Benchmark Almanac

Fara-7B

Fara-7B.

Microsoft Released November 24th, 2025 Family Fara The lab's model card Compare with others
7
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Microsoft Nov 2025

Fara-7B

Open weights Small

No Epoch Capabilities Index score yet
  • WebTailBench 24.1% #7 /7
  • WebVoyager 73.5% #11 /12
  • ScreenSpot-v2 89.3% #11 /14

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Agents and tools

BenchmarkScoreRankSource
ScreenSpot 86.7% #8 of 11 Lab model card
ScreenSpot-v2 89.3% #11 of 14 Lab model card
WebVoyager 73.5% #11 of 12 Lab model card
Online-Mind2Web 34.1% #10 of 10 Lab model card
WebTailBench 24.1% #7 of 7 Official leaderboard
DeepShop 26.2% #2 of 2 Lab model card

Safety and security

BenchmarkScoreRankSource
WebTailBench-Refusals 81.9% #2 of 2 Lab model card

Its lab's number next to a leaderboard

Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.

Benchmark Lab says Board says Gap
WebTailBench 38.4% WebTailBench 24.1% Leaderboard, v1.5 +14 pts

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 4 of them aren't in the launch post.