Ripple 65B Preview Release - Instruct - τ³-bench banking: leaderboard
Ricursive Ripple-65B Preview native instruct comparison, immutable card revision e27e171792f303d74c048184e8259ba663cfa0d5. Full BF16 precision and maximum effort are applied only to Ricursive in-house evaluations and its own instruct column; imported official-card cells retain unreported precision/effort and distinct source-qualified identities. Native percentages, higher is better. Ripple-65B Preview:in-house/OpenCode; Nemotron 3 Ultra 550B:official-card; Inkling 975B:official-card; Muse Spark Open 816B:in-house/OpenCode; Reflection Beam 501B:official-card. Terminal-Bench self-reported and Terminus2 comparisons are separate; native table80.5 is retained, not replaced by prose80.52. No throughput/cost/model-size row is a benchmark. This source family alone does not establish independent main-rank eligibility.
Metric: Native τ³-bench banking (%). Source: huggingface.co. Saturation forecast: Rough model projection: around 2026. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Reflection Beam 501B (Ripple Release Run: phase=Instruct;origin=official-card;precision=unreported;effort=unreported) | 36.1 | |
| 2 | Ripple-65B Preview (Ripple Release Run: phase=Instruct;origin=in-house;precision=BF16;effort=maximum;harness=OpenCode) | 31.27 | |
| 3 | Inkling 975B (Ripple Release Run: phase=Instruct;origin=official-card;precision=unreported;effort=unreported) | 23.7 | |
| 4 | Nemotron 3 Ultra 550B (Ripple Release Run: phase=Instruct;origin=official-card;precision=unreported;effort=unreported) | 22.6 | |
| 5 | Muse Spark Open 816B (Ripple Release Run: phase=Instruct;origin=in-house;precision=BF16;effort=maximum;harness=OpenCode) | 14.4 |
Interactive version: theaggregate.ai/benchmark?slug=ripple-65b-preview-release-instruct-tau3-bench-banking · How It Works · Data refreshed daily, snapshot 2026-11-06.