Voice Standard v0.1.3 (claude-opus-5-5; 120s) - Information Extraction: leaderboard
Published information_extraction task_quality (1-100), canonical v0.1.3, 120s 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 information_extraction task_quality (1-100), canonical v0.1.3, 120s 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: Around January 2027. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Luna (High) | 93 | #52 (GPT-6 Luna) |
| 2 | Gemini 4 Argon | 91 | #7 |
| 3 | GPT-5.6 Sol | 90 | #18 |
| 4 | Gemini 3.5 Flash | 90 | #57 |
| 5 | GPT-6 Sol | 90 | #14 |
| 6 | GPT-5.5 | 89 | #32 |
| 7 | GPT-6 Astra | 89 | #5 |
| 8 | Claude Sonnet 5.5 | 89 | #10 |
| 9 | Grok 4.7 | 89 | #27 |
| 10 | Claude Opus 5 | 88 | #12 |
| 11 | Claude Sonnet 5 | 88 | #55 |
| 12 | Gemini 3.7 Flash | 88 | #24 |
| 13 | GLM-5.3 | 88 | #40 |
| 14 | GPT-6 Luna | 88 | #52 |
| 15 | GPT-5 | 86 | #94 |
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-5-5-120s-information-extraction · How It Works · Data refreshed daily, snapshot 2026-10-16.