Benchmark Almanac

AMemOps

GDN 80.3% tops its leaderboard
Not in model cards

Models track instruments and their changing attributes in long audio streams. Questions test whether they recall the latest value and recognize absent sources.

Released
October 2026
Kind
Audio understanding and voice
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Measures
Capability
Language
English
In and out
Audio, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Audio and speech
9
Entries in its paper, 0 models we track

GDN tops the leaderboard with 80.3%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score. The headline is the plain mean of all-query accuracy for environmental sounds and instruments. 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.

  1. 1 GDN 24k training steps 80.3%
  2. 2 GDN2 24k training steps 79.8%
  3. 3 matched, no RoPE 24k training steps 79.5%
  4. 4 matched + RoPE 24k training steps 79.5%
  5. 5 KDA 24k training steps 79%
  6. 6 no-erase 24k training steps 75.6%
  7. 7 Mamba-2-style 24k training steps 71.8%
  8. 8 standard + RoPE 24k training steps 68.3%
  9. 9 standard, no RoPE 24k training steps 64.5%

Source: The AMemOps paper

#EntryScoreSettingDateSource
1 GDN 80.3% 24k training steps Official leaderboard
2 GDN2 79.8% 24k training steps Official leaderboard
3 matched, no RoPE 79.5% 24k training steps Official leaderboard
4 matched + RoPE 79.5% 24k training steps Official leaderboard
5 KDA 79% 24k training steps Official leaderboard
6 no-erase 75.6% 24k training steps Official leaderboard
7 Mamba-2-style 71.8% 24k training steps Official leaderboard
8 standard + RoPE 68.3% 24k training steps Official leaderboard
9 standard, no RoPE 64.5% 24k training steps Official 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 Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

7 of 8 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 9 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 9 entries at the last read, none a model we track.
  • 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.

How we check