Inference
EN
Ricursive Intelligence

Ripple-65B Preview

Ripple-65B Preview is a reasoning model from Ricursive Intelligence in the Ripple family. 17 benchmarks count toward its index, in 6 categories.

  • New
  • Open weights
  • Reasoning
  • Input: text
  • Released 2026-11
RankedEnough results for an index.
IndexAll categories, out of 100.52.3±5.4Median 51.0
CoverageIndex weight that has results.85%
SpeedOutput tokens per second.63/sMedian 67/s
First tokenSeconds to the first output token.0.4 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$0.20Median $0.60
Output / 1MUS dollars per 1M output tokens.$0.60Median $2.55
ContextMaximum tokens in one request.1.05MMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
ricursiveai/ripple-65b-preview
Max outputMaximum output tokens per request.
131K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.05
WeightsLink to the published weights.
Hugging Face (opens in a new tab) ↗
RetiresDate OpenRouter removes the model.
—

Run locally

64.78B parameters
16-bit
137.0 GB
8-bit
73.3 GB
4-bit
42.2 GB
Weights
Hugging Face (opens in a new tab) ↗

Memory need with a short context. The 4-bit copy fits in 48 GB. Compare local models

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.5 counted49.5131 / 218
CodingCode writing and repair.3 counted55.393 / 209
ReasoningLogic problems and puzzles.1 counted58.8—
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.3 counted48.1149 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted63.0—
MathMath problems.4 counted52.774 / 168

Results

17 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
American Invitational Mathematics Examination 2024Math97.1%1 / 27
American Invitational Mathematics Examination 2025Math98.3%2 / 53
Massive Multitask Language UnderstandingKnowledge89.6%8 / 34
Instruction Following BenchmarkInstruction79.2%17 / 57
Harvard-MIT Mathematics Tournament February 2026Math90.5%9 / 27
Massive Multitask Language Understanding ProfessionalKnowledge84.2%26 / 75
SWE-bench ProCoding61.4%29 / 83
Software Engineering Benchmark VerifiedCoding76.5%41 / 114
Terminal-Bench 2.1 · BenchLMAgentic80.5%33 / 86
Artificial Analysis Long Context ReasoningReasoning75.0%95 / 217
AIME 2026Math95.0%17 / 34
MCP AtlasAgentic71.7%30 / 52
Scientific Code BenchmarkCoding39.4%22 / 35
AutomationBenchAgentic36.4%21 / 32
GPQA Diamond · BenchLMKnowledge85.2%58 / 84
τ³-Bench Tool-Agent-User EvaluationAgentic31.3%24 / 32
DeepSWEAgentic44.3%53 / 59

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuse

History

5 releases
Index52.3 → 52.3
11 Nov 202612 Nov 2026
Output / 1M$0.60 → $0.60
11 Nov 202612 Nov 2026

Questions

How much does Ripple-65B Preview cost?
$0.20 per 1M input tokens, $0.60 per 1M output tokens.
How good is Ripple-65B Preview?
Its index is 52.3 out of 100. That is place 124 of 283 ranked models.
What is Ripple-65B Preview best at?
Math: 52.7 out of 100, place 74 of 168.
How fast is Ripple-65B Preview?
63 output tokens per second, 0.4 s to the first token.
What is the context window of Ripple-65B Preview?
1.05M tokens.
Is Ripple-65B Preview open source?
Yes. Its weights are published.
When was Ripple-65B Preview released?
November 2026.

Badge

Ripple-65B Preview on Inference360: place 124 of 283, index 52.3
HTML
<a href="https://inference360.ai/models/ripple-65b-preview"><img src="https://inference360.ai/badges/ripple-65b-preview.svg" alt="Ripple-65B Preview on Inference360: place 124 of 283, index 52.3" height="20"></a>
Markdown
[![Ripple-65B Preview on Inference360: place 124 of 283, index 52.3](https://inference360.ai/badges/ripple-65b-preview.svg)](https://inference360.ai/models/ripple-65b-preview)

Compare with

Mercury 352.3Hy3 Preview52.3Kimi K2.552.2dots3-note Preview63.4

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeNemotron 3 Ultra50.8 · Free