Voice Standard v0.1.3 (gpt-5.6-sol; 900s) - Summarization: leaderboard
Published summarization task_quality (1-100), canonical v0.1.3, 900s audio-length bucket; reference-free gpt-5.6-sol 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, 900s audio-length bucket; reference-free gpt-5.6-sol 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. 52 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 100 | #5 |
| 2 | GPT-5.6 Terra | 98 | #42 |
| 3 | GPT-6 Luna | 98 | #52 |
| 4 | Claude Opus 5.5 | 97 | #3 |
| 5 | GPT-6 Luna (High) | 97 | #52 (GPT-6 Luna) |
| 6 | GPT-6 Luna (Non-reasoning) | 97 | #52 (GPT-6 Luna) |
| 7 | GPT-5.5 | 96 | #32 |
| 8 | GPT-5.2 | 94 | #109 |
| 9 | GPT-5 Mini | 94 | #184 |
| 10 | Kimi K3 | 94 | #30 |
| 11 | Gemini 4 Argon | 94 | #7 |
| 12 | Claude Opus 4.7 | 93 | #49 |
| 13 | Claude Opus 4.8 | 93 | #38 |
| 14 | GPT-5.1 | 93 | #133 |
| 15 | Claude Opus 5 | 93 | #12 |
No result here: #8 GPT-6.1 Sol, #9 Claude Fable 5.1, #10 Claude Sonnet 5.5.
Interactive version: theaggregate.ai/benchmark?slug=voice-standard-v0-1-3-gpt-5-6-sol-900s-summarization · How It Works · Data refreshed daily, snapshot 2026-10-16.