Leaderboard
AI is only as safe as its weakest models
leaderboard.far.ai AI Models & Agents / Prompts, Evals & LLM Observability
- Monthly visits
- <5K
- Sep 2026
- Public revenue
- Undisclosed
- No public revenue evidence yet
- Entry price
- Free
- No monthly subscription pricing
- Launched
- 4mo ago
- 2026-07-29 · Est.
Traffic
Marketing moves
Launches, search & content, referrals, promotions- In Sydney for NeurIPS? On Monday, December 7, we’re co-hosting an evening with Gradient Institute on the state of frontier AI evaluation and red teaming. @IBeMrT opens with a technical talk on our red-teaming work and the AI Security Leader
@farairesearch · 2026-11-09 · 5 likes · 1 reposts · 698 views
- @StephenLCasper 🔗 https://buff.ly/oLjCmvk 回复原帖 @farairesearch： At the CAIRD workshop, @StephenLCasper argued AI politics is incident-driven. AI policy debates have barely moved since 2023, but policy can sit still for years and then move
@farairesearch · 2026-10-29 · 3 likes · 0 reposts · 458 views
- At the CAIRD workshop, @StephenLCasper argued AI politics is incident-driven. AI policy debates have barely moved since 2023, but policy can sit still for years and then move in weeks after a shock. His call to researchers is to do the work
@farairesearch · 2026-10-29 · 23 likes · 5 reposts · 2,102 views
Launched on Show HN (4 pts)Launch
AI Security Leaderboard – comparing cyber and CBRN safeguards — There's no shortage of leaderboards for model capabilities - but the security of models is becoming increasingly relevant, from the risk o…
Jul 29 · 4mo agoLaunch page
Third-party reviews & case dossiers
Acquisition breakdowns, engineer reviews & open-source metrics- Post excerpt:
- There's no shortage of leaderboards for model capabilities - but the security of models is becoming increasingly relevant, from the risk of an AI agent processing unsanitized input being hijacked to models being pulled due to cybersecurity jailbreaks. We developed an automated test suite that runs models through 1500 automatically generated jailbreak attempt
Traffic sources
Traffic breakdown
Channels
- Direct46%
- Organic Search30%
- Referrals7%
- Social6%
- Other11%
Countries
- United States78%
- Canada10%
- Germany8%
- India5%
Search
Domain authority —Domain registered 2017-12-16
| Keyword | Monthly volume |
|---|---|
| gemini jailbreak | 5,610 |
| most vulnerable models ai jailbreakbel | 120 |
| far.ai's ai security leaderboard | 40 |
| ai model leaderboard hacking | 10 |
Traffic data: Vaneform
Pricing
Website does not list public plan prices.
Trial: None · Observed 2026-11-05 · Source page
Pages & changes
Key pages
Weekly snapshotsChanges
No pricing, plan, or positioning changes detected since tracking started.
Questions & evidence
- How much website traffic does Leaderboard get?
- Vaneform estimates <5K website visits in 2026-09. Visits can include repeat visits; this estimate does not measure paying customers or revenue.Source
Related products in this category
These products share a catalog category. Compare customer tasks, features and deployment requirements before treating them as alternatives.
| Product | Entry price | Visits | Revenue |
|---|---|---|---|
| LMSYS Chatbot ArenaGiantExperience the frontier | — | 30M | Undisclosed |
| Prompt CowboyTurn lazy prompts into great ones | $8/mo | 1.5M | Undisclosed |
| Codex雷达站查看雷达站正在改什么：工单分组内全部工单的阶段、进展与最近变化。 | — | 946.3K | Undisclosed |
| LiveBench 2.0A challenging, contamination-free long-horizon AI benchmark. | — | 824.6K | Undisclosed |
| LangfuseOpen Source Agent Evals &Observability | $29/mo | 722.9K | Undisclosed |
| 鉄道模型 NgaugeJP公式サイト鉄道模型Ｎゲージ新製品、発売日などNゲージに関する情報サイト（Nゲージインフォメーション） | — | 689.4K | Undisclosed |