FrontierCode
Private maintainer-authored repository tasks graded for mergeability: correctness, tests, scope discipline, style, and code quality.
FrontierCode 1.1 remains difficult and newly launched; Cognition's official results show substantial headroom on the current Main and Extended sets.
Performance Timeline
Longitudinal progression of model scores against human baselines.Performance & Historical Trajectory
Empirical score progression across model release dates and evaluation rounds.
| Model | Score | Date | Source Type | Provenance |
|---|---|---|---|---|
| SWE-1.6 (FrontierCode 1.1 Main pass rate) | 9.4% | 2024-06-01 | vendor-reported | Source ↗ |
| Kimi K2.7 Code (FrontierCode 1.1 Main pass rate) | 30.1% | 2024-06-01 | independent | Source ↗ |
| SWE-1.7 (FrontierCode 1.1 Main pass rate) | 42.3% | 2024-06-01 | vendor-reported | Source ↗ |
| GPT-5.5 (FrontierCode 1.1 Main pass rate) | 43% | 2024-06-01 | independent | Source ↗ |
| Claude Opus 4.8 (FrontierCode 1.1 Main pass rate) | 46.5% | 2024-06-01 | independent | Source ↗ |
Human Baseline & Difficulty Horizon
Calibrated human reference points, specialist benchmarks, and ceiling thresholds.Senior software engineer completion rate on repository-scale frontier programming challenges.
Metric & Scoring Methodology
Verification protocols, aggregation formulas, and specialized metric variants.pass rate on FrontierCode 1.1 Main (%)Dataset & Compute Cost
Evaluation volume, public availability, API pricing, and local hardware requirements.$5 – $20 USD for full benchmark evaluation run on frontier APIs.
1x NVIDIA RTX 4090 (24GB) or A100 (40GB/80GB) via vLLM / SGLang
How to Run & Reproduce
Standardized evaluation protocols, CLI commands, and reproducible runner templates.lm_eval --model hf --model_args pretrained=<model_path> --tasks frontiercode --batch_size autoopencompass --datasets frontiercode --models <model_config># Standard API Evaluation Loop
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": prompt}],
temperature=0.0,
)When publishing results for FrontierCode, always report the exact prompt template, few-shot exemplar ordering, sampling temperature (temperature=0), maximum reasoning budget tokens, and the precise timestamped model snapshot ID.
Contamination & Memorization Analysis
Audit of pretraining exposure risks, memorization vectors, and refresh policies.Static fixed snapshot
Public on web / HuggingFace