VoiceLongMemEval - Indirect 140Q - Descriptive: leaderboard
VoiceLongMemEval tests retrieval of past conversational facts that depend on vocal affect. These text-input experiments compare transcripts alone with descriptions of paralinguistic metadata, averaged over three seeds with five distractor sessions; they do not test raw speech perception. This series reports VoiceLongMemEval - Indirect 140Q - Descriptive from 2609.00570v1, S5.T6: Accuracy (%). Higher is better.
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around 2031. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 30.5 | #57 |
| 2 | GPT-5.5 | 28.5 | #48 |
| 3 | Claude Sonnet 4.6 | 25.9 | #159 |
| 4 | Qwen3-Next-80B | 24.5 | #656 |
| 5 | Llama 4 Maverick | 20.7 | #1166 |
| 6 | Gemma 3 12B | 17.6 | #2086 |
| 7 | Llama 3.3 70B | 15.2 | #1590 |
| 8 | Qwen 3.5 122B A10B | 14.8 | #335 |
No result here: #4 Claude Opus 5.5, #5 GPT-6 Astra, #9 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=voicelongmemeval-indirect-140q-descriptive · How It Works · Data refreshed daily, snapshot 2026-11-08.