FrontierCode
cognition.com- Category
- Developer Tools
- Rank
- No. 2531Tools index
Previous survey · No. 2390 ·
- Listed in
- Find AI benchmarks
- Type
- TOOL
- Use case
- Model & Agent Evaluation
- Date
About
Cognition's benchmark of hard, real open-source issues where coding agents must produce mergeable fixes. Epoch AI found too little public information to review it, so treat reported scores cautiously.
Why it made the leaderboard
Compare the task, benchmark version, harness, and grading method before using model scores to choose a model.
Intel on FrontierCode
- Gemini 4 models land on Cognition's FrontierCode 2.0
- Cognition's FrontierCode 2.0 tests judgment beyond the spec
- Coding Agent Index v2.0 swaps in FrontierCode and resets the scores
- FrontierCode 1.1 benchmarks mergeable PRs on Artificial Analysis
- FrontierCode 1.1 leaderboard grades coding models on merge-readiness
Tags
benchmarkevaluation
Media
Comments (0)
No comments yet
Editorially curated, with community endorsements as a secondary signal. Corrections welcome.