# DeepSeek V4 Pro vs Ornith-1.5-35B-A3B

> Side-by-side benchmark comparison for DeepSeek V4 Pro and Ornith-1.5-35B-A3B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/deepseek-v4-pro-vs-ornith-1-5-35b-a3b
- Last updated: November 18, 2026

- Shared sourced benchmarks: 14
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

DeepSeek V4 Pro leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- DeepSeek V4 Pro has the higher overall point estimate 62.71 to 33. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in coding, where the averages are 51.4 for DeepSeek V4 Pro and 23.9 for Ornith-1.5-35B-A3B.
- The biggest single benchmark swing is DeepSWE in Coding, with scores of 62.7% and 22.0%.
- Ornith-1.5-35B-A3B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- DeepSeek V4 Pro also has the larger context window at 1M.

## Model Snapshot

| Property | DeepSeek V4 Pro | Ornith-1.5-35B-A3B |
|----------|----------|----------|
| Creator | DeepSeek | Ornith AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 262K |
| Overall Score | 62.71 | 33 |
| Benchmarks Covered | 45 | 18 |
| Pricing (input/output) | $1.32 / $3.96 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 57 (Supported · #41/138)
- Ornith-1.5-35B-A3B public-lane score: 30 (Estimated · #112/138)

| Benchmark | DeepSeek V4 Pro | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.1 | 6.70% | Coming soon | Coming soon |
| Finch | 67.4% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 67.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 87.9% | 67.8% | DeepSeek V4 Pro |
| BrowseComp | 83.4% | 67.6% | DeepSeek V4 Pro |
| HLE w/ tools | 60.0% | 33.4% | DeepSeek V4 Pro |
| MCP Atlas | 73.6% | 70.2% | DeepSeek V4 Pro |
| Toolathlon | 51.8% | Coming soon | Coming soon |
| CyberGym | 83.3% | Coming soon | Coming soon |
| Toolathlon-Verified | 74.1% | 48.7% | DeepSeek V4 Pro |
| Agents' Last Exam | 25.7% | Coming soon | Coming soon |
| AutomationBench | 31.8% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 54.7% | Coming soon | Coming soon |
| WideResearch | Coming soon | 67.8% | Coming soon |
| Claw-Eval | Coming soon | 72.5% | Coming soon |

### Coding

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 51.4 (Supported · #41/160)
- Ornith-1.5-35B-A3B public-lane score: 23.9 (Estimated · #127/160)

| Benchmark | DeepSeek V4 Pro | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench Pass@1-COT | 93.5% | Coming soon | Coming soon |
| Codeforces | 3206.0 | Coming soon | Coming soon |
| SWE-bench Verified | 80.6% | 79% | DeepSeek V4 Pro |
| SWE-bench Pro | 55.4% | 59.6% | Ornith-1.5-35B-A3B |
| SWE Multilingual | 76.2% | 71.4% | DeepSeek V4 Pro |
| Terminal-Bench 2.0 | 67.9% | Coming soon | Coming soon |
| Vibe Code Bench | 49.93% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 87.9% | 67.8% | DeepSeek V4 Pro |
| NL2Repo | 61.5% | 46.2% | DeepSeek V4 Pro |
| DeepSWE | 62.7% | 22.0% | DeepSeek V4 Pro |
| DSBench-FullStack | 71.1% | Coming soon | Coming soon |
| DSBench-Hard | 67.2% | Coming soon | Coming soon |
| OpenHarmony Bench v1.0 | 59.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 96.4% | Coming soon | Coming soon |
| frontierBench | Coming soon | 5.1% | Coming soon |

### Reasoning

- Winner: Not comparable
- DeepSeek V4 Pro public-lane score: 58.1 (Supported · #33/159)
- Ornith-1.5-35B-A3B public-lane score: Coming soon

| Benchmark | DeepSeek V4 Pro | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MRCR 1M | 83.5% | Coming soon | Coming soon |
| CorpusQA 1M | 62.0% | Coming soon | Coming soon |
| ARC-AGI-1 | 90.00% | Coming soon | Coming soon |
| ARC-AGI-2 | 61.3% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- DeepSeek V4 Pro public-lane score: 64.2 (Supported · #35/179)
- Ornith-1.5-35B-A3B public-lane score: 37.2 (Estimated · #124/179)

| Benchmark | DeepSeek V4 Pro | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 87.5% | Coming soon | Coming soon |
| Chinese-SimpleQA | 84.4% | Coming soon | Coming soon |
| GPQA | 90.1% | 89.2% | DeepSeek V4 Pro |
| GPQA-D | 90.1% | 89.2% | DeepSeek V4 Pro |
| HLE | 42.7% | 25.6% | DeepSeek V4 Pro |
| GPQA Diamond (Vals) | 92.4% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.0% | Coming soon | Coming soon |
| HLE w/o tools | Coming soon | 25.6% | Coming soon |

### Instruction Following

- Winner: Not comparable
- DeepSeek V4 Pro public-lane score: 93.8 (#7/157)
- Ornith-1.5-35B-A3B public-lane score: Coming soon

### Mathematics

- Winner: Not comparable
- DeepSeek V4 Pro public-lane score: 73.9 (#4/13)
- Ornith-1.5-35B-A3B public-lane score: Coming soon

| Benchmark | DeepSeek V4 Pro | Ornith-1.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| HMMT Feb 2026 | 95.2% | Coming soon | Coming soon |
| IMOAnswerBench | 89.8% | Coming soon | Coming soon |
| Apex | 38.3% | Coming soon | Coming soon |
| Apex Shortlist | 90.2% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 64.561% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 26.829% | Coming soon | Coming soon |

## FAQ

### Which is better overall, DeepSeek V4 Pro or Ornith-1.5-35B-A3B?

DeepSeek V4 Pro has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between DeepSeek V4 Pro and Ornith-1.5-35B-A3B?

The widest category gap is in coding, where the averages are 51.4 for DeepSeek V4 Pro and 23.9 for Ornith-1.5-35B-A3B.

### How many benchmarks does DeepSeek V4 Pro cover on BenchLM?

DeepSeek V4 Pro currently has 45 sourced benchmark scores on BenchLM.

### How many benchmarks does Ornith-1.5-35B-A3B cover on BenchLM?

Ornith-1.5-35B-A3B currently has 18 sourced benchmark scores on BenchLM.

## Related Comparisons

- [DeepSeek V4 Pro vs Ornith-1.5-397B](/compare/deepseek-v4-pro-vs-ornith-1-5-397b)
- [Ornith-1.5-35B-A3B vs Ornith-1.5-397B](/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-397b)
- [DeepSeek V4 Pro vs Ornith-1.5-9B](/compare/deepseek-v4-pro-vs-ornith-1-5-9b)
- [Ornith-1.5-35B-A3B vs Ornith-1.5-9B](/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-9b)

## Explore More

- [DeepSeek V4 Pro profile](/models/deepseek-v4-pro)
- [Ornith-1.5-35B-A3B profile](/models/ornith-1-5-35b-a3b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)
