Fable-5 vs Claude Opus 5
New ComparisonScores are fetched live from the current database on every visit — nothing is cached.
Winner
Claude Opus 5
Claude Opus 5 wins this comparison with an overall score of 84 vs 62 for Fable-5, leading 12 of 17 shared benchmarks.
Claude Opus 5
84.3
Fable-5
62
Based on 17 of 76 benchmarks scored by all 2 selected models.
Benchmark Scores Comparison
Fable-5
Claude Opus 5
Fable-5
Score: 15.0
Claude Opus 5
Score: 40.0
Coverage matrix
2 models × 76 benchmarks — hover a benchmark name for its category
Shading = score relative to the best score among the selected models:
Low
Mid
High
Missing (—)
The totals row shows how many of the 76 benchmarks each model has scores for.
| Benchmark | Fable-5 Anthropic | Claude Opus 5 Anthropic |
|---|---|---|
| GPQA Diamond | 92.6 | 93.7 |
| ArXivMath | — | 71.5 |
| Hy-LifeSearch (Internal) | — | 56.1 |
| Automation-Bench | 29.1 | 48.7 |
| SWE-bench Pro | 80 | 79.2 |
| BioMysteryBench | — | 72.1 |
| PRBench-Finance | 55.8 | — |
| Agents' Last Exam | 23.8 | 25.1 |
| Toolathlon Verified | 77.9 | 76.5 |
| Hy-Backend 2.0 (Internal) | — | 40.3 |
| PLawBench | 70.2 | — |
| Hy-SWE Max Verified (Internal) | — | 70.1 |
| Hy-BrowseComp-Pro2 (Internal) | — | 61.3 |
| QwenReactBench | 1770 | — |
| OfficeQA Pro | — | 66.9 |
| QwenSVGBench | 1690 | — |
| SWE Atlas - TW | — | 68.7 |
| LOCA-Bench (256k) | — | 53.7 |
| SWE Atlas - QnA | — | 57.5 |
| NL2Repo | — | 75.3 |
| PRBench-Legal | 57.6 | — |
| PostTrainBench | 41.8 | 35 |
| DSBench-FullStack | 77.2 | — |
| Terminal-Bench 3.0 | 33.7 | — |
| BabyVision | — | 94.1 |
| Apex-Agents | — | 41.8 |
| WorkSpaceBench | 68.7 | 75 |
| BankerToolBench | — | 81.9 |
| E-Bench-Code (Internal) | — | 82.7 |
| ExploitGym (6h) | 247 | — |
| HLE (with tools) | 64.5 | 60.9 |
| CharXiv (RQ) | — | 83.7 |
| FrontierSWE | 88.2 | — |
| GDP.pdf | — | 21.6 |
| CritPt (no tools) | — | 29.1 |
| NL2Repo-Bench | — | 75.3 |
| DRACO | — | 88.6 |
| SkillsBench | 70.9 | — |
| CoWorkBench | 75.9 | — |
| SWE-bench Multilingual | — | 89.5 |
| PaperBench | 88.8 | — |
| Hy-FinAgentBench (Internal) | — | 82 |
| IFBench | 63.5 | — |
| Humanity's Last Exam | 53.3 | 54.9 |
| DSBench-Hard | 68.3 | — |
| QwenSWEBench | 86.3 | — |
| ExploitGym (2h) | 181 | — |
| SUPERChem | — | 76.7 |
| HorizonMath (pass@4) | — | 5.3 |
| Terminal-Bench 2.1 (Terminus-2) | — | 86.7 |
| DeepSWE | 70 | 68.8 |
| ExploitBench | 78 | — |
| BrokenArXiv | — | 77.7 |
| Hy-FinmodelBench v2 (Internal) | — | 66 |
| MathArena Apex 2025 | — | 91.4 |
| Terminal Bench 2.1 | 84.6 | — |
| JobBench | 57.4 | 68 |
| $OneMillion-Bench | 55.9 | 68.1 |
| QwenQoderBench | 63.1 | — |
| OSWorld 2.0 (Binary) | — | 70.6 |
| WideSearch | 81.2 | 84 |
| SkillsBench Avg5 | — | 63.7 |
| E-Bench (Internal) | — | 77.8 |
| ProgramBench | 33 | 39.5 |
| MCP-Atlas | — | 85.7 |
| AndroidBench | 84.5 | — |
| SWE-Marathon | 33.1 | 50 |
| Cybergym | 83.1 | — |
| Terminal-Bench 4.0 | — | 51.8 |
| SWE Atlas - RF | — | 60 |
| DeepSWE 1.1 | 70 | 74 |
| Hy-CompanyBench V2 (Internal) | — | 72.7 |
| Harbor-Index | — | 56.9 |
| SWE Refactor Bench | — | 31 |
| MLS-Bench-Lite | 49.9 | — |
| GDPVal-AA v2 | 1743 | 1831 |
| Covered | 39/76 | 54/76 |
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 |
|---|---|---|---|---|---|
| Claude Opus 5 Winner | 84.3 | 12 of 17 | 54 of 76 (71.0%) | General Capabilities | Agentic Coding |
| Fable-5 | 62 | 5 of 17 | 39 of 76 (51.0%) | STEM & Reasoning | General Capabilities |
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 | Claude Opus 5 | Fable-5 |
|---|---|---|
| Agentic Coding 32 benchmarks | 95.6 | 90.4 |
| General Agents 20 benchmarks | 99.6 | 81.2 |
| STEM & Reasoning 10 benchmarks | 97.6 | 98.3 |
| General Capabilities 4 benchmarks | 100 | 53.6 |
Fully comparable benchmarks
Scored by all 2 selected models (17)
| Benchmark | Category | Fable-5 | Claude Opus 5 |
|---|---|---|---|
| GPQA Diamond | stem_reasoning | 92.6 | 93.7 |
| Automation-Bench | general_agent | 29.1 | 48.7 |
| SWE-bench Pro | coding_agent | 80 | 79.2 |
| Agents' Last Exam | general_agent | 23.8 | 25.1 |
| Toolathlon Verified | general_agent | 77.9 | 76.5 |
| PostTrainBench | coding_agent | 41.8 | 35 |
| WorkSpaceBench | general_agent | 68.7 | 75 |
| HLE (with tools) | stem_reasoning | 64.5 | 60.9 |
| Humanity's Last Exam | stem_reasoning | 53.3 | 54.9 |
| DeepSWE | coding_agent | 70 | 68.8 |
| JobBench | general_agent | 57.4 | 68 |
| $OneMillion-Bench | general_capabilities | 55.9 | 68.1 |
| WideSearch | general_agent | 81.2 | 84 |
| ProgramBench | coding_agent | 33 | 39.5 |
| SWE-Marathon | coding_agent | 33.1 | 50 |
| DeepSWE 1.1 | coding_agent | 70 | 74 |
| GDPVal-AA v2 | general_agent | 1743 | 1831 |
Partial coverage benchmarks
Scored by at least one but not all selected models (59) — missing scores show as —
| Benchmark | Category | Fable-5 | Claude Opus 5 |
|---|---|---|---|
| ArXivMath 1/2 models | stem_reasoning | — | 71.5 |
| Hy-LifeSearch (Internal) 1/2 models | general_agent | — | 56.1 |
| BioMysteryBench 1/2 models | stem_reasoning | — | 72.1 |
| PRBench-Finance 1/2 models | general_capabilities | 55.8 | — |
| Hy-Backend 2.0 (Internal) 1/2 models | coding_agent | — | 40.3 |
| PLawBench 1/2 models | general_capabilities | 70.2 | — |
| Hy-SWE Max Verified (Internal) 1/2 models | coding_agent | — | 70.1 |
| Hy-BrowseComp-Pro2 (Internal) 1/2 models | general_agent | — | 61.3 |
| QwenReactBench 1/2 models | coding_agent | 1770 | — |
| OfficeQA Pro 1/2 models | general_agent | — | 66.9 |
| QwenSVGBench 1/2 models | coding_agent | 1690 | — |
| SWE Atlas - TW 1/2 models | coding_agent | — | 68.7 |
| LOCA-Bench (256k) 1/2 models | long_context | — | 53.7 |
| SWE Atlas - QnA 1/2 models | coding_agent | — | 57.5 |
| NL2Repo 1/2 models | coding_agent | — | 75.3 |
| PRBench-Legal 1/2 models | general_capabilities | 57.6 | — |
| DSBench-FullStack 1/2 models | coding_agent | 77.2 | — |
| Terminal-Bench 3.0 1/2 models | coding_agent | 33.7 | — |
| BabyVision 1/2 models | vision_language | — | 94.1 |
| Apex-Agents 1/2 models | general_agent | — | 41.8 |
| BankerToolBench 1/2 models | general_agent | — | 81.9 |
| E-Bench-Code (Internal) 1/2 models | coding_agent | — | 82.7 |
| ExploitGym (6h) 1/2 models | cybersecurity | 247 | — |
| CharXiv (RQ) 1/2 models | document_understanding | — | 83.7 |
| FrontierSWE 1/2 models | coding_agent | 88.2 | — |
| GDP.pdf 1/2 models | long_context | — | 21.6 |
| CritPt (no tools) 1/2 models | stem_reasoning | — | 29.1 |
| NL2Repo-Bench 1/2 models | coding_agent | — | 75.3 |
| DRACO 1/2 models | general_agent | — | 88.6 |
| SkillsBench 1/2 models | general_agent | 70.9 | — |
| CoWorkBench 1/2 models | general_agent | 75.9 | — |
| SWE-bench Multilingual 1/2 models | coding_agent | — | 89.5 |
| PaperBench 1/2 models | coding_agent | 88.8 | — |
| Hy-FinAgentBench (Internal) 1/2 models | domain_finance | — | 82 |
| IFBench 1/2 models | instruction_following | 63.5 | — |
| DSBench-Hard 1/2 models | coding_agent | 68.3 | — |
| QwenSWEBench 1/2 models | coding_agent | 86.3 | — |
| ExploitGym (2h) 1/2 models | cybersecurity | 181 | — |
| SUPERChem 1/2 models | stem_reasoning | — | 76.7 |
| HorizonMath (pass@4) 1/2 models | stem_reasoning | — | 5.3 |
| Terminal-Bench 2.1 (Terminus-2) 1/2 models | coding_agent | — | 86.7 |
| ExploitBench 1/2 models | cybersecurity | 78 | — |
| BrokenArXiv 1/2 models | stem_reasoning | — | 77.7 |
| Hy-FinmodelBench v2 (Internal) 1/2 models | domain_finance | — | 66 |
| MathArena Apex 2025 1/2 models | stem_reasoning | — | 91.4 |
| Terminal Bench 2.1 1/2 models | coding_agent | 84.6 | — |
| QwenQoderBench 1/2 models | coding_agent | 63.1 | — |
| OSWorld 2.0 (Binary) 1/2 models | general_agent | — | 70.6 |
| SkillsBench Avg5 1/2 models | coding_agent | — | 63.7 |
| E-Bench (Internal) 1/2 models | general_agent | — | 77.8 |
| MCP-Atlas 1/2 models | general_agent | — | 85.7 |
| AndroidBench 1/2 models | coding_agent | 84.5 | — |
| Cybergym 1/2 models | general_agent | 83.1 | — |
| Terminal-Bench 4.0 1/2 models | coding_agent | — | 51.8 |
| SWE Atlas - RF 1/2 models | coding_agent | — | 60 |
| Hy-CompanyBench V2 (Internal) 1/2 models | general_agent | — | 72.7 |
| Harbor-Index 1/2 models | coding_agent | — | 56.9 |
| SWE Refactor Bench 1/2 models | coding_agent | — | 31 |
| MLS-Bench-Lite 1/2 models | coding_agent | 49.9 | — |
Comparison FAQ
Which model is better, Claude Opus 5 or Fable-5?
Claude Opus 5 wins this comparison with an overall score of 84 vs 62 for Fable-5, leading 12 of 17 shared benchmarks.
Which model is better at General Agents, Claude Opus 5 or Fable-5?
Claude Opus 5 leads the General Agents category (strength score 99.6/100 across 7 comparable benchmarks).
Where does Fable-5 outperform Claude Opus 5?
Fable-5 leads the STEM & Reasoning category (strength score 98.3/100 across 3 comparable benchmarks).
How reliable is this comparison verdict?
Based on 17 of 76 benchmarks scored by all 2 selected models.