- Score
- 8.6 (+4.51 points)
- Total Cost (Current Price)
- $0.061 · 27.7% cheaper
- Response Time (avg)
- 7.51s · 55.8% faster
Liquid
Release: 2026-11-06
Tested on: 2026-11-09 22:19
liquid/lfm-3-1.7b::none
1.7BDenseWeights available Summary
LFM3-1.7B scores 4.1 on AI BENCHY and ranks #430. It has 10.0 reliability, a 34.8% pass rate, $0.084 total cost, and 16.99s average response time.
What makes LFM3-1.7B unique: It stands out most in Combined, where it ranks #1, while Data parsing and extraction is its weakest area at #9.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 8.3 (+4.20 points)
- Total Cost (Current Price)
- $0.047 · 43.9% cheaper
- Response Time (avg)
- 18.07s · 6.3% slower
- Score
- 5.2 (+1.13 points)
- Total Cost (Current Price)
- $0.004 · 95.9% cheaper
- Response Time (avg)
- 3.40s · 80.0% faster
Model facts
Researched on 2026-11-09
- Parameters
- 1.7B
- Architecture
- Dense
- Availability
- Weights available
- License
- LFM-1.0
The official model card reports 1.73B parameters in a 24-layer tri-hybrid stack of gated short convolutions, sliding-window and global attention; dense here means no mixture of experts. Weights are public and ungated under the custom LFM Open License v1.0, so the checkpoint is weights_available rather than open_source.
4.1
Consistency
8.2
10.0
$0.084
Total Output Tokens
329,997
Total Input Tokens
219,830
Input Price
$0.080 / 1M
Output Price
$0.200 / 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.
Flaky tests
5
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#430 LiquidAI: LFM3-1.7B
default
OpenRouter returned no showcase content (finish_reason: length).
- Cost
- $0.002
- Time
- 23.3s
- Tokens
- 8,320 tok
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
LFM3-1.7BdefaultFree AvailablevsMercury 2.5noneLFM3-1.7BdefaultFree AvailablevsQwen3.5-9BmediumLFM3-1.7BdefaultFree Availablevsgpt-oss-120bnoneLFM3-1.7BdefaultFree AvailablevsLing 3.0 TinydefaultLFM3-1.7BdefaultFree AvailablevsGLM 4.7 FlashmediumLFM3-1.7BdefaultFree AvailablevsGranite 4.1 8bdefaultLFM3-1.7BdefaultFree AvailablevsMiniMax M2.5mediumLFM3-1.7BdefaultFree AvailablevsNemotron 3.5 LightningnoneFree AvailableLFM3-1.7BdefaultFree AvailablevsMercury 2noneLFM3-1.7BdefaultFree AvailablevsXing4.0 29b A4bmediumFree Available
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 3.4 | 9.6 | |
| Anti-AI Tricks | 7.0 | 7.9 | |
| Coding | 2.9 | 10.0 | |
| Combined | 6.5 | 10.0 | |
| Data parsing and extraction | 2.9 | 5.8 | |
| Domain specific | 5.9 | 7.2 | |
| General Intelligence | 4.2 | 9.9 | |
| Instructions following | 6.3 | 10.0 | |
| Puzzle Solving | 4.2 | 4.4 | |
| Tool Calling | 3.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |