source

Score

5.7

Consistency

8.6

Reliability

10.0

Total Cost (Current Price)

$0.059

Total Output Tokens

14,653

Total Input Tokens

81,438

Input Price

$0.500 / 1M

Output Price

$1.200 / 1M

Tests Correct

Wrong Tests: 13

Attempt pass rate: 50.0%

Flaky tests

4

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

Response Time (avg)

2.08s

Response Time (max): 5.82s

Response Time (total): 45.87s

Wrong answer: 9 Did not follow instructions: 2 Invalid tool call: 2

Hamster playing table tennis

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

#164 Thinking Machines: Inkling Small

low
Cost
$0.001
Time
5.9s
Tokens
759 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 03:56 Re-test 5.7 10.0 $0.055 ↓ Compare
2026-08-01 13:00 Initial run 5.7 10.0 $0.059 Current run

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-08-01 13:27 $0.500 / 1M $1.200 / 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

Inkling SmalllowvsGLM 5noneInkling SmalllowvsLing-3.0-flashnoneInkling SmalllowvsNemotron 3 SupermediumFree AvailableInkling SmalllowvsGLM 5.1noneInkling SmalllowvsNorth Mini CodemediumFree AvailableInkling SmalllowvsKimi K2.6noneInkling SmalllowvsSolar Pro 4noneInkling SmalllowvsQwen3.5-122B-A10BnoneInkling SmalllowvsGPT-5.4noneInkling SmalllowvsKAT-Coder-Air V2.5high

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 9.2 8.4
Coding 4.6 5.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 5.3 10.0
Instructions following 9.9 10.0
Puzzle Solving 5.3 7.2
Tool Calling 3.0 10.0
Trivia 3.0 10.0

Compared models