ContextBench: leaderboard
Benchmark for context retrieval in coding agents, measuring how well agents retrieve and use multi-file code context before producing fixes.
Metric: Pass@1 (percentage). Source: contextbench.github.io. Source: benchmarklist.com. Saturation forecast: Around October 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 53 | #142 |
| 2 | GPT-5 | 47.2 | #98 |
| 3 | Devstral 2 | 40.2 | #411 |
| 4 | Gemini 2.5 Pro | 36.4 | #152 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=contextbench · How It Works · Data refreshed daily, snapshot 2026-10-20.