From 3241fd2428d6abdefd548fb059c480e9a2fc580f Mon Sep 17 00:00:00 2001 From: marcot3ssar1 Date: Sun, 6 Sep 2026 05:50:02 +0200 Subject: [PATCH] Add infiniteMem external rows (LoCoMo + LongMemEval-S, self-reported) --- external_results.json | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) diff --git a/external_results.json b/external_results.json index 71988cf..2bc2de2 100644 --- a/external_results.json +++ b/external_results.json @@ -221,6 +221,20 @@ "source_url": "https://memmachine.ai/blog/2025/09/memmachine-reaches-new-heights-on-locomo/", "source_label": "MemMachine Blog (Sep 2025)", "comment": "Evaluated by a competitor (MemMachine). LLM-as-a-judge with GPT-4o-mini. Adversarial questions excluded. Results reported by a competing system \u2014 potential for biased setup or prompt choices." + }, + { + "memory": "infiniteMem (mini top-50)", + "accuracy": 0.759, + "source_url": "https://github.com/marcot3ssar1/InfiniteMemOs/releases/tag/v1.2-top50-kimi", + "source_label": "infiniteMem v1.2 (self-reported, reproducible)", + "comment": "Self-reported. Brute top-50 contexts, mini reader+judge, Mem0 prompts verbatim, cat5 excluded, n=1535. Engine re-certified: contexts bit-identical to frozen engine output (see MEASUREMENT_NOTE.md). Per-question cache in repo." + }, + { + "memory": "infiniteMem (kimi-k3 top-50)", + "accuracy": 0.8599, + "source_url": "https://github.com/marcot3ssar1/InfiniteMemOs/releases/tag/v1.2-top50-kimi", + "source_label": "infiniteMem v1.2 (self-reported, reproducible)", + "comment": "Self-reported. kimi-k3 reader, brute top-50, mini judge pinned, Mem0 prompts verbatim, cat5 excluded, n=1535. Different reader from mini rows - not directly comparable. Per-question cache in repo." } ] }, @@ -386,6 +400,20 @@ "source_url": "https://arxiv.org/abs/2603.16862", "source_label": "Chronos Paper (arXiv:2603.16862)", "comment": "Self-reported by Chronos authors. Best of two configurations tested; the GPT-4o configuration achieved 92.6%. This configuration uses Claude Opus 4.6 as backbone, which is considerably more capable than the models used by most other entries here." + }, + { + "memory": "infiniteMem (mini top-10)", + "accuracy": 0.598, + "source_url": "https://github.com/marcot3ssar1/InfiniteMemOs/releases/tag/v1.3-lmem-kimi", + "source_label": "infiniteMem v1.3 (self-reported, reproducible)", + "comment": "Self-reported. Brute top-10 sessions, mini reader+judge, upstream prompts verbatim, n=500 incl. ABS. Per-question cache in repo." + }, + { + "memory": "infiniteMem (kimi-k3 top-5)", + "accuracy": 0.888, + "source_url": "https://github.com/marcot3ssar1/InfiniteMemOs/releases/tag/v1.3-lmem-kimi", + "source_label": "infiniteMem v1.3 (self-reported, reproducible)", + "comment": "Self-reported. kimi-k3 reader (max_tokens 1500), brute top-5 sessions, mini judge pinned, upstream prompts verbatim, n=500 incl. ABS. 6 structural errors declared. Per-question cache in repo." } ] }, @@ -651,4 +679,4 @@ } ] } -} \ No newline at end of file +}