PulseAugur
EN
LIVE 07:01:21

Ricursive's Ripple-65B Preview benchmarked on agentic coding tasks

By PulseAugur Editorial · [1 sources] ·

Ricursive's Ripple-65B Preview model was benchmarked on agentic coding tasks, achieving a score of 0.028 on the Gauntlet sb-7.2 benchmark and scores of 0.0858 and 0.0770 on Forge 2.0. These results are compared against DeepSeek V4.1 Flash 1017, which scored 0.6957 on Gauntlet in October, and Liquid AI's LFM3-1.7B, which scored 0.0055 on Gauntlet. The report notes that Ripple-65B's performance was impacted by a backend issue that caused HTTP requests to fail, leading to tests being moved in-process. The model also demonstrated specific performance characteristics on a Mac with an M3 Ultra chip, running at 13.5 tokens per second. AI

IMPACT Provides benchmark data for agentic coding capabilities, informing developers on model performance for complex tasks.

RANK_REASON The item details benchmark results for a specific model (Ripple-65B Preview) on agentic coding tasks, comparing it to other models and providing technical performance data. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Ricursive's Ripple-65B Preview benchmarked on agentic coding tasks

How we ranked this

Signal score
49 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item details benchmark results for a specific model (Ripple-65B Preview) on agentic coding tasks, comparing it to other models and providing technical performance data. [lever_c_demoted from re…
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Mihai Perdum ·

    Ripple-65B Preview Benchmark: Gauntlet, Forge 2.0, LFM3-1.7B

    <p>Ricursive's Ripple-65B Preview scored 0.028 out of 1 on our Gauntlet sb-7.2 agentic coding benchmark, where DeepSeek V4.1 Flash 1017 scored 0.6957 in October. One wiring line made every /api request in its app fail with a 500, and after seeing that on three HTTP checks it move…

RELATED ENTITIES

RELATED TOPICS