reasoning benchmark
FrontierCode 2.0 Leaderboard
FrontierCode 2.0 is Cognition's private benchmark for assessing the end-to-end code quality of coding-agent changes.
Updated Nov 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
FrontierCode 2.0 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score49.10% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelMA | Score19.70% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
FrontierCode 2.0 Highlights
The leading models and scores on this benchmark.
FrontierCode 2.0 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for FrontierCode 2.0
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is FrontierCode 2.0?
What FrontierCode 2.0 measures and how its scores work.
FrontierCode 2.0 is a private benchmark assessing coding-agent changes.
It measures the end-to-end code quality of coding-agent changes, including whether a repository maintainer would merge the change.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FrontierCode 2.0
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about FrontierCode 2.0.
Which model scores highest on FrontierCode 2.0?
Claude Fable 5.2 is currently ranked first with 49.10%.
What are the top three models on FrontierCode 2.0?
The current leaders are Claude Fable 5.2 (49.10%) and Mistral Large 4 (19.70%).
Which FrontierCode 2.0 model has the lowest official input price?
Mistral Large 4 has the lowest matched official input price at $0.70 input / $2.1 output per 1M tokens.
Which models are fastest among FrontierCode 2.0 results?
The fastest matched records are Mistral Large 4 (50.35 tok/s via Mistral AI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.