Compare / Ripple 65B Preview vs K2-V2 Instruct
Ripple 65B Preview vs K2-V2 Instruct
Updated November 2026
Verdict
Ripple 65B Preview scores higher on the Small LM Index: 74.6 vs 58.2. On the 6 benchmarks both labs report, Ripple 65B Preview wins 6 and K2-V2 Instruct wins 0. Ripple 65B Preview is smaller: it needs about 41.9 GB of memory at 4-bit, against 47 GB for K2-V2 Instruct. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick Ripple 65B Preview if…
- you want the strongest model overall
- you need math and reasoning
- you need precise instruction following
- you have limited memory (about 41.9 GB at 4-bit)
- you work with long documents
- you want the more widely used model (more quantized builds and community support)
Pick K2-V2 Instruct if…
No clear advantage in the data we have.
Specifications
| Ripple 65B Preview | K2-V2 Instruct | |
|---|---|---|
| Small LM Index | 74.6 (likely 74–77) | 58.2 (likely 56–61) |
| Lab | Ricursive Intelligence · Other | LLM360 / MBZUAI (K2) · Other |
| Released | 2026-11-04 | 2025-12-03 |
| Parameters | 64.8B (dense) | 70B (dense) |
| Memory at 4-bit | ~41.9 GB | ~47 GB |
| Context window | 1M tokens | 512K tokens |
| Input | text | text |
| Reasoning | Always thinks | Hybrid (thinking on/off) |
| License | Apache-2.0 | Apache-2.0 |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 15K | 2.3K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | Ripple 65B Preview | K2-V2 Instruct |
|---|---|---|
| MMLU-Pro Knowledge | 84.2 | 78.6✓ |
| GPQA Diamond Knowledge | 85.2 | 68.1✓ |
| Humanity's Last Exam Reasoning | ≈ 18 | 10.5✓ |
| AIME Math | 98.3 | 78.3✓ |
| LiveCodeBench Coding | ≈ 90 | 69.4✓ |
| SWE-bench Verified Coding | 76.5 | ≈ 51 |
| Terminal-Bench Agentic | 80.5 | — |
| τ²-Bench Agentic | — | 27.8✓ |
| IFBench Instruction following | 79.2 | 60.1✓ |
| MMLU Knowledge | 89.6 | — |
| IFEval Instruction following | — | 90.0 |
| HMMT Math | 90.5 | 71.4 |
| AA-LCR Long context | 75.0 | 35.0✓ |
| SciCode Coding | 39.4 | — |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, Ripple 65B Preview or K2-V2 Instruct?
Ripple 65B Preview scores higher on the Small LM Index: 74.6 vs 58.2. On the 6 benchmarks both labs report, Ripple 65B Preview wins 6 and K2-V2 Instruct wins 0.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. Ripple 65B Preview is smaller: it needs about 41.9 GB of memory at 4-bit, against 47 GB for K2-V2 Instruct.
Which has the longer context window?
Ripple 65B Preview has the longer context window: 1M tokens against 512K.
Can I use Ripple 65B Preview and K2-V2 Instruct commercially?
Both are released under the Apache-2.0 license. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.