Memory Discipline
Models answer project questions using saved memories. The tasks separate using relevant facts from asking for clarification when memories are absent or contradictory.
The two Kaggle tasks replay the recorded responses from the preregistered run.
- Made by
- GiulioDER
- Released
- October 2026
- Kind
- Finding facts in long inputs
- Level
- School
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
GPT-6 Astra leads with 99.7% among models released by September 2026 GPT-6 Astra leads with 99.7% among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- Claude Opus 5.5
- and 12 more
- 99.7 GPT-6 Astra
- 99.3
Gemini 2.5 Pro
- 99.3 Claude Sonnet 4.6
- 99.3
Gemma 4 31B IT
- 99.3
Gemini 3.7 Flash
- 99.3
Gemini 3.8 Flash
- 99.0 Claude Opus 4.7
- 99.0
Gemini 3.5 Flash
- 98.6
Gemini 3 Flash
- 98.6
Gemini 3.1 Pro
- 98.6
Gemini 3.6 Flash
- 98.3 Claude Opus 4.5
- 98.0 GPT-5.6 Luna
- 97.7 Claude Opus 4.8
- 97.7 Claude Opus 5
- 97.6
Gemma 4 26B A4B
- 97.2 GPT-5.6 Sol
- 97.0 Claude Sonnet 5
- 96.7
Gemini 2.5 Flash
- 96.5 GLM-5
- 96.3
Qwen3-Coder-480B-A35B
- 95.5 Claude Haiku 4.5
- 95.0
Gemini 3.5 Flash-Lite
- 94.8
DeepSeek-R1
- 94.4 GPT-5.6 Terra
- 91.4
Gemini 3.1 Flash-Lite
- 91.1 GPT-5.4
- 90.7 Qwen 3 235B A22B Instruct 2506
- 90.3 GPT-5.5
- 89.6 Claude Opus 4.6
- 87.0
Qwen3-Next-80B-A3B
- 85.1 Grok 4.20
- 82.1 GPT-5.4 Mini
- 81.8 GPT-5.4 Nano
- 81.6 Qwen 3 Next 80B Instruct
- 74.0 gpt-oss-20b
- 64.0 gpt-oss-120b
- 1 GPT-6 Astra 99.7%
- 2
Gemini 2.5 Pro Jun 2025 99.3%
- 3 Claude Sonnet 4.6 99.3%
- 4
Gemma 4 31B IT 99.3%
- 5
Gemini 3.7 Flash 99.3%
- 6
Gemini 3.8 Flash 99.3%
- 7 Claude Opus 4.7 99%
- 8
Gemini 3.5 Flash 99%
- 9
Gemini 3 Flash 98.6%
- 10
Gemini 3.1 Pro 98.6%
- 11
Gemini 3.6 Flash 98.6%
- 12 Claude Opus 4.5 98.3%
- 13 GPT-5.6 Luna 98%
- 14 Claude Opus 4.8 97.7%
- 15 Claude Opus 5 97.7%
- 16
Gemma 4 26B A4B 97.6%
- 17 GPT-5.6 Sol 97.2%
- 18 Claude Sonnet 5 97%
- 19
Gemini 2.5 Flash Sep 2025 96.7%
- 20 GLM-5 96.5%
- 21
Qwen3-Coder-480B-A35B 96.3%
- 22 Claude Haiku 4.5 95.5%
- 23
Gemini 3.5 Flash-Lite 95%
- 24
DeepSeek-R1 May 2025 94.8%
- 25 GPT-5.6 Terra 94.4%
- 26
Gemini 3.1 Flash-Lite 91.4%
- 27 GPT-5.4 91.1%
- 28 Qwen 3 235B A22B Instruct 2506 90.7%
- 29 GPT-5.5 90.3%
- 30 Claude Opus 4.6 89.6%
- 31
Qwen3-Next-80B-A3B 87%
- 32 Grok 4.20 reasoning 85.1%
- 33 GPT-5.4 Mini 82.1%
- 34 GPT-5.4 Nano 81.8%
- 35 Qwen 3 Next 80B Instruct 81.6%
- 36 gpt-oss-20b 74%
- 37 gpt-oss-120b 64%
Source: Official Memory Discipline leaderboard
- 99.7 GPT-6 Astra
- 99.3
Gemini 2.5 Pro
- 99.3 Claude Sonnet 4.6
- 99.3
Gemma 4 31B IT
- 99.3
Gemini 3.7 Flash
- 99.3
Gemini 3.8 Flash
- 99.0 Claude Opus 4.7
- 99.0
Gemini 3.5 Flash
- 98.6
Gemini 3 Flash
- 98.6
Gemini 3.1 Pro
- 98.6
Gemini 3.6 Flash
- 98.3 Claude Opus 4.5
- 98.0 GPT-5.6 Luna
- 97.7 Claude Opus 4.8
- 97.7 Claude Opus 5
- 97.6
Gemma 4 26B A4B
- 97.2 GPT-5.6 Sol
- 97.0 Claude Sonnet 5
- 96.7
Gemini 2.5 Flash
- 96.5 GLM-5
- 96.3
Qwen3-Coder-480B-A35B
- 95.5 Claude Haiku 4.5
- 95.0
Gemini 3.5 Flash-Lite
- 94.8
DeepSeek-R1
- 94.4 GPT-5.6 Terra
- 91.4
Gemini 3.1 Flash-Lite
- 91.1 GPT-5.4
- 90.3 GPT-5.5
- 89.6 Claude Opus 4.6
- 87.0
Qwen3-Next-80B-A3B
- 85.1 Grok 4.20
- 82.1 GPT-5.4 Mini
- 81.8 GPT-5.4 Nano
- 74.0 gpt-oss-20b
- 64.0 gpt-oss-120b
- 1 GPT-6 Astra 99.7%
- 2
Gemini 2.5 Pro Jun 2025 99.3%
- 3 Claude Sonnet 4.6 99.3%
- 4
Gemma 4 31B IT 99.3%
- 5
Gemini 3.7 Flash 99.3%
- 6
Gemini 3.8 Flash 99.3%
- 7 Claude Opus 4.7 99%
- 8
Gemini 3.5 Flash 99%
- 9
Gemini 3 Flash 98.6%
- 10
Gemini 3.1 Pro 98.6%
- 11
Gemini 3.6 Flash 98.6%
- 12 Claude Opus 4.5 98.3%
- 13 GPT-5.6 Luna 98%
- 14 Claude Opus 4.8 97.7%
- 15 Claude Opus 5 97.7%
- 16
Gemma 4 26B A4B 97.6%
- 17 GPT-5.6 Sol 97.2%
- 18 Claude Sonnet 5 97%
- 19
Gemini 2.5 Flash Sep 2025 96.7%
- 20 GLM-5 96.5%
- 21
Qwen3-Coder-480B-A35B 96.3%
- 22 Claude Haiku 4.5 95.5%
- 23
Gemini 3.5 Flash-Lite 95%
- 24
DeepSeek-R1 May 2025 94.8%
- 25 GPT-5.6 Terra 94.4%
- 26
Gemini 3.1 Flash-Lite 91.4%
- 27 GPT-5.4 91.1%
- 28 GPT-5.5 90.3%
- 29 Claude Opus 4.6 89.6%
- 30
Qwen3-Next-80B-A3B 87%
- 31 Grok 4.20 reasoning 85.1%
- 32 GPT-5.4 Mini 82.1%
- 33 GPT-5.4 Nano 81.8%
- 34 gpt-oss-20b 74%
- 35 gpt-oss-120b 64%
Source: Official Memory Discipline leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 99.7% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 2 | | 99.3% | Jun 2025 | Oct 2026 | Official leaderboard | |
| 3 | Claude Sonnet 4.6 | 99.3% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 4 | | 99.3% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 5 | | 99.3% | Aug 2026 | Oct 2026 | Official leaderboard | |
| 6 | | 99.3% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 7 | Claude Opus 4.7 | 99% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 8 | | 99% | May 2026 | Oct 2026 | Official leaderboard | |
| 9 | | 98.6% | Dec 2025 | Oct 2026 | Official leaderboard | |
| 10 | | 98.6% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 11 | | 98.6% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 12 | Claude Opus 4.5 | 98.3% | Nov 2025 | Oct 2026 | Official leaderboard | |
| 13 | GPT-5.6 Luna | 98% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 14 | Claude Opus 4.8 | 97.7% | May 2026 | Oct 2026 | Official leaderboard | |
| 15 | Claude Opus 5 | 97.7% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 16 | | 97.6% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 17 | GPT-5.6 Sol | 97.2% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 18 | Claude Sonnet 5 | 97% | Jun 2026 | Oct 2026 | Official leaderboard | |
| 19 | | 96.7% | Sep 2025 | Oct 2026 | Official leaderboard | |
| 20 | GLM-5 | 96.5% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 21 | | 96.3% | Jul 2025 | Oct 2026 | Official leaderboard | |
| 22 | Claude Haiku 4.5 | 95.5% | Oct 2025 | Oct 2026 | Official leaderboard | |
| 23 | | 95% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 24 | | 94.8% | May 2025 | Oct 2026 | Official leaderboard | |
| 25 | GPT-5.6 Terra | 94.4% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 26 | | 91.4% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 27 | GPT-5.4 | 91.1% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 28 | Qwen 3 235B A22B Instruct 2506 | 90.7% | Oct 2026 | Official leaderboard | ||
| 29 | GPT-5.5 | 90.3% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 30 | Claude Opus 4.6 | 89.6% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 31 | | 87% | Sep 2025 | Oct 2026 | Official leaderboard | |
| 32 | Grok 4.20 | 85.1% | reasoning | Feb 2026 | Oct 2026 | Official leaderboard |
| 33 | GPT-5.4 Mini | 82.1% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 34 | GPT-5.4 Nano | 81.8% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 35 | Qwen 3 Next 80B Instruct | 81.6% | Oct 2026 | Official leaderboard | ||
| 36 | gpt-oss-20b | 74% | Aug 2025 | Oct 2026 | Official leaderboard | |
| 37 | gpt-oss-120b | 64% | Aug 2025 | Oct 2026 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 99.7% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 2 | | 99.3% | Jun 2025 | Oct 2026 | Official leaderboard | |
| 3 | Claude Sonnet 4.6 | 99.3% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 4 | | 99.3% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 5 | | 99.3% | Aug 2026 | Oct 2026 | Official leaderboard | |
| 6 | | 99.3% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 7 | Claude Opus 4.7 | 99% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 8 | | 99% | May 2026 | Oct 2026 | Official leaderboard | |
| 9 | | 98.6% | Dec 2025 | Oct 2026 | Official leaderboard | |
| 10 | | 98.6% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 11 | | 98.6% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 12 | Claude Opus 4.5 | 98.3% | Nov 2025 | Oct 2026 | Official leaderboard | |
| 13 | GPT-5.6 Luna | 98% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 14 | Claude Opus 4.8 | 97.7% | May 2026 | Oct 2026 | Official leaderboard | |
| 15 | Claude Opus 5 | 97.7% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 16 | | 97.6% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 17 | GPT-5.6 Sol | 97.2% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 18 | Claude Sonnet 5 | 97% | Jun 2026 | Oct 2026 | Official leaderboard | |
| 19 | | 96.7% | Sep 2025 | Oct 2026 | Official leaderboard | |
| 20 | GLM-5 | 96.5% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 21 | | 96.3% | Jul 2025 | Oct 2026 | Official leaderboard | |
| 22 | Claude Haiku 4.5 | 95.5% | Oct 2025 | Oct 2026 | Official leaderboard | |
| 23 | | 95% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 24 | | 94.8% | May 2025 | Oct 2026 | Official leaderboard | |
| 25 | GPT-5.6 Terra | 94.4% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 26 | | 91.4% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 27 | GPT-5.4 | 91.1% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 28 | GPT-5.5 | 90.3% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 29 | Claude Opus 4.6 | 89.6% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 30 | | 87% | Sep 2025 | Oct 2026 | Official leaderboard | |
| 31 | Grok 4.20 | 85.1% | reasoning | Feb 2026 | Oct 2026 | Official leaderboard |
| 32 | GPT-5.4 Mini | 82.1% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 33 | GPT-5.4 Nano | 81.8% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 34 | gpt-oss-20b | 74% | Aug 2025 | Oct 2026 | Official leaderboard | |
| 35 | gpt-oss-120b | 64% | Aug 2025 | Oct 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Memory Discipline leaderboard
DeepSeek-R1 on the official leaderboard passed 85% in May 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Memory Discipline leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Long context
- MRCR v2 In use Multi-round coreference: retrieve the n-th of several similar requests hidden in a long synthetic conversation, up to 1M tokens.
Muse Spark 1.3 98.5%
- LongBench v2 In use 503 multiple-choice questions over 8K-2M-word contexts (QA, dialogue, code repos, structured data). Accuracy.
Inkling 2 Small 70.6%
- GraphWalks In use A graph is given as an edge list in long context. The model answers BFS or parent queries, scored by F1. Claude Fable 5 99.96%
- OpenAI MRCR v2 In use Models read a long synthetic chat that hides 2, 4 or 8 identical writing requests and must reproduce the response to the i-th one. Scored by mean string match ratio per context bin.
Gemini 3.7 Flash 89%
- CL-bench In use Model must learn new knowledge from a supplied long context (rules, procedures, data) and solve tasks. Strict LLM-verified rubrics. GPT-5.4 27.9%
- AA-LCR 1.1 In use Models answer 100 questions that need reasoning across sets of real documents of about 100K tokens. An LLM equality checker with a fixed system prompt compares each answer with the key.
Step 5 Preview 88.3%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (37 entries).
- Pass Models scored 35 models we track, plus 2 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for GPT-6 Astra.
- Note Frontier models 1 of the top 10 has a score, which is fine for a retired test. The strongest tested is GPT-6 Astra (#4).
- Note Headroom Saturated. The best is 99.7%, past 85% since May 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on kaggle.com: 36 rows for models we track and 2 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.