X Browse (xAI)
Agents answer questions that need multi-hop search and browsing on the X platform. Scored by answer accuracy.
xAI describes it in one sentence as an internal benchmark and gives no grading details, so the scoring type is assumed.
- Made by
- xAI
- Released
- November 2025
- Kind
- Deep research
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Kept private
- Strongest model tested
-
Gemini 3 Pro #55 on the capability index - Last in a launch post
- November 2025, dropped before it saturated
- Last model added
- November 2025
- Scores refreshed
- November 12th, 2026
Grok 4 Fast leads with 58%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
Grok 4.1 Fast leads with 56.3% across all independent runs
Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.
Grok 4 Fast leads with 58%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.
- 1 Grok 4 Fast 58%
- 2 Grok 4.1 Fast 56.3%
Source: Labs’ model cards
- 1 Grok 4.1 Fast 56.3%
- 2 Gemini 3 Pro 26.5%
- 3 GPT-5 24.2%
- 4 Claude Sonnet 4.5 14.6%
Source: Official X Browse (xAI) leaderboard
- 1 Grok 4 Fast 58%
- 2 Grok 4.1 Fast 56.3%
- 3 Gemini 3 Pro 26.5%
- 4 GPT-5 24.2%
- 5 Claude Sonnet 4.5 14.6%
Sources: Labs’ model cards and official X Browse (xAI) leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4 Fast | 58% | Sep 2025 | Lab model card | |
| 2 | Grok 4.1 Fast | 56.3% | Nov 2025 | Lab model card |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4.1 Fast | 56.3% | Agent Tools API | Nov 2025 | Official leaderboard |
| 2 | Gemini 3 Pro | 26.5% | Nov 2025 | Official leaderboard | |
| 3 | GPT-5 | 24.2% | Aug 2025 | Official leaderboard | |
| 4 | Claude Sonnet 4.5 | 14.6% | Sep 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4 Fast | 58% | Sep 2025 | Lab model card | |
| 2 | Grok 4.1 Fast | 56.3% | Agent Tools API | Nov 2025 | Official leaderboard |
| 3 | Gemini 3 Pro | 26.5% | Nov 2025 | Official leaderboard | |
| 4 | GPT-5 | 24.2% | Aug 2025 | Official leaderboard | |
| 5 | Claude Sonnet 4.5 | 14.6% | Sep 2025 | Official leaderboard |
The benchmark's own leaderboard has 4 models. Switch the scores above to rank them together.
Number one over time 3 models have held number one across all independent runs since its release in November 2025 Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official X Browse (xAI) 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 X Browse (xAI) leaderboard and labs’ model cards
No launch post has listed it since November 2025
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 |
|---|---|---|---|
| Nov 19, 2025 | Grok 4.1 Fast | 56.3 | X Browse (internal, Agent Tools API) |
| Sep 19, 2025 | Grok 4 Fast | 58 | X Browse (internal) pass@1 |
One lab claim 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. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| Grok 4.1 Fast | 56.3% X Browse (internal, Agent Tools API) | 56.3% Leaderboard, Agent Tools API | 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%