AI BENCHY
Advertise here
#292

LFM2-24B-A2B

Liquid Release: 2026-02-24 Tested on: 2026-05-06 14:04 liquid/lfm-2-24b-a2b::none
24B total (2.3B active)MoEWeights available

Summary

LFM2-24B-A2B scores 2.2 on AI BENCHY and ranks #292. It has N/A reliability, a 12.1% pass rate, $0.001 total cost, and 782ms average response time.

What makes LFM2-24B-A2B unique: It stands out most in Domain specific, where it ranks #6, while Anti-AI Tricks is its weakest area at #25. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Archived model: this model is no longer updated or tested on new tests.

Model facts

Researched on 2026-08-12

Reported
Parameters
24B total (2.3B active)
Architecture
MoE
Availability
Weights available
License
LFM-1.0
Parameter source Availability source

Score

2.2

Consistency

6.9

Reliability

N/A

Total Cost (Current Price)

$0.001

Total Output Tokens

1,173

Total Input Tokens

10,771

Input Price

$0.030 / 1M

Output Price

$0.120 / 1M

Tests Correct

Wrong Tests: 14

Attempt pass rate: 12.1%

Flaky tests

1

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

Response Time (avg)

782ms

Response Time (max): 3.15s

Response Time (total): 10.94s

Wrong answer: 9 API error: 4 Did not follow instructions: 1

Hamster playing table tennis

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

#292 LiquidAI: LFM2-24B-A2B

none
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-05-06 14:04 Re-test 2.2 N/A $0.001 Current run
2026-05-06 14:04 Re-test 2.2 N/A $0.001 Compare
2026-05-06 14:04 Re-test 4.2 N/A $0.001 Compare
2026-05-06 14:04 Re-test 4.2 N/A $0.001 Compare
2026-05-06 14:04 Suite changed 4.2 N/A $0.001 Compare
2026-04-10 23:27 First recorded run 4.1 N/A $0.001 Compare

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 15:40 $0.030 / 1M $0.120 / 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

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 2.5 7.4
Coding 0.0 0.0
Combined 1.5 5.0
Data parsing and extraction 3.0 10.0
Domain specific 5.9 7.2
General Intelligence 4.0 10.0
Instructions following 6.3 10.0
Puzzle Solving 3.8 10.0
Tool Calling 3.0 10.0
Trivia 0.0 0.0

Compared models