Kimi K3.1 Pro vs Ripple-65B Preview
New ComparisonScores are fetched live from the current database on every visit — nothing is cached.
Winner
Kimi K3.1 Pro scores higher overall across category strength profiles (94 vs 42 for Ripple-65B Preview); only 2 benchmarks are directly comparable.
Only 2 of 65 benchmarks are scored by every selected model — the verdict leans on category strength profiles and is indicative.
Benchmark Scores Comparison
Kimi K3.1 Pro
2.8T params
Ripple-65B Preview
65.0B params
Coverage matrix
2 models × 65 benchmarks — hover a benchmark name for its category
| Benchmark | Kimi K3.1 Pro Moonshot AI | Ripple-65B Preview Ricursive Intelligence |
|---|---|---|
| PerceptionBench | 68.3 | — |
| GPQA Diamond | 94.2 | 85.2 |
| Design Bench | 957 | — |
| SWE-bench Pro | — | 61.42 |
| BioMysteryBench | 80.6 | — |
| AA-LCR | — | 75 |
| AIME 26 | — | 95 |
| BenchCAD w/o tools | 72.8 | — |
| BabyVision w/ python | 95.4 | — |
| Agents' Last Exam | 43.2 | — |
| Kimi Hallu Bench w/o tools | 5.4 | — |
| AutomationBench (Public) | — | 36.4 |
| Kimi Hallu Bench Hard w/ tools | 8.3 | — |
| ZeroBench_main w/ python (pass@5) | 63 | — |
| OfficeQA Pro | 67.4 | — |
| StrongREJECT v2 (adaptive) | — | 97.5 |
| GDP.pdf w/ python | 85.7 | — |
| BenchCAD w/ tools | 92.7 | — |
| ChartoGraphy w/ python | 90.2 | — |
| SWE-bench Pro v2.0 Hard | — | 79.1 |
| MMMU-Pro | 84.1 | — |
| Program Bench | 31.5 | — |
| PostTrainBench | 36.5 | — |
| OSWorld V2.1 | 79.6 | — |
| Apex-Agents | 69.4 | — |
| MMLU-Pro | — | 84.2 |
| Terminal-Bench Science 0.1 | 38.1 | — |
| ExploitGym (6h) | 20.7 | — |
| Frontier Finance | 58.6 | — |
| xdev-bench-hard | 81 | — |
| HLE (with tools) | 70 | — |
| CharXiv (RQ) | 89 | — |
| Automation Bench-AA | 73.3 | — |
| GDP.pdf | 34.6 | — |
| AIME 2024 | — | 97.1 |
| BrowseComp | 92.1 | — |
| MMLU | — | 89.6 |
| Harvey Legal Agent | 23.7 | — |
| OfficeQA Pro v2 | 64.4 | — |
| CharXiv (RQ) w/ python | 93.4 | — |
| Agents' Last Exam (CLI) | 44.2 | — |
| IFBench | — | 79.2 |
| SWE-bench Verified | — | 76.5 |
| Humanity's Last Exam | 51.1 | — |
| HANDBOOK.md | 44.6 | — |
| HLE-Diamond (no tools) | 39.4 | — |
| MMMU-Pro w/ python | 90 | — |
| Terminal-Bench 2.1 (Terminus-2) | — | 80.5 |
| ExploitBench | 74.7 | — |
| HMMT Feb 26 | — | 90.5 |
| Terminal Bench 2.1 | — | 80.5 |
| AIME 2025 | — | 98.3 |
| Kimi Code Bench 3.0 Long-horizon | 61.2 | — |
| Kimi Code Bench V2 | 77.1 | — |
| DECK-Arena | 1456 | — |
| TauBench V3 Banking | — | 31.27 |
| MCP-Atlas | — | 71.67 |
| SWE-Marathon | 51.7 | — |
| Terminal-Bench 4.0 | 65.7 | — |
| DeepSWE 1.1 | 75.5 | 44.3 |
| FORTRESS Benign | — | 95.5 |
| Business Operation | 37.8 | — |
| AA-Briefcase v1.1 | 1678 | — |
| SciCode | — | 39.4 |
| GDPval-AA v2.1 | 1846 | — |
| Covered | 46/65 | 21/65 |
Scorecard
Overall 0–100 score — category strengths (50%), shared-benchmark wins (30%), coverage (20%)
| Model | Overall score | Shared benchmark wins | Coverage | Strongest at | Weakest at |
|---|---|---|---|---|---|
| Kimi K3.1 Pro Winner | 94.2 | 2 of 2 | 46 of 65 (71.0%) | STEM & Reasoning | Agentic Coding |
| Ripple-65B Preview | 41.8 | 0 of 2 | 21 of 65 (32.0%) | STEM & Reasoning | Agentic Coding |
Category strengths
Where each model stands, per benchmark category — score relative to the best model, adjusted for benchmark coverage. This also ranks models when they share few benchmarks.
| Category | Kimi K3.1 Pro | Ripple-65B Preview |
|---|---|---|
| Agentic Coding 15 benchmarks | 100 | 58.6 |
| STEM & Reasoning 9 benchmarks | 100 | 83 |
Fully comparable benchmarks
Scored by all 2 selected models (2)
| Benchmark | Category | Kimi K3.1 Pro | Ripple-65B Preview |
|---|---|---|---|
| GPQA Diamond | stem_reasoning | 94.2 | 85.2 |
| DeepSWE 1.1 | coding_agent | 75.5 | 44.3 |
Partial coverage benchmarks
Scored by at least one but not all selected models (63) — missing scores show as —
| Benchmark | Category | Kimi K3.1 Pro | Ripple-65B Preview |
|---|---|---|---|
| PerceptionBench 1/2 models | vision_language | 68.3 | — |
| Design Bench 1/2 models | agentic | 957 | — |
| SWE-bench Pro 1/2 models | coding_agent | — | 61.42 |
| BioMysteryBench 1/2 models | stem_reasoning | 80.6 | — |
| AA-LCR 1/2 models | long_context | — | 75 |
| AIME 26 1/2 models | stem_reasoning | — | 95 |
| BenchCAD w/o tools 1/2 models | coding_agent | 72.8 | — |
| BabyVision w/ python 1/2 models | vision_language | 95.4 | — |
| Agents' Last Exam 1/2 models | general_agent | 43.2 | — |
| Kimi Hallu Bench w/o tools 1/2 models | safety | 5.4 | — |
| AutomationBench (Public) 1/2 models | general_agent | — | 36.4 |
| Kimi Hallu Bench Hard w/ tools 1/2 models | safety | 8.3 | — |
| ZeroBench_main w/ python (pass@5) 1/2 models | vision_language | 63 | — |
| OfficeQA Pro 1/2 models | general_agent | 67.4 | — |
| StrongREJECT v2 (adaptive) 1/2 models | safety | — | 97.5 |
| GDP.pdf w/ python 1/2 models | document_understanding | 85.7 | — |
| BenchCAD w/ tools 1/2 models | coding_agent | 92.7 | — |
| ChartoGraphy w/ python 1/2 models | vision_language | 90.2 | — |
| SWE-bench Pro v2.0 Hard 1/2 models | coding_agent | — | 79.1 |
| MMMU-Pro 1/2 models | vision_language | 84.1 | — |
| Program Bench 1/2 models | coding_agent | 31.5 | — |
| PostTrainBench 1/2 models | coding_agent | 36.5 | — |
| OSWorld V2.1 1/2 models | general_agent | 79.6 | — |
| Apex-Agents 1/2 models | general_agent | 69.4 | — |
| MMLU-Pro 1/2 models | knowledge | — | 84.2 |
| Terminal-Bench Science 0.1 1/2 models | coding_agent | 38.1 | — |
| ExploitGym (6h) 1/2 models | cybersecurity | 20.7 | — |
| Frontier Finance 1/2 models | domain_finance | 58.6 | — |
| xdev-bench-hard 1/2 models | safety | 81 | — |
| HLE (with tools) 1/2 models | stem_reasoning | 70 | — |
| CharXiv (RQ) 1/2 models | document_understanding | 89 | — |
| Automation Bench-AA 1/2 models | agentic | 73.3 | — |
| GDP.pdf 1/2 models | long_context | 34.6 | — |
| AIME 2024 1/2 models | stem_reasoning | — | 97.1 |
| BrowseComp 1/2 models | general_agent | 92.1 | — |
| MMLU 1/2 models | knowledge | — | 89.6 |
| Harvey Legal Agent 1/2 models | general_agent | 23.7 | — |
| OfficeQA Pro v2 1/2 models | document_understanding | 64.4 | — |
| CharXiv (RQ) w/ python 1/2 models | vision_language | 93.4 | — |
| Agents' Last Exam (CLI) 1/2 models | general_agent | 44.2 | — |
| IFBench 1/2 models | instruction_following | — | 79.2 |
| SWE-bench Verified 1/2 models | coding_agent | — | 76.5 |
| Humanity's Last Exam 1/2 models | stem_reasoning | 51.1 | — |
| HANDBOOK.md 1/2 models | general_agent | 44.6 | — |
| HLE-Diamond (no tools) 1/2 models | stem_reasoning | 39.4 | — |
| MMMU-Pro w/ python 1/2 models | vision_language | 90 | — |
| Terminal-Bench 2.1 (Terminus-2) 1/2 models | coding_agent | — | 80.5 |
| ExploitBench 1/2 models | cybersecurity | 74.7 | — |
| HMMT Feb 26 1/2 models | stem_reasoning | — | 90.5 |
| Terminal Bench 2.1 1/2 models | coding_agent | — | 80.5 |
| AIME 2025 1/2 models | stem_reasoning | — | 98.3 |
| Kimi Code Bench 3.0 Long-horizon 1/2 models | coding_agent | 61.2 | — |
| Kimi Code Bench V2 1/2 models | coding_agent | 77.1 | — |
| DECK-Arena 1/2 models | agentic | 1456 | — |
| TauBench V3 Banking 1/2 models | general_agent | — | 31.27 |
| MCP-Atlas 1/2 models | general_agent | — | 71.67 |
| SWE-Marathon 1/2 models | coding_agent | 51.7 | — |
| Terminal-Bench 4.0 1/2 models | coding_agent | 65.7 | — |
| FORTRESS Benign 1/2 models | safety | — | 95.5 |
| Business Operation 1/2 models | agentic | 37.8 | — |
| AA-Briefcase v1.1 1/2 models | general_agent | 1678 | — |
| SciCode 1/2 models | — | — | 39.4 |
| GDPval-AA v2.1 1/2 models | general_agent | 1846 | — |
Comparison FAQ
Which model is better, Kimi K3.1 Pro or Ripple-65B Preview?
Kimi K3.1 Pro scores higher overall across category strength profiles (94 vs 42 for Ripple-65B Preview); only 2 benchmarks are directly comparable.
Which model is better at Agentic Coding, Kimi K3.1 Pro or Ripple-65B Preview?
Kimi K3.1 Pro leads the Agentic Coding category (strength score 100/100 across 1 comparable benchmark).
How reliable is this comparison verdict?
Only 2 of 65 benchmarks are scored by every selected model — the verdict leans on category strength profiles and is indicative.