Benchmark Almanac

COREBench (Conversational Reasoning)

Gemini 2.5 Pro May 2025 81.3% leads since June 2025
Not in model cards

Models listen to a conversation with several speakers and answer a question that can require information from multiple turns.

The HELM code references an earlier dataset path. The AHELM paper links the public CoReBench v1 dataset.

Released
June 2025
Kind
Audio understanding and voice
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Audio, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Audio and speech
Strongest model tested
Gemini 2.5 Flash May 2025 #114 on the capability index
Last model added
May 2025
Scores refreshed
November 20th, 2026
17
Entries on AHELM’s leaderboard, 11 models we track

Gemini 2.5 Pro leads with 81.3% among models released by May 2025 Gemini 2.5 Pro leads with 81.3% among models released by May 2025

Best score per entry from AHELM’s leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. Agents built around a model, such as gpt-4o-transcribe transcription (GPT-4o + gpt-4o-transcribe), are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.

The newest model with a score here came out in May 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemini 2.5 Pro May 2025 81.3%
  2. 2 Gemini 1.5 Pro Sep 2024 79.9%
  3. 3 Gemini 1.5 Flash Sep 2024 77.6%
  4. 4 Gemini 2.0 Flash Feb 2025 75.6%
  5. 5 Gemini 2.0 Flash Dec 2024 75.4%
  6. 6 Gemini 2.0 Flash-Lite 73.7%
  7. 7 Gemini 1.5 Flash May 2024 72.2%
  8. 8 Gemini 1.5 Pro May 2024 65.9%
  9. 9 Gemini 2.5 Flash May 2025 64.4%
  10. 10 Qwen2.5-Omni-7B 56%
  11. 11 gpt-4o-mini-audio-preview-2024-12-17 51.4%
  12. 12 gpt-4o-transcribe transcription (GPT-4o + gpt-4o-transcribe) Nov 2024 38.8%
  13. 13 whisper-1 transcription (GPT-4o + whisper-1) Nov 2024 37.7%
  14. 14 gpt-4o-mini-transcribe transcription (GPT-4o + gpt-4o-mini-transcribe) Nov 2024 37.3%
  15. 15 gpt-4o-audio-preview-2024-12-17 35.9%
  16. 16 gpt-4o-audio-preview-2024-10-01 34.2%
  17. 17 Qwen2-Audio-7B-Instruct 23.3%

Source: AHELM’s leaderboard

#EntryScoreSettingReleasedRun onSource
1 Gemini 2.5 Pro May 2025 81.3% May 2025 Official leaderboard
2 Gemini 1.5 Pro Sep 2024 79.9% Sep 2024 Official leaderboard
3 Gemini 1.5 Flash Sep 2024 77.6% Aug 2024 Official leaderboard
4 Gemini 2.0 Flash Feb 2025 75.6% Feb 2025 Official leaderboard
5 Gemini 2.0 Flash Dec 2024 75.4% Dec 2024 Official leaderboard
6 Gemini 2.0 Flash-Lite 73.7% Feb 2025 Official leaderboard
7 Gemini 1.5 Flash May 2024 72.2% May 2024 Official leaderboard
8 Gemini 1.5 Pro May 2024 65.9% May 2024 Official leaderboard
9 Gemini 2.5 Flash May 2025 64.4% May 2025 Official leaderboard
10 Qwen2.5-Omni-7B 56% Mar 2025 Official leaderboard
11 gpt-4o-mini-audio-preview-2024-12-17 51.4% Dec 2024 Official leaderboard
12 gpt-4o-transcribe transcription (GPT-4o + gpt-4o-transcribe) Nov 2024 38.8% Nov 2024 Nov 2024 Official leaderboard
13 whisper-1 transcription (GPT-4o + whisper-1) Nov 2024 37.7% Nov 2024 Nov 2024 Official leaderboard
14 gpt-4o-mini-transcribe transcription (GPT-4o + gpt-4o-mini-transcribe) Nov 2024 37.3% Nov 2024 Nov 2024 Official leaderboard
15 gpt-4o-audio-preview-2024-12-17 35.9% Dec 2024 Official leaderboard
16 gpt-4o-audio-preview-2024-10-01 34.2% Oct 2024 Official leaderboard
17 Qwen2-Audio-7B-Instruct 23.3% Aug 2024 Official leaderboard
#ModelScoreSettingReleasedRun onSource
1 Gemini 2.5 Pro May 2025 81.3% May 2025 Official leaderboard
2 Gemini 1.5 Pro Sep 2024 79.9% Sep 2024 Official leaderboard
3 Gemini 1.5 Flash Sep 2024 77.6% Aug 2024 Official leaderboard
4 Gemini 2.0 Flash Feb 2025 75.6% Feb 2025 Official leaderboard
5 Gemini 2.0 Flash Dec 2024 75.4% Dec 2024 Official leaderboard
6 Gemini 2.0 Flash-Lite 73.7% Feb 2025 Official leaderboard
7 Gemini 1.5 Flash May 2024 72.2% May 2024 Official leaderboard
8 Gemini 1.5 Pro May 2024 65.9% May 2024 Official leaderboard
9 Gemini 2.5 Flash May 2025 64.4% May 2025 Official leaderboard
10 Qwen2.5-Omni-7B 56% Mar 2025 Official leaderboard
11 Qwen2-Audio-7B-Instruct 23.3% Aug 2024 Official leaderboard

Number one over time

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

Google DeepMind
AHELM leaderboard Not tested since Jun 2025

Source: AHELM’s leaderboard

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
On AHELM’s leaderboard Best so far
0% 20% 40% 60% 80% 100% 2024 2025 Near the ceiling (85%) Gemini 2.5 Pro Gemini 1.5 Pro Gemini 1.5 Flash 0% 20% 40% 60% 80% 100% 2024 2025 Near the ceiling (85%) Gemini 2.5 Pro Gemini 1.5 Flash

Source: AHELM’s 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 18 months ago, in May 2025, for Gemini 2.5 Flash. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (17 entries).
  • Pass Models scored 11 models we track, plus 6 other entries on its leaderboard.
  • Warning Newest score The newest came 18 months ago, in May 2025, for Gemini 2.5 Flash.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 2.5 Flash (#114).
  • Pass Headroom The best is 81.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on AHELM: 14 rows for models we track and 3 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