Qwen3.6-35B-A3B vs Ornith-1.0-35B
New ComparisonScores are fetched live from the current database on every visit — nothing is cached.
Winner
Ornith-1.0-35B
Ornith-1.0-35B wins this comparison with an overall score of 82 vs 55 for Qwen3.6-35B-A3B, leading 10 of 10 shared benchmarks.
Ornith-1.0-35B
82.4
Qwen3.6-35B-A3B
55
Based on 10 of 85 benchmarks scored by all 2 selected models.
Benchmark Scores Comparison
Qwen3.6-35B-A3B
Ornith-1.0-35B
Qwen3.6-35B-A3B
35.0B params
Score: 100.0
Ornith-1.0-35B
35.0B params
Score: 100.0
Coverage matrix
2 models × 85 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 85 benchmarks each model has scores for.
| Benchmark | Qwen3.6-35B-A3B Qwen Team (Alibaba Cloud) | Ornith-1.0-35B DeepReinforce AI |
|---|---|---|
| HMMT Feb 25 | 90.7 | — |
| DynaMath | 82.8 | — |
| GPQA Diamond | 86 | — |
| MathVista (mini) | 86.4 | — |
| MMBench EN-DEV v1.1 | 92.8 | — |
| LiveCodeBench v6 | 80.4 | — |
| SWE-bench Pro | 49.5 | 50.4 |
| BFCL-V4 | 64.7 | — |
| RealWorldQA | 85.3 | — |
| EmbSpatialBench | 84.3 | — |
| AA-LCR | 69.3 | — |
| AIME 26 | 92.7 | — |
| Toolathlon Verified | 41.7 | — |
| VITA-Bench | 35.6 | — |
| TAU3-Bench | 67.2 | — |
| AutomationBench (Public) | 24.9 | — |
| MMStar | 80.7 | — |
| GDPVal | 67.4 | — |
| SWE Atlas - TW | 13.3 | 27.8 |
| WildClawBench | 68.7 | — |
| SWE Atlas - QnA | 15.5 | 37.1 |
| AI2D_TEST | 92.7 | — |
| ParseBench Text Formatting | 58.3 | — |
| NL2Repo | 29.4 | 34.6 |
| MMMU-Pro | 75.3 | — |
| QwenClawBench | 52.6 | — |
| Claw-Eval Avg | 68.7 | 69.8 |
| VideoMMMU | 83.7 | — |
| HMMT Nov 25 | 89.1 | — |
| Multi-Challenge | 58.2 | — |
| MMLU-Pro | 85.2 | — |
| SuperGPQA | 64.7 | — |
| HLE (with tools) | 28.9 | — |
| LVBench | 71.4 | — |
| CharXiv (RQ) | 78 | — |
| GDP.pdf | 6.6 | — |
| BrowseComp | 62 | — |
| MMLU-Redux | 93.3 | — |
| ParseBench Text Content | 90.7 | — |
| MCPMark | 37 | — |
| AA-Omniscience Index (public set) | -7.2 | — |
| SWE-bench Multilingual | 67.2 | 69.3 |
| MLVU | 86.2 | — |
| IFBench | 66.6 | — |
| SWE-bench Verified | 73.4 | 75.6 |
| IMOAnswerBench | 78.9 | — |
| Humanity's Last Exam | 21.4 | — |
| CountBench | 96.1 | — |
| ERQA | 61.8 | — |
| VideoMME (w/o sub.) | 82.5 | — |
| Terminal-Bench 2.0 | 51.5 | — |
| DeepPlanning | 25.9 | — |
| QwenWebBench | 1397 | — |
| ODInW13 | 50.8 | — |
| VlmsAreBlind | 96.6 | — |
| Terminal-Bench 2.1 (Terminus-2) | 52.5 | 64.2 |
| DeepSWE | 0 | — |
| OmniDocBench 1.5 | 89.9 | — |
| HallusionBench | 69.8 | — |
| OCRBench | 90 | — |
| HMMT Feb 26 | 83.6 | — |
| Terminal-Bench Lite | 63.3 | — |
| CC-OCR | 81.9 | — |
| RefCOCO (avg) | 92 | — |
| Artificial Analysis Intelligence Index | 32 | — |
| Tool Decathlon | 26.9 | — |
| Frontier-Bench v0.1 | 1.4 | — |
| ParseBench Mean | 44.1 | — |
| ZEROBench_sub | 34.4 | — |
| C-Eval | 90 | — |
| WideSearch | 60.1 | — |
| SimpleVQA | 58.9 | — |
| VideoMME (w sub.) | 86.6 | — |
| SkillsBench Avg5 | 28.7 | — |
| Claw-Eval Pass^3 | 50 | — |
| MCP-Atlas | 62.8 | — |
| SWE Atlas - RF | 11.4 | 29.7 |
| V-Star | 90.1 | — |
| Terminal-Bench 2.1 (Claude Code) | 49.2 | 62.8 |
| Chatbot Korean (internal) | 74.5 | — |
| SciCode | 35.6 | — |
| RefSpatialBench | 64.3 | — |
| BrowseComp Plus | 34.8 | — |
| MMMU | 81.7 | — |
| MVBench | 74.6 | — |
| Covered | 85/85 | 10/85 |
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 |
|---|---|---|---|---|---|
| Ornith-1.0-35B Winner | 82.4 | 10 of 10 | 10 of 85 (12.0%) | Agentic Coding | Agentic Coding |
| Qwen3.6-35B-A3B | 55 | 0 of 10 | 85 of 85 (100.0%) | Agentic Coding | 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 | Ornith-1.0-35B | Qwen3.6-35B-A3B |
|---|---|---|
| Agentic Coding 19 benchmarks | 100 | 69.9 |
Fully comparable benchmarks
Scored by all 2 selected models (10)
| Benchmark | Category | Qwen3.6-35B-A3B | Ornith-1.0-35B |
|---|---|---|---|
| SWE-bench Pro | coding_agent | 49.5 | 50.4 |
| SWE Atlas - TW | coding_agent | 13.3 | 27.8 |
| SWE Atlas - QnA | coding_agent | 15.5 | 37.1 |
| NL2Repo | coding_agent | 29.4 | 34.6 |
| Claw-Eval Avg | coding_agent | 68.7 | 69.8 |
| SWE-bench Multilingual | coding_agent | 67.2 | 69.3 |
| SWE-bench Verified | coding_agent | 73.4 | 75.6 |
| Terminal-Bench 2.1 (Terminus-2) | coding_agent | 52.5 | 64.2 |
| SWE Atlas - RF | coding_agent | 11.4 | 29.7 |
| Terminal-Bench 2.1 (Claude Code) | coding_agent | 49.2 | 62.8 |
Partial coverage benchmarks
Scored by at least one but not all selected models (75) — missing scores show as —
| Benchmark | Category | Qwen3.6-35B-A3B | Ornith-1.0-35B |
|---|---|---|---|
| HMMT Feb 25 1/2 models | stem_reasoning | 90.7 | — |
| DynaMath 1/2 models | vision_language | 82.8 | — |
| GPQA Diamond 1/2 models | stem_reasoning | 86 | — |
| MathVista (mini) 1/2 models | vision_language | 86.4 | — |
| MMBench EN-DEV v1.1 1/2 models | vision_language | 92.8 | — |
| LiveCodeBench v6 1/2 models | stem_reasoning | 80.4 | — |
| BFCL-V4 1/2 models | general_agent | 64.7 | — |
| RealWorldQA 1/2 models | vision_language | 85.3 | — |
| EmbSpatialBench 1/2 models | spatial_intelligence | 84.3 | — |
| AA-LCR 1/2 models | long_context | 69.3 | — |
| AIME 26 1/2 models | stem_reasoning | 92.7 | — |
| Toolathlon Verified 1/2 models | general_agent | 41.7 | — |
| VITA-Bench 1/2 models | general_agent | 35.6 | — |
| TAU3-Bench 1/2 models | general_agent | 67.2 | — |
| AutomationBench (Public) 1/2 models | general_agent | 24.9 | — |
| MMStar 1/2 models | vision_language | 80.7 | — |
| GDPVal 1/2 models | general_agent | 67.4 | — |
| WildClawBench 1/2 models | coding_agent | 68.7 | — |
| AI2D_TEST 1/2 models | document_understanding | 92.7 | — |
| ParseBench Text Formatting 1/2 models | document_understanding | 58.3 | — |
| MMMU-Pro 1/2 models | vision_language | 75.3 | — |
| QwenClawBench 1/2 models | coding_agent | 52.6 | — |
| VideoMMMU 1/2 models | video_understanding | 83.7 | — |
| HMMT Nov 25 1/2 models | stem_reasoning | 89.1 | — |
| Multi-Challenge 1/2 models | instruction_following | 58.2 | — |
| MMLU-Pro 1/2 models | knowledge | 85.2 | — |
| SuperGPQA 1/2 models | knowledge | 64.7 | — |
| HLE (with tools) 1/2 models | stem_reasoning | 28.9 | — |
| LVBench 1/2 models | video_understanding | 71.4 | — |
| CharXiv (RQ) 1/2 models | document_understanding | 78 | — |
| GDP.pdf 1/2 models | long_context | 6.6 | — |
| BrowseComp 1/2 models | general_agent | 62 | — |
| MMLU-Redux 1/2 models | knowledge | 93.3 | — |
| ParseBench Text Content 1/2 models | document_understanding | 90.7 | — |
| MCPMark 1/2 models | general_agent | 37 | — |
| AA-Omniscience Index (public set) 1/2 models | knowledge | -7.2 | — |
| MLVU 1/2 models | video_understanding | 86.2 | — |
| IFBench 1/2 models | instruction_following | 66.6 | — |
| IMOAnswerBench 1/2 models | stem_reasoning | 78.9 | — |
| Humanity's Last Exam 1/2 models | stem_reasoning | 21.4 | — |
| CountBench 1/2 models | spatial_intelligence | 96.1 | — |
| ERQA 1/2 models | spatial_intelligence | 61.8 | — |
| VideoMME (w/o sub.) 1/2 models | video_understanding | 82.5 | — |
| Terminal-Bench 2.0 1/2 models | coding_agent | 51.5 | — |
| DeepPlanning 1/2 models | general_agent | 25.9 | — |
| QwenWebBench 1/2 models | coding_agent | 1397 | — |
| ODInW13 1/2 models | spatial_intelligence | 50.8 | — |
| VlmsAreBlind 1/2 models | vision_language | 96.6 | — |
| DeepSWE 1/2 models | coding_agent | 0 | — |
| OmniDocBench 1.5 1/2 models | document_understanding | 89.9 | — |
| HallusionBench 1/2 models | vision_language | 69.8 | — |
| OCRBench 1/2 models | document_understanding | 90 | — |
| HMMT Feb 26 1/2 models | stem_reasoning | 83.6 | — |
| Terminal-Bench Lite 1/2 models | coding_agent | 63.3 | — |
| CC-OCR 1/2 models | document_understanding | 81.9 | — |
| RefCOCO (avg) 1/2 models | spatial_intelligence | 92 | — |
| Artificial Analysis Intelligence Index 1/2 models | composite | 32 | — |
| Tool Decathlon 1/2 models | general_agent | 26.9 | — |
| Frontier-Bench v0.1 1/2 models | coding_agent | 1.4 | — |
| ParseBench Mean 1/2 models | document_understanding | 44.1 | — |
| ZEROBench_sub 1/2 models | vision_language | 34.4 | — |
| C-Eval 1/2 models | knowledge | 90 | — |
| WideSearch 1/2 models | general_agent | 60.1 | — |
| SimpleVQA 1/2 models | vision_language | 58.9 | — |
| VideoMME (w sub.) 1/2 models | video_understanding | 86.6 | — |
| SkillsBench Avg5 1/2 models | coding_agent | 28.7 | — |
| Claw-Eval Pass^3 1/2 models | coding_agent | 50 | — |
| MCP-Atlas 1/2 models | general_agent | 62.8 | — |
| V-Star 1/2 models | vision_language | 90.1 | — |
| Chatbot Korean (internal) 1/2 models | multilingual | 74.5 | — |
| SciCode 1/2 models | — | 35.6 | — |
| RefSpatialBench 1/2 models | spatial_intelligence | 64.3 | — |
| BrowseComp Plus 1/2 models | general_agent | 34.8 | — |
| MMMU 1/2 models | vision_language | 81.7 | — |
| MVBench 1/2 models | video_understanding | 74.6 | — |
Comparison FAQ
Which model is better, Ornith-1.0-35B or Qwen3.6-35B-A3B?
Ornith-1.0-35B wins this comparison with an overall score of 82 vs 55 for Qwen3.6-35B-A3B, leading 10 of 10 shared benchmarks.
Which model is better at Agentic Coding, Ornith-1.0-35B or Qwen3.6-35B-A3B?
Ornith-1.0-35B leads the Agentic Coding category (strength score 100/100 across 10 comparable benchmarks).
How reliable is this comparison verdict?
Based on 10 of 85 benchmarks scored by all 2 selected models.