reasoning benchmark
FrontierCode 1.1 Leaderboard
FrontierCode 1.1 evaluates whether coding-agent changes are mergeable using unit tests, maintainer-defined rubrics, and verifiers.
Updated Oct 23, 2026
Models23
Model coverage23
MetricScore
EvidenceB
FrontierCode 1.1 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score54.40% | Percentile100.00% | Participants23 | EvidenceC | Evaluated |
| Rank02 | ModelAN | Score53.50% | Percentile95.45% | Participants23 | EvidenceB | Evaluated |
| Rank03 | ModelAN | Score53.40% | Percentile90.91% | Participants23 | EvidenceB | Evaluated |
| Rank04 | ModelOP | Score53.30% | Percentile86.36% | Participants23 | EvidenceC | Evaluated |
| Rank05 | ModelAN | Score52.10% | Percentile81.82% | Participants23 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score50.20% | Percentile77.27% | Participants23 | EvidenceB | Evaluated |
| Rank07 | ModelOP | Score49.30% | Percentile72.73% | Participants23 | EvidenceC | Evaluated |
| Rank08 | ModelOP | Score47.50% | Percentile68.18% | Participants23 | EvidenceB | Evaluated |
| Rank09 | ModelAN | Score46.50% | Percentile63.64% | Participants23 | EvidenceB | Evaluated |
| Rank10 | ModelAN | Score46.40% | Percentile59.09% | Participants23 | EvidenceC | Evaluated |
| Rank11 | ModelGO | Score43.60% | Percentile54.55% | Participants23 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score43.00% | Percentile50.00% | Participants23 | EvidenceB | Evaluated |
| Rank13 | ModelAN | Score42.70% | Percentile45.45% | Participants23 | EvidenceB | Evaluated |
| Rank14 | ModelXA | Score42.40% | Percentile40.91% | Participants23 | EvidenceB | Evaluated |
| Rank15 | ModelOP | Score42.40% | Percentile36.36% | Participants23 | EvidenceC | Evaluated |
| Rank16 | ModelOP | Score41.30% | Percentile31.82% | Participants23 | EvidenceB | Evaluated |
| Rank17 | ModelOP | Score39.80% | Percentile27.27% | Participants23 | EvidenceB | Evaluated |
| Rank18 | ModelAN | Score38.50% | Percentile22.73% | Participants23 | EvidenceB | Evaluated |
| Rank19 | ModelMA | Score30.10% | Percentile18.18% | Participants23 | EvidenceB | Evaluated |
| Rank20 | ModelZA | Score24.50% | Percentile13.64% | Participants23 | EvidenceB | Evaluated |
| Rank21 | ModelDE | Score17.60% | Percentile9.09% | Participants23 | EvidenceB | Evaluated |
| Rank22 | ModelMI | Score14.70% | Percentile4.55% | Participants23 | EvidenceB | Evaluated |
| Rank23 | ModelAC | Score10.20% | Percentile0.00% | Participants23 | EvidenceB | Evaluated |
FrontierCode 1.1 Highlights
The leading models and scores on this benchmark.
FrontierCode 1.1 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for FrontierCode 1.1
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is FrontierCode 1.1?
What FrontierCode 1.1 measures and how its scores work.
FrontierCode 1.1 is a reasoning benchmark for evaluating coding-agent changes.
It measures a Score reported as a ratio; runs flagged for unfair internet use receive a zero score.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FrontierCode 1.1
- 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 1.1.
Which model scores highest on FrontierCode 1.1?
Claude Opus 5.5 is currently ranked first with 54.40%.
What are the top three models on FrontierCode 1.1?
The current leaders are Claude Opus 5.5 (54.40%), Claude Fable 5 (53.50%), and Claude Opus 5 (53.40%).
Which FrontierCode 1.1 model has the lowest official input price?
Claude Haiku 5.5 has the lowest matched official input price at $0.10 input / $0.50 output per 1M tokens.
Which models are fastest among FrontierCode 1.1 results?
The fastest matched records are Gemini 3.7 Flash (409.96 tok/s via Google), GPT-5.6 Luna (215.52 tok/s via OpenAI), and Grok 4.5 (80.00 tok/s via xAI).
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.