Fable-5 vs Ripple-65B Preview
New ComparisonScores are fetched live from the current database on every visit — nothing is cached.
Winner
Fable-5 wins this comparison with an overall score of 85 vs 56 for Ripple-65B Preview, leading 4 of 5 shared benchmarks.
Based on 5 of 55 benchmarks scored by all 2 selected models.
Benchmark Scores Comparison
Fable-5
Score: 15.0
Ripple-65B Preview
65.0B params
Coverage matrix
2 models × 55 benchmarks — hover a benchmark name for its category
| Benchmark | Ripple-65B Preview Ricursive Intelligence | Fable-5 Anthropic |
|---|---|---|
| GPQA Diamond | 85.2 | 92.6 |
| Automation-Bench | — | 29.1 |
| SWE-bench Pro | 61.42 | 80 |
| PRBench-Finance | — | 55.8 |
| AA-LCR | 75 | — |
| AIME 26 | 95 | — |
| Agents' Last Exam | — | 23.8 |
| Toolathlon Verified | — | 77.9 |
| PLawBench | — | 70.2 |
| QwenReactBench | — | 1770 |
| AutomationBench (Public) | 36.4 | — |
| QwenSVGBench | — | 1690 |
| StrongREJECT v2 (adaptive) | 97.5 | — |
| SWE-bench Pro v2.0 Hard | 79.1 | — |
| PRBench-Legal | — | 57.6 |
| PostTrainBench | — | 41.8 |
| DSBench-FullStack | — | 77.2 |
| Terminal-Bench 3.0 | — | 33.7 |
| WorkSpaceBench | — | 68.7 |
| MMLU-Pro | 84.2 | — |
| ExploitGym (6h) | — | 247 |
| HLE (with tools) | — | 64.5 |
| FrontierSWE | — | 88.2 |
| AIME 2024 | 97.1 | — |
| SkillsBench | — | 70.9 |
| CoWorkBench | — | 75.9 |
| MMLU | 89.6 | — |
| PaperBench | — | 88.8 |
| IFBench | 79.2 | 63.5 |
| SWE-bench Verified | 76.5 | — |
| Humanity's Last Exam | — | 53.3 |
| DSBench-Hard | — | 68.3 |
| QwenSWEBench | — | 86.3 |
| ExploitGym (2h) | — | 181 |
| Terminal-Bench 2.1 (Terminus-2) | 80.5 | — |
| DeepSWE | — | 70 |
| ExploitBench | — | 78 |
| HMMT Feb 26 | 90.5 | — |
| Terminal Bench 2.1 | 80.5 | 84.6 |
| AIME 2025 | 98.3 | — |
| JobBench | — | 57.4 |
| $OneMillion-Bench | — | 55.9 |
| QwenQoderBench | — | 63.1 |
| WideSearch | — | 81.2 |
| TauBench V3 Banking | 31.27 | — |
| ProgramBench | — | 33 |
| MCP-Atlas | 71.67 | — |
| AndroidBench | — | 84.5 |
| SWE-Marathon | — | 33.1 |
| Cybergym | — | 83.1 |
| DeepSWE 1.1 | 44.3 | 70 |
| FORTRESS Benign | 95.5 | — |
| MLS-Bench-Lite | — | 49.9 |
| SciCode | 39.4 | — |
| GDPVal-AA v2 | — | 1743 |
| Covered | 21/55 | 39/55 |
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 |
|---|---|---|---|---|---|
| Fable-5 Winner | 85.4 | 4 of 5 | 39 of 55 (71.0%) | STEM & Reasoning | Instruction Following |
| Ripple-65B Preview | 55.7 | 1 of 5 | 21 of 55 (38.0%) | Instruction Following | 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 | Fable-5 | Ripple-65B Preview |
|---|---|---|
| Agentic Coding 21 benchmarks | 100 | 78.4 |
| STEM & Reasoning 7 benchmarks | 100 | 85.5 |
| Instruction Following 1 benchmark | 72.2 | 100 |
Fully comparable benchmarks
Scored by all 2 selected models (5)
| Benchmark | Category | Fable-5 | Ripple-65B Preview |
|---|---|---|---|
| GPQA Diamond | stem_reasoning | 92.6 | 85.2 |
| SWE-bench Pro | coding_agent | 80 | 61.42 |
| IFBench | instruction_following | 63.5 | 79.2 |
| Terminal Bench 2.1 | coding_agent | 84.6 | 80.5 |
| DeepSWE 1.1 | coding_agent | 70 | 44.3 |
Partial coverage benchmarks
Scored by at least one but not all selected models (50) — missing scores show as —
| Benchmark | Category | Fable-5 | Ripple-65B Preview |
|---|---|---|---|
| Automation-Bench 1/2 models | general_agent | 29.1 | — |
| PRBench-Finance 1/2 models | general_capabilities | 55.8 | — |
| AA-LCR 1/2 models | long_context | — | 75 |
| AIME 26 1/2 models | stem_reasoning | — | 95 |
| Agents' Last Exam 1/2 models | general_agent | 23.8 | — |
| Toolathlon Verified 1/2 models | general_agent | 77.9 | — |
| PLawBench 1/2 models | general_capabilities | 70.2 | — |
| QwenReactBench 1/2 models | coding_agent | 1770 | — |
| AutomationBench (Public) 1/2 models | general_agent | — | 36.4 |
| QwenSVGBench 1/2 models | coding_agent | 1690 | — |
| StrongREJECT v2 (adaptive) 1/2 models | safety | — | 97.5 |
| SWE-bench Pro v2.0 Hard 1/2 models | coding_agent | — | 79.1 |
| PRBench-Legal 1/2 models | general_capabilities | 57.6 | — |
| PostTrainBench 1/2 models | coding_agent | 41.8 | — |
| DSBench-FullStack 1/2 models | coding_agent | 77.2 | — |
| Terminal-Bench 3.0 1/2 models | coding_agent | 33.7 | — |
| WorkSpaceBench 1/2 models | general_agent | 68.7 | — |
| MMLU-Pro 1/2 models | knowledge | — | 84.2 |
| ExploitGym (6h) 1/2 models | cybersecurity | 247 | — |
| HLE (with tools) 1/2 models | stem_reasoning | 64.5 | — |
| FrontierSWE 1/2 models | coding_agent | 88.2 | — |
| AIME 2024 1/2 models | stem_reasoning | — | 97.1 |
| SkillsBench 1/2 models | general_agent | 70.9 | — |
| CoWorkBench 1/2 models | general_agent | 75.9 | — |
| MMLU 1/2 models | knowledge | — | 89.6 |
| PaperBench 1/2 models | coding_agent | 88.8 | — |
| SWE-bench Verified 1/2 models | coding_agent | — | 76.5 |
| Humanity's Last Exam 1/2 models | stem_reasoning | 53.3 | — |
| DSBench-Hard 1/2 models | coding_agent | 68.3 | — |
| QwenSWEBench 1/2 models | coding_agent | 86.3 | — |
| ExploitGym (2h) 1/2 models | cybersecurity | 181 | — |
| Terminal-Bench 2.1 (Terminus-2) 1/2 models | coding_agent | — | 80.5 |
| DeepSWE 1/2 models | coding_agent | 70 | — |
| ExploitBench 1/2 models | cybersecurity | 78 | — |
| HMMT Feb 26 1/2 models | stem_reasoning | — | 90.5 |
| AIME 2025 1/2 models | stem_reasoning | — | 98.3 |
| JobBench 1/2 models | general_agent | 57.4 | — |
| $OneMillion-Bench 1/2 models | general_capabilities | 55.9 | — |
| QwenQoderBench 1/2 models | coding_agent | 63.1 | — |
| WideSearch 1/2 models | general_agent | 81.2 | — |
| TauBench V3 Banking 1/2 models | general_agent | — | 31.27 |
| ProgramBench 1/2 models | coding_agent | 33 | — |
| MCP-Atlas 1/2 models | general_agent | — | 71.67 |
| AndroidBench 1/2 models | coding_agent | 84.5 | — |
| SWE-Marathon 1/2 models | coding_agent | 33.1 | — |
| Cybergym 1/2 models | general_agent | 83.1 | — |
| FORTRESS Benign 1/2 models | safety | — | 95.5 |
| MLS-Bench-Lite 1/2 models | coding_agent | 49.9 | — |
| SciCode 1/2 models | — | — | 39.4 |
| GDPVal-AA v2 1/2 models | general_agent | 1743 | — |
Comparison FAQ
Which model is better, Fable-5 or Ripple-65B Preview?
Fable-5 wins this comparison with an overall score of 85 vs 56 for Ripple-65B Preview, leading 4 of 5 shared benchmarks.
Which model is better at Agentic Coding, Fable-5 or Ripple-65B Preview?
Fable-5 leads the Agentic Coding category (strength score 100/100 across 3 comparable benchmarks).
Where does Ripple-65B Preview outperform Fable-5?
Ripple-65B Preview leads the Instruction Following category (strength score 100/100 across 1 comparable benchmark).
How reliable is this comparison verdict?
Based on 5 of 55 benchmarks scored by all 2 selected models.