Fara1.5-27B model card (Hugging Face) May 21, 2026
- WebVoyager 89.3
- Online-Mind2Web 72.3
- WebTailBench 40.2
Fara1.5-27B
Fara1.5-27B ranks first on 2 of the 6 benchmarks with five or more models scored.
7
Benchmarks with a score
2
Ranked first, out of five or more models
4
In the top three
Microsoft May 2026 Fara1.5-27B
Open weights Mid-size
No Epoch Capabilities Index score yet
- WebTailBench 40.2% #3 /7
- OSWorld-G 71.3% #1 /5
- ScreenSpot-Pro 66.8% #18 /32
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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WebVoyager | 89.3% | #1 of 12 | Lab model card | |
| ScreenSpot-v2 | 94.4% | #2 of 14 | Lab model card | |
| OSWorld-G | 71.3% | #1 of 5 | Lab model card | |
| WebTailBench | 40.2% | #3 of 7 | Official leaderboard | |
| ScreenSpot-Pro | 66.8% | #18 of 32 | Lab model card | |
| Online-Mind2Web | 72.3% | #7 of 10 | Lab model card |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WebTailBench-Refusals | 100% | #1 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 | 40.2% WebTailBench | 40.2% Leaderboard, v1.5 | Same |
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.
Capabilities
- WebVoyager 89.3
- Online-Mind2Web 72.3
- WebTailBench 40.2
- ScreenSpot-v2 94.4
- ScreenSpot-Pro 66.8
- OSWorld-G 71.3