Voice Standard v0.1.3 (claude-opus-5-5; 30s) - Summarization: leaderboard
Published summarization task_quality (1-100), canonical v0.1.3, 30s audio-length bucket; reference-free claude-opus-5-5 rubric, source transcript as context; normalized 1-5 rubric components; higher is better. Latency, cost and mixed-judge composites are not scored here.
Metric: Published summarization task_quality (1-100), canonical v0.1.3, 30s audio-length bucket; reference-free claude-opus-5-5 rubric, source transcript as context; normalized 1-5 rubric components; higher is better. Latency, cost and mixed-judge composites are not scored here.. Source: raw.githubusercontent.com. Saturation forecast: Estimated already saturated. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Kimi K3 | 99 | #30 |
| 2 | GPT-5.6 Terra | 99 | #42 |
| 3 | GPT-6 Astra | 98 | #5 |
| 4 | Gemini 3.8 Flash | 98 | #21 |
| 5 | GPT-6 Sol | 98 | #14 |
| 6 | GPT-6.1 Sol | 98 | #8 |
| 7 | GPT-5.5 | 97 | #32 |
| 8 | Gemini 3.6 Flash | 97 | #50 |
| 9 | Gemini 4 Argon | 97 | #7 |
| 10 | GPT-6 Luna (Non-reasoning) | 97 | #52 (GPT-6 Luna) |
| 11 | GPT-5.6 Luna | 96 | #69 |
| 12 | GPT-6 Luna | 96 | #52 |
| 13 | GPT-6 Luna (High) | 96 | #52 (GPT-6 Luna) |
| 14 | GPT-5 | 95 | #94 |
| 15 | Gemma 4 31B | 95 | #195 |
No result here: #3 Claude Opus 5.5, #9 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=voice-standard-v0-1-3-claude-opus-5-5-30s-summarization · How It Works · Data refreshed daily, snapshot 2026-10-16.