Advertise here
#305

Inkling 2 Mini

Thinkingmachines Release: 2026-11-20 Tested on: 2026-11-22 00:11 thinkingmachines/inkling-2-mini::low
26.4B total (3.4B active)MoEOpen source

Summary

Inkling 2 Mini scores 6.4 on AI BENCHY and ranks #305. It has 10.0 reliability, a 62.3% pass rate, $0.176 total cost, and 27.95s average response time.

What makes Inkling 2 Mini unique: It stands out most in Domain specific, where it ranks #4, while Agentic is its weakest area at #13.

Model facts

Researched on 2026-11-22

Reported
Parameters
26.4B total (3.4B active)
Architecture
MoE
Availability
Open source
License
Apache-2.0

Multimodal looped sparse MoE: 8 of 128 experts per token, middle layers run three times (about 5.4B effective active parameters). Public Apache-2.0 weights with vLLM, SGLang and transformers instructions; use is also subject to the Thinking Machines Model Acceptable Use Policy. Training code and data are not published. Released 2026-11-20.

Score

6.4

Consistency

9.2

Total Output Tokens

339,066

Total Input Tokens

401,060

Input Price

$0.100 / 1M

Output Price

$0.400 / 1M

Cache Read Price

$0.020 / 1M

Cache Write Price

N/A

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: 10

Attempt pass rate: 62.3%

Flaky tests

2

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

Response Time (avg)

27.95s

Response Time (max): 152.77s

Response Time (total): 642.86s

Hamster playing table tennis

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

#305 Thinking Machines: Inkling 2 Mini

low
Cost
$0.001
Time
12.1s
Tokens
2,152 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

Category Breakdown

Category Score Consistency Tests Correct
Agentic 3.4 9.6
Anti-AI Tricks 10.0 10.0
Coding 5.9 7.2
Combined 6.3 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.9 7.2
General Intelligence 5.3 10.0
Instructions following 9.8 10.0
Puzzle Solving 5.9 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models