Benchmark Almanac

Agri STT Benchmarking Dataset

Gemini 2.5 Pro (snapshot unspecified) 31.4% tops its leaderboard
Not in model cards

Models transcribe farmers’ spoken questions in Hindi, Telugu and Odia. Researchers score errors against human transcripts and separately measure errors on agricultural terms.

Digital Green evaluated ten systems on 10,934 recordings. It first released 10,864 recordings and later removed 56, leaving 10,808 in the public dataset.

Made by
Digital Green
Released
January 2026
Kind
Speech recognition and translation
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
Hindi, Telugu, Odia
In and out
Audio → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Occupations
Farming, fishing and forestry
In views
Audio and speech
5
Entries in its paper, 0 models we track

Gemini 2.5 Pro (snapshot unspecified) tops the leaderboard with 31.4%

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 word error rate, so this is the plain mean for Hindi, Telugu and Odia. 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 Gemini 2.5 Pro (snapshot unspecified) Best speaker 31.4%
  2. 2 Azure Diarize Best speaker 34.2%
  3. 3 Sarvam AI Full transcript 37%
  4. 4 Google STT Full transcript 40%
  5. 5 MMS (Meta) Full transcript 60.1%

Source: The Agri STT Benchmarking Dataset paper

#EntryScoreSettingDateSource
1 Gemini 2.5 Pro (snapshot unspecified) 31.4% Best speaker Official leaderboard
2 Azure Diarize 34.2% Best speaker Official leaderboard
3 Sarvam AI 37% Full transcript Official leaderboard
4 Google STT 40% Full transcript Official leaderboard
5 MMS (Meta) 60.1% Full transcript 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 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the benchmark’s paper (5 entries).
  • Pass Models scored 5 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 5 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