Context-Bench
Benchmarks & Leaderboards · Free + paid
A benchmark for agentic context engineering
At a glance
- Made by
- Letta
- Korean
- None (English and a few others only)
- Available on
- Web
What is Context-Bench?
Context-Bench is a benchmark of agents' context engineering ability, created by Letta Research. The Filesystem Suite evaluates the ability to chain file operations, track entity relationships, and retrieve information across multiple steps, while the Skills Suite evaluates the ability to find and load relevant skills from a library and complete tasks. Grading uses LLM-judge rubrics, and the leaderboard shows each model's score and cost. Task or model contributions are accepted by email or GitHub issue.
- Filesystem Suite (file-based retrieval and reasoning)
- Skills Suite (skill discovery, loading, and use)
- LLM-as-a-judge rubric grading
- Score and cost shown per model
- Filter by provider
- Update history
Who uses Context-Bench and for what
- Developers compare context-handling ability when choosing a model for agents
Pricing
Free (public benchmark/leaderboard)
Mostly free leaderboards/datasets released for academic and community purposes
Estimate based on AI knowledge - please verify on the official site
AI tools similar to Context-Bench (alternatives)
Context-Bench vs. alternatives at a glance
| AI | Pricing | Combos on the map | Connected tools | Free | Cheapest monthly | Korean |
|---|---|---|---|---|---|---|
| Context-Bench | Free + paid | 0 | 11 | — | — | No |
| APEX-Agents | Free + paid | 0 | 11 | — | — | No |
| ARC-AGI-2 | Free + paid | 0 | 11 | — | — | No |
| MCP Atlas | Free + paid | 0 | 11 | — | — | No |
| OSWorld | Free + paid | 0 | 5 | — | — | — |
0 of these 5 tools have a free plan.
Combo and connection counts are based on the relationships recorded on AI Galaxy Map (2026-10-26); they are not a quality ranking.
Context-Bench on AI Galaxy Map
- One of 27 AI tools in the Benchmarks & Leaderboards field.
- Connected to 11 other tools — #6 in its field.
Frequently asked questions
Can I use Context-Bench for free?
Free (public benchmark/leaderboard). Prices can change, so check the official site before paying.
What AI can I use instead of Context-Bench?
Tools that do the same job, such as APEX-Agents, ARC-AGI-2, MCP Atlas, OSWorld, are connected to it on the map.
Can I use Context-Bench in Korean?
None (English and a few others only)
Sources (official pages)
Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying.