Contextual Earnings-22
Models transcribe clips from earnings calls with a custom vocabulary. The benchmark measures keyword recognition and transcription errors.
- Made by
- Argmax
- Released
- March 2026
- Kind
- Speech recognition and translation
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- Earnings-22
- In views
- Audio and speech
- Last model added
- January 2026
- Scores refreshed
- November 20th, 2026
ElevenLabs tops the leaderboard with 9.08% Qwen3-ASR-1.7B leads with 9.19%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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 Qwen3-ASR-1.7B, at 9.19%. This view shows only models we track, each at its best.
- 1 ElevenLabs file-keywords 9.08%
- 2
Qwen3-ASR-1.7B chunk-keywords 9.19%
- 3 AssemblyAI chunk-keywords 11.7%
- 4 Argmax (parakeet-v2) chunk-keywords 12.5%
- 5 Deepgram (nova-3) chunk-keywords 13.3%
- 6 Argmax (parakeet-v3) chunk-keywords 14.6%
- 7 Whisper large-v3-turbo file-keywords 14.7%
- 8 Apple (SpeechAnalyzer) no keywords 17%
- 9 OpenAI (whisper-1) no keywords 20.7%
- 10 Apple (SFSpeechRecognizer) chunk-keywords 27%
Source: Official Contextual Earnings-22 leaderboard
- 1
Qwen3-ASR-1.7B chunk-keywords 9.19%
- 2 Whisper large-v3-turbo file-keywords 14.7%
Source: Official Contextual Earnings-22 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | ElevenLabs | 9.08% | file-keywords | Official leaderboard | |
| 2 | | 9.19% | chunk-keywords | Jan 2026 | Official leaderboard |
| 3 | AssemblyAI | 11.7% | chunk-keywords | Official leaderboard | |
| 4 | Argmax (parakeet-v2) | 12.5% | chunk-keywords | Official leaderboard | |
| 5 | Deepgram (nova-3) | 13.3% | chunk-keywords | Official leaderboard | |
| 6 | Argmax (parakeet-v3) | 14.6% | chunk-keywords | Official leaderboard | |
| 7 | Whisper large-v3-turbo | 14.7% | file-keywords | Oct 2024 | Official leaderboard |
| 8 | Apple (SpeechAnalyzer) | 17% | no keywords | Official leaderboard | |
| 9 | OpenAI (whisper-1) | 20.7% | no keywords | Official leaderboard | |
| 10 | Apple (SFSpeechRecognizer) | 27% | chunk-keywords | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 9.19% | chunk-keywords | Jan 2026 | Official leaderboard |
| 2 | Whisper large-v3-turbo | 14.7% | file-keywords | Oct 2024 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Contextual Earnings-22 leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Contextual Earnings-22 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
- 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 10 months ago, in January 2026, for Qwen3-ASR-1.7B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (10 entries).
- Pass Models scored 2 models we track, plus 8 other entries on its leaderboard.
- Warning Newest score The newest came 10 months ago, in January 2026, for Qwen3-ASR-1.7B.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Lower is better, so there’s no ceiling to reach.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 6 rows for models we track and 8 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.