agents benchmark
FrontierSWE V2 Leaderboard
FrontierSWE V2 evaluates agents on open-ended technical projects and reports mean@5.
Updated Sep 24, 2026
Models2
Model coverage2
MetricScore
EvidenceB
FrontierSWE V2 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score62.30% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelXA | Score29.00% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
FrontierSWE V2 Highlights
The leading models and scores on this benchmark.
FrontierSWE V2 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for FrontierSWE V2
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is FrontierSWE V2?
What FrontierSWE V2 measures and how its scores work.
FrontierSWE V2 is a benchmark for agents working on open-ended technical projects.
It measures performance using mean@5, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FrontierSWE V2
- Modality
- text
- Primary category
- agents
- 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 FrontierSWE V2.
Which model scores highest on FrontierSWE V2?
Claude Opus 5.5 is currently ranked first with 62.30%.
What are the top three models on FrontierSWE V2?
The current leaders are Claude Opus 5.5 (62.30%) and Grok 4.7 (29.00%).
Which FrontierSWE V2 model has the lowest official input price?
Grok 4.7 has the lowest matched official input price at $2.0 input / $6.0 output per 1M tokens.
Which models are fastest among FrontierSWE V2 results?
The fastest matched records are Claude Opus 5.5 (64.14 tok/s via Anthropic) and Grok 4.7 (5.32 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.