Benchmark Almanac

GeoSound

PSM 0.90 tops its leaderboard
Not in model cards

Models match environmental recordings to satellite images of their locations and retrieve recordings from images. The test holds out geographic areas and contains 9,931 examples.

The Sat2Sound follow-up evaluated ImageBind on Sentinel imagery. The correct recording ranked in the top tenth for 21.4% of image queries.

Released
August 2024
Kind
Audio understanding and voice
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
In and out
Audio, Images → Images, Audio
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
2
Entries in its paper, 0 models we track

PSM tops the leaderboard with 0.90

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The headline is image-to-audio recall at the top 10% of candidates for the specified imagery and evaluation setting. 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 PSM Bing, PCME++, zoom 1, training metadata on, test text on, test metadata on 0.90
  2. 2 GeoCLAP Bing, infoNCE, zoom 5, training metadata off, test text on, test metadata off 0.58

Source: The GeoSound paper

#EntryScoreSettingDateSource
1 PSM 0.90 Bing, PCME++, zoom 1, training metadata on, test text on, test metadata on Official leaderboard
2 GeoCLAP 0.58 Bing, infoNCE, zoom 5, training metadata off, test text on, test metadata off 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

All 7 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
  • Pass Independent runs Scores from the benchmark’s paper (2 entries).
  • Note Models scored 2 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 2 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