Claude Opus 5 vs Ornith-1.5-35B-A3B

New Comparison

Scores 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 98 vs 37 for Ornith-1.5-35B-A3B, leading 12 of 12 shared benchmarks.

Claude Opus 5 98.3 Ornith-1.5-35B-A3B 36.7

Based on 12 of 59 benchmarks scored by all 2 selected models.

Benchmark Scores Comparison

Claude Opus 5 Ornith-1.5-35B-A3B

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

Full Coverage Matrix
Hides benchmarks where all selected models score identically.
Shading = score relative to the best score among the selected models: Low Mid High Missing (—) The totals row shows how many of the 59 benchmarks each model has scores for.
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.

What now?

You've seen 2 models side by side — keep the loop going.

Share this comparison

The URL is the comparison — copy or share it anywhere. No tracking, no cookies.

Not the right matchup?

Swap one model out — the pre-filled form keeps the rest of the selection.

Swap Claude Opus 5 × Swap Ornith-1.5-35B-A3B ×