context-compressor
Public
bench / results / 2026-08-24-glm-4.7-flash-uncensored-heretic-neo-code-imatrix-max.md
bench / results / 2026-08-24-glm-4.7-flash-uncensored-heretic-neo-code-imatrix-max.md
Model: glm-4.7-flash-uncensored-heretic-neo-code-imatrix-max
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 | 3/5 | — | -183% | 49037.7/70564/71552 | ✅ | ✅ |
| research | 0/3 | — | 33% | 70176/70176/70176 | ✅ | ✅ |
| contradictory-updates | 3/3 | — | 25% | 2209/2209/2209 | ✅ | ✅ |
| tool-spam | 3/3 | 2/3 | 5% | 22117.4/14315/69894 | ✅ | ✅ |
Recall = seeded facts answered correctly from the compacted view alone. Results are comparable only within one model; see bench/README.md.
Model: glm-4.7-flash-uncensored-heretic-neo-code-imatrix-max
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 | 3/5 | — | -183% | 49037.7/70564/71552 | ✅ | ✅ |
| research | 0/3 | — | 33% | 70176/70176/70176 | ✅ | ✅ |
| contradictory-updates | 3/3 | — | 25% | 2209/2209/2209 | ✅ | ✅ |
| tool-spam | 3/3 | 2/3 | 5% | 22117.4/14315/69894 | ✅ | ✅ |
Recall = seeded facts answered correctly from the compacted view alone. Results are comparable only within one model; see bench/README.md.