LLM Stats (FLEURS): leaderboard
Few-shot Learning Evaluation of Universal Representations of Speech: multilingual speech understanding benchmark spanning 102 languages.
Metric: Score (%). Source: llm-stats.com. Saturation forecast: Estimated already saturated. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen2.5-Omni-7B | 95.9 | #624 |
| 2 | Gemini 1.0 Pro | 93.6 | #933 |
| 3 | Gemini 1.5 Pro | 93.3 | #445 |
| 4 | Gemma 4 12B | 93.1 | #535 |
| 5 | Gemini 1.5 Flash | 90.4 | #618 |
| 6 | Gemini 1.5 Flash-8B | 86.4 | #819 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm-stats-fleurs · How It Works · Data refreshed daily, snapshot 2026-10-20.