Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

Update notices

A note when a benchmark one of your indexes uses gets a new version, with a one-click upgrade.

Other · released 2026-10-27

LFM3-VL-2B

Measured on 25 benchmarks.

Compare

1.7

#81 of 81 models

Strengths

  • LFM3-VL-2B
  • Fable 5.2 (#1)
  • Field median
bestField medianFrontierCode 2.0-AATerminal-Benchv4-AAAutomationBench-AAAA-Briefcase v1.1GDP.pdfTerminal-Bench-Science-AACritPt v2 HardSubsetAA-Omnisciencev1.1 AccuracyHLE-DiamondAA-Omnisciencev1.1Non-hallucination
  1. FrontierCode 2.0-AA15%0.0%#75 of 81
  2. Terminal-Bench v4-AA10%0.0%#68 of 81
  3. AutomationBench-AA5%0.2%#80 of 81
  4. AA-Briefcase v1.115%0.0#73 of 81
  5. GDP.pdf5%0.0%#81 of 81
  6. Terminal-Bench-Science-AA15%0.0%#58 of 81
  7. CritPt v2 Hard Subset10%0.0%#77 of 81
  8. AA-Omniscience v1.1 Accuracy10%8.7%#79 of 81
  9. HLE-Diamond10%4.6%#75 of 81
  10. AA-Omniscience v1.1 Non-hallucination5%7.3%#79 of 81

Bars show where LFM3-VL-2B sits among the 81 ranked models on each benchmark (right is best); the tick is the field median.

By category

  • LFM3-VL-2B
  • Fable 5.2 (#1)
  • Field median
p25p50p75topField medianCodingAgents & computeruseProfessional workScience & researchReasoning &puzzlesKnowledge &accuracyVision
  1. Coding2 benchmarks1%#81 of 81
  2. Agents & computer use5 benchmarks1%#81 of 81
  3. Professional work3 benchmarks0%#81 of 81
  4. Science & research3 benchmarks3%#79 of 80
  5. Reasoning & puzzles2 benchmarks4%#76 of 79
  6. Knowledge & accuracy3 benchmarks3%#80 of 80
  7. Vision2 benchmarks0%#67 of 67

Across 20 results on every current benchmark that measured LFM3-VL-2B, not only this ranking’s. The percentage is its average standing among the 81 models in this ranking that took the same benchmarks: 100% beat them all, 0% trailed them all. A benchmark in two categories counts in both; a category needs two benchmarks.

Cost and speed

against 81 ranked models

Output speed

#2 fastest of 66

356 tok/s

Time to first token

quickest of 66

0.5s

Output tokens per task

#9 fewest of 73

41k

Token price

$0.024 per 1M tokens at API prices

97.0% cache read · 2.50% fresh input · 0.00% cache write · 0.50% output

Assumed mix: no measured T3 Code usage for this model.

Not measured for LFM3-VL-2B: cost per task, time per task (no published API price yet).

Availability

API providers

1
ProviderIn / out per 1MTok/sFirst
  • Liquid AI$0.10 / $0.503560.5s

Artificial Analysis

This ranking’s benchmarks

10 of 10 measured

Cost per task is what a subscriber pays: the model’s plan price, a share of API price. Models no plan sells are at API price.

Agents & computer use

AutomationBench-AA

282 results
  1. #276default of 2820.2%

Leader: Gemini 4 Neon · 79.3%

Professional work

AA-Briefcase v1.1

287 results
  1. #278default of 2870

Leader: Sonnet 5.5 · 1815

Science & research

CritPt v2 Hard Subset

159 results
  1. #159default of 1590.0%

Leader: Fable 5.2 · 76.5%

Coding

FrontierCode 2.0-AA

156 results
  1. #156default of 1560.0%

Leader: Fable 5.2 · 49.1%

Professional work

GDP.pdf

281 results
  1. #278default of 2810.0%

Leader: Gemini 4 Neon · 33.4%

Knowledge & accuracy

HLE-Diamond

196 results
  1. #178default of 1964.6%

Leader: Fable 5.2 · 80.2%

Knowledge & accuracy

AA-Omniscience v1.1 Accuracy

169 results
  1. #167default of 1698.7%

Leader: Fable 5.2 · 79.1%

Knowledge & accuracy

AA-Omniscience v1.1 Non-hallucination

169 results
  1. #164default of 1697.3%

Leader: Gemini 4 Carbon · 95.8%

Science & research

Terminal-Bench-Science-AA

167 results
  1. #165default of 1670.0%

Leader: GPT-6.2 Astra · 78.6%

Agents & computer use

Terminal-Bench v4-AA

278 results
  1. #226default of 2780.0%

Leader: Kimi K3.1 · 67.2%

All 25 benchmarks

show 15 more