Benchmark Almanac

GSR-Bench

TeleASR 4.54 tops its leaderboard Gemini 3.1 Pro 4.21 leads the models we track
Not in model cards

Models turn speech into transcripts, meeting notes, or other requested text. Judges check whether the output preserves the meaning and stays grounded in the recording.

Released
October 2026
Kind
Speech recognition and translation
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Measures
Capability
In and out
Audio, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
In views
Audio and speech
Strongest model tested
Gemini 3.1 Pro #40 on the capability index
Last model added
February 2026
Scores refreshed
November 20th, 2026
10
Entries in its paper, 3 models we track

TeleASR tops the leaderboard with 4.54 Gemini 3.1 Pro leads with 4.21 among models released by February 2026

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 the GSR-Refine LLM-Score in Table 1, on a scale from 1 to 5. 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. The best model we track is Gemini 3.1 Pro, at 4.21. This view shows only models we track, each at its best.

The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 TeleASR 4.54
  2. 2 UniGSR-Post 4.52
  3. 3 Gemini 3.1 Pro 4.21
  4. 4 UniGSR-ASR 4.20
  5. 5 FireRed-LLM 4.16
  6. 6 FireRed-AED 4.13
  7. 7 Qwen3-ASR-0.6B 4.09
  8. 8 Qwen3-ASR-1.7B 4.06
  9. 9 FunASR-Nano 4.04
  10. 10 StepAudio-R1 3.96

Source: The GSR-Bench paper

#EntryScoreSettingDateSource
1 TeleASR 4.54 ASR + LLM cascade Official leaderboard
2 UniGSR-Post 4.52 Official leaderboard
3 Gemini 3.1 Pro 4.21 Feb 2026 Official leaderboard
4 UniGSR-ASR 4.20 Official leaderboard
5 FireRed-LLM 4.16 Official leaderboard
6 FireRed-AED 4.13 Official leaderboard
7 Qwen3-ASR-0.6B 4.09 Jan 2026 Official leaderboard
8 Qwen3-ASR-1.7B 4.06 Jan 2026 Official leaderboard
9 FunASR-Nano 4.04 Official leaderboard
10 StepAudio-R1 3.96 Official leaderboard
#ModelScoreSettingDateSource
1 Gemini 3.1 Pro 4.21 Feb 2026 Official leaderboard
2 Qwen3-ASR-0.6B 4.09 Jan 2026 Official leaderboard
3 Qwen3-ASR-1.7B 4.06 Jan 2026 Official leaderboard

Rankings by part

We read 9 parts from the benchmark’s paper, each ranking models on one part of the test, such as GPT-4o Fidelity, GPT-4o Fluency and GPT-4o Readability. Qwen3-ASR-1.7B leads 5 of them, and Gemini 3.1 Pro leads the other 4. Arrows show how far a model moved from its overall rank among the models we track.

GPT-4o Fidelity

3 models we track have a score here.

  1. 1 Qwen3-ASR-1.7B ↑2 4.74
  2. 2 Qwen3-ASR-0.6B 4.60
  3. 3 Gemini 3.1 Pro ↓2 4.14

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind
Benchmark paper Not tested since Oct 2026

Source: The GSR-Bench paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper
4.05 4.10 4.15 4.20 4.25 2026 4.05 4.10 4.15 4.20 4.25 2026

Source: Official GSR-Bench 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 9 checks pass, 2 warnings. 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 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (10 entries).
  • Pass Models scored 3 models we track, plus 7 other entries on its leaderboard.
  • Warning Newest score The newest came 9 months ago, in February 2026, for Gemini 3.1 Pro.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3.1 Pro (#40).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 3 rows for models we track and 7 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.

How we check