FocusBench (Meta)
Muse Wonder Full 54.2% leads since October 2026 Agents do personal tasks in domains such as housing, travel, IT and finance. The test checks whether they keep working through real-world blockers across several interactions as the environment changes.
Meta in-house eval behind the Active Focus feature, reported in the Muse Wonder model card. The card does not say how tasks are graded, so the scoring type is a guess. Part of Meta's PSI composite.
- Released
- October 2026
- Kind
- General assistants
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Kept private
- Strongest model tested
- GPT-6 Astra #3 on the capability index
- Last in a launch post
- October 2026
- Last model added
- October 2026
- Scores refreshed
- November 12th, 2026
Muse Wonder Full leads with 54.2%
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1 Muse Wonder Full max 54.2%
- 2 GPT-6 Astra max 47.7%
- 3 Claude Opus 5.5 max 45.8%
- 4 Muse Wonder max 44.9%
- 5 Claude Fable 5.1 max 36.6%
Source: Official FocusBench (Meta) leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Muse Wonder Full | 54.2% | max | Oct 2026 | Official leaderboard |
| 2 | GPT-6 Astra | 47.7% | max | Sep 2026 | Official leaderboard |
| 3 | Claude Opus 5.5 | 45.8% | max | Sep 2026 | Official leaderboard |
| 4 | Muse Wonder | 44.9% | max | Oct 2026 | Official leaderboard |
| 5 | Claude Fable 5.1 | 36.6% | max | Sep 2026 | Official leaderboard |
Labs report scores for 2 models in their cards. We plot every source in the charts below.
2 models have held number one on the official leaderboard since its release in October 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official FocusBench (Meta) leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official FocusBench (Meta) leaderboard and labs’ model cards
One lab put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Oct 12, 2026 | Muse Wonder | 44.9 | FocusBench (chart label) |
| Oct 12, 2026 | Muse Wonder Full | 54.2 | FocusBench (chart label) |
2 lab claims next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 2 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| Muse Wonder Full | 54.2% FocusBench (chart label) | 54.2% Leaderboard, max | Same |
| Muse Wonder | 44.9% FocusBench (chart label) | 44.9% Leaderboard, max | Same |
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state.
Gemini 4 Carbon 53.9% - MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
- BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes.
Qwen3.7-Max 75% - τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
- Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%