context-compressor
Public
bench / results / 2026-08-20-qwen-qwen3.8-27b.md
bench / results / 2026-08-20-qwen-qwen3.8-27b.md
Model: qwen/qwen3.8-27b
Settings: {"limitTokens":500,"floorTokens":400,"keepRecentTokens":300,"chunkTokens":800,"summarizerMaxTokens":400,"consolidationBudgetTokens":600,"consolidationKeepNewest":2,"mergeMaxTokens":400,"maxExcerptChars":32000,"quizMaxTokens":120}
| Fixture | Recall (compacted) | Recall (consolidated) | Reduction | Chunk latency mean/p50/max (ms) | Structure | Cache |
|---|---|---|---|---|---|---|
| coding-agent | 5/5 | 5/5 | 29% | 13110/10717/16644 | ✅ | ✅ |
| research | 2/3 | — | 7% | 15144.5/14547/15742 | ✅ | ✅ |
| contradictory-updates | 3/3 | — | 18% | 25103/25103/25103 | ✅ | ✅ |
| tool-spam | 3/3 | 3/3 | 28% | 14076.9/12223/21075 | ✅ | ✅ |
Recall = seeded facts answered correctly from the compacted view alone. Results are comparable only within one model; see bench/README.md.
Model: qwen/qwen3.8-27b
Settings: {"limitTokens":500,"floorTokens":400,"keepRecentTokens":300,"chunkTokens":800,"summarizerMaxTokens":400,"consolidationBudgetTokens":600,"consolidationKeepNewest":2,"mergeMaxTokens":400,"maxExcerptChars":32000,"quizMaxTokens":120}
| Fixture | Recall (compacted) | Recall (consolidated) | Reduction | Chunk latency mean/p50/max (ms) | Structure | Cache |
|---|---|---|---|---|---|---|
| coding-agent | 5/5 | 5/5 | 29% | 13110/10717/16644 | ✅ | ✅ |
| research | 2/3 | — | 7% | 15144.5/14547/15742 | ✅ | ✅ |
| contradictory-updates | 3/3 | — | 18% | 25103/25103/25103 | ✅ | ✅ |
| tool-spam | 3/3 | 3/3 | 28% | 14076.9/12223/21075 | ✅ | ✅ |
Recall = seeded facts answered correctly from the compacted view alone. Results are comparable only within one model; see bench/README.md.