Claude Opus 5 vs Ornith-1.5-35B-A3B
New ComparisonScores are fetched live from the current database on every visit — nothing is cached.
Winner
Claude Opus 5 wins this comparison with an overall score of 98 vs 37 for Ornith-1.5-35B-A3B, leading 12 of 12 shared benchmarks.
Based on 12 of 59 benchmarks scored by all 2 selected models.
Benchmark Scores Comparison
Claude Opus 5
Score: 40.0
Ornith-1.5-35B-A3B
36.0B params
Score: 100.0
Coverage matrix
2 models × 59 benchmarks — hover a benchmark name for its category
| Benchmark | Ornith-1.5-35B-A3B Ornith AI | Claude Opus 5 Anthropic |
|---|---|---|
| GPQA Diamond | 89.2 | 93.7 |
| ArXivMath | — | 71.5 |
| Hy-LifeSearch (Internal) | — | 56.1 |
| Automation-Bench | — | 48.7 |
| SWE-bench Pro | 59.6 | 79.2 |
| BioMysteryBench | — | 72.1 |
| Agents' Last Exam | — | 25.1 |
| Toolathlon Verified | 48.7 | 76.5 |
| Hy-Backend 2.0 (Internal) | — | 40.3 |
| Hy-SWE Max Verified (Internal) | — | 70.1 |
| Hy-BrowseComp-Pro2 (Internal) | — | 61.3 |
| OfficeQA Pro | — | 66.9 |
| SWE Atlas - TW | — | 68.7 |
| LOCA-Bench (256k) | — | 53.7 |
| WildClawBench | 72.5 | — |
| SWE Atlas - QnA | 39.8 | 57.5 |
| NL2Repo | 46.2 | 75.3 |
| PostTrainBench | — | 35 |
| BabyVision | — | 94.1 |
| Apex-Agents | — | 41.8 |
| WorkSpaceBench | — | 75 |
| BankerToolBench | — | 81.9 |
| E-Bench-Code (Internal) | — | 82.7 |
| HLE (with tools) | 33.4 | 60.9 |
| CharXiv (RQ) | — | 83.7 |
| GDP.pdf | — | 21.6 |
| CritPt (no tools) | — | 29.1 |
| BrowseComp | 67.6 | — |
| NL2Repo-Bench | — | 75.3 |
| DRACO | — | 88.6 |
| SWE-bench Multilingual | 71.4 | 89.5 |
| Hy-FinAgentBench (Internal) | — | 82 |
| SWE-bench Verified | 79 | — |
| Humanity's Last Exam | 25.6 | 54.9 |
| SUPERChem | — | 76.7 |
| HorizonMath (pass@4) | — | 5.3 |
| Terminal-Bench 2.1 (Terminus-2) | 67.8 | 86.7 |
| DeepSWE | 22 | 68.8 |
| BrokenArXiv | — | 77.7 |
| Hy-FinmodelBench v2 (Internal) | — | 66 |
| MathArena Apex 2025 | — | 91.4 |
| JobBench | — | 68 |
| $OneMillion-Bench | — | 68.1 |
| Frontier-Bench v0.1 | 5.1 | — |
| OSWorld 2.0 (Binary) | — | 70.6 |
| WideSearch | 67.8 | 84 |
| SkillsBench Avg5 | — | 63.7 |
| E-Bench (Internal) | — | 77.8 |
| ProgramBench | — | 39.5 |
| MCP-Atlas | 70.2 | 85.7 |
| SWE-Marathon | — | 50 |
| Terminal-Bench 4.0 | — | 51.8 |
| SWE Atlas - RF | — | 60 |
| DeepSWE 1.1 | — | 74 |
| Terminal-Bench 2.1 (Claude Code) | 68.5 | — |
| Hy-CompanyBench V2 (Internal) | — | 72.7 |
| Harbor-Index | — | 56.9 |
| SWE Refactor Bench | — | 31 |
| GDPVal-AA v2 | — | 1831 |
| Covered | 17/59 | 54/59 |
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 | 98.3 | 12 of 12 | 54 of 59 (92.0%) | STEM & Reasoning | Agentic Coding |
| Ornith-1.5-35B-A3B | 36.7 | 0 of 12 | 17 of 59 (29.0%) | General Agents | STEM & Reasoning |
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 | Ornith-1.5-35B-A3B |
|---|---|---|
| Agentic Coding 24 benchmarks | 100 | 62.6 |
| General Agents 18 benchmarks | 100 | 62.8 |
| STEM & Reasoning 10 benchmarks | 100 | 59.1 |
Fully comparable benchmarks
Scored by all 2 selected models (12)
| Benchmark | Category | Claude Opus 5 | Ornith-1.5-35B-A3B |
|---|---|---|---|
| GPQA Diamond | stem_reasoning | 93.7 | 89.2 |
| SWE-bench Pro | coding_agent | 79.2 | 59.6 |
| Toolathlon Verified | general_agent | 76.5 | 48.7 |
| SWE Atlas - QnA | coding_agent | 57.5 | 39.8 |
| NL2Repo | coding_agent | 75.3 | 46.2 |
| HLE (with tools) | stem_reasoning | 60.9 | 33.4 |
| SWE-bench Multilingual | coding_agent | 89.5 | 71.4 |
| Humanity's Last Exam | stem_reasoning | 54.9 | 25.6 |
| Terminal-Bench 2.1 (Terminus-2) | coding_agent | 86.7 | 67.8 |
| DeepSWE | coding_agent | 68.8 | 22 |
| WideSearch | general_agent | 84 | 67.8 |
| MCP-Atlas | general_agent | 85.7 | 70.2 |
Partial coverage benchmarks
Scored by at least one but not all selected models (47) — missing scores show as —
| Benchmark | Category | Claude Opus 5 | Ornith-1.5-35B-A3B |
|---|---|---|---|
| ArXivMath 1/2 models | stem_reasoning | 71.5 | — |
| Hy-LifeSearch (Internal) 1/2 models | general_agent | 56.1 | — |
| Automation-Bench 1/2 models | general_agent | 48.7 | — |
| BioMysteryBench 1/2 models | stem_reasoning | 72.1 | — |
| Agents' Last Exam 1/2 models | general_agent | 25.1 | — |
| Hy-Backend 2.0 (Internal) 1/2 models | coding_agent | 40.3 | — |
| Hy-SWE Max Verified (Internal) 1/2 models | coding_agent | 70.1 | — |
| Hy-BrowseComp-Pro2 (Internal) 1/2 models | general_agent | 61.3 | — |
| OfficeQA Pro 1/2 models | general_agent | 66.9 | — |
| SWE Atlas - TW 1/2 models | coding_agent | 68.7 | — |
| LOCA-Bench (256k) 1/2 models | long_context | 53.7 | — |
| WildClawBench 1/2 models | coding_agent | — | 72.5 |
| PostTrainBench 1/2 models | coding_agent | 35 | — |
| BabyVision 1/2 models | vision_language | 94.1 | — |
| Apex-Agents 1/2 models | general_agent | 41.8 | — |
| WorkSpaceBench 1/2 models | general_agent | 75 | — |
| BankerToolBench 1/2 models | general_agent | 81.9 | — |
| E-Bench-Code (Internal) 1/2 models | coding_agent | 82.7 | — |
| CharXiv (RQ) 1/2 models | document_understanding | 83.7 | — |
| GDP.pdf 1/2 models | long_context | 21.6 | — |
| CritPt (no tools) 1/2 models | stem_reasoning | 29.1 | — |
| BrowseComp 1/2 models | general_agent | — | 67.6 |
| NL2Repo-Bench 1/2 models | coding_agent | 75.3 | — |
| DRACO 1/2 models | general_agent | 88.6 | — |
| Hy-FinAgentBench (Internal) 1/2 models | domain_finance | 82 | — |
| SWE-bench Verified 1/2 models | coding_agent | — | 79 |
| SUPERChem 1/2 models | stem_reasoning | 76.7 | — |
| HorizonMath (pass@4) 1/2 models | stem_reasoning | 5.3 | — |
| 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 | — |
| JobBench 1/2 models | general_agent | 68 | — |
| $OneMillion-Bench 1/2 models | general_capabilities | 68.1 | — |
| Frontier-Bench v0.1 1/2 models | coding_agent | — | 5.1 |
| 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 | — |
| ProgramBench 1/2 models | coding_agent | 39.5 | — |
| SWE-Marathon 1/2 models | coding_agent | 50 | — |
| Terminal-Bench 4.0 1/2 models | coding_agent | 51.8 | — |
| SWE Atlas - RF 1/2 models | coding_agent | 60 | — |
| DeepSWE 1.1 1/2 models | coding_agent | 74 | — |
| Terminal-Bench 2.1 (Claude Code) 1/2 models | coding_agent | — | 68.5 |
| 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 | — |
| GDPVal-AA v2 1/2 models | general_agent | 1831 | — |
Comparison FAQ
Which model is better, Claude Opus 5 or Ornith-1.5-35B-A3B?
Claude Opus 5 wins this comparison with an overall score of 98 vs 37 for Ornith-1.5-35B-A3B, leading 12 of 12 shared benchmarks.
Which model is better at Agentic Coding, Claude Opus 5 or Ornith-1.5-35B-A3B?
Claude Opus 5 leads the Agentic Coding category (strength score 100/100 across 6 comparable benchmarks).
How reliable is this comparison verdict?
Based on 12 of 59 benchmarks scored by all 2 selected models.