Model comparison
Ornith-1.0-35B vs Ornith-1.0-397B
Head-to-head evidence from 7 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Sibling matchup inside the Ornith 1.0 family.
Evidence parity. Ornith-1.0-35B and Ornith-1.0-397B share 7 comparable benchmark results. 2 of 8 categories are comparable. 0 results are unique to Ornith-1.0-35B; 0 to Ornith-1.0-397B.
Updated July 17, 2026- Shared results
- 7
- Ornith-1.0-35B only
- 0
- Ornith-1.0-397B only
- 0
- Comparable categories
- 2 / 8
Ornith-1.0-35B makes more sense if you want this variant’s specific profile, while Ornith-1.0-397B is the cleaner fit if agentic is the priority.
Confidence note. This is a partial-evidence comparison with 7 shared benchmark results across 2 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Ornith-1.0-35B and Ornith-1.0-397B sit in the same Ornith 1.0 family. This page is less about two unrelated model lineages and more about how the siblings trade off on benchmark shape, token costs, and practical limits like context window.
Ornith-1.0-397B is clearly ahead on the BenchAlign aggregate, 72 to 62. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Ornith-1.0-397B's sharpest advantage is in agentic, where it averages 77.5 against 64.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 64.2% to 77.5%.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Ornith-1.0-35B | Δ | Ornith-1.0-397B |
|---|---|---|---|
| Agentic | Ornith-1.0-35B64.2 | Margin→ 13.3 | Ornith-1.0-397B77.5 |
| Coding | Ornith-1.0-35B65.9 | Margin→ 8.7 | Ornith-1.0-397B74.6 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 64.2%B 77.5%Winner: Ornith-1.0-397BΔ 13.3Terminal-Bench 2.0: Ornith-1.0-35B scored 64.2%; Ornith-1.0-397B scored 77.5%. Ornith-1.0-397B wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 50.4%B 62.2%Winner: Ornith-1.0-397BΔ 11.8SWE-bench Pro: Ornith-1.0-35B scored 50.4%; Ornith-1.0-397B scored 62.2%. Ornith-1.0-397B wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 75.6%B 82.4%Winner: Ornith-1.0-397BΔ 6.8SWE-bench Verified: Ornith-1.0-35B scored 75.6%; Ornith-1.0-397B scored 82.4%. Ornith-1.0-397B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Ornith-1.0-35B | Ornith-1.0-397B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Ornith-1.0-35B$0 input / $0 output | Ornith-1.0-397B$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | Ornith-1.0-35BNot available | Ornith-1.0-397BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Ornith-1.0-35BNot available | Ornith-1.0-397BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Ornith-1.0-35B256K | Ornith-1.0-397B256K | Listed context windows are equal. |
Benchmark Deep Dive
AgenticOrnith-1.0-397B wins2 benchmarks
CodingOrnith-1.0-397B wins5 benchmarks
| Benchmark | Ornith-1.0-35B | Ornith-1.0-397B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 75.6% | 82.4% | Ornith-1.0-397B leads |
| SWE-bench ProSource | 50.4% | 62.2% | Ornith-1.0-397B leads |
| SWE MultilingualSource | 69.3% | 78.9% | Ornith-1.0-397B leads |
| NL2RepoSource | 34.6% | 48.2% | Ornith-1.0-397B leads |
| Terminal-Bench 2.0Source | 64.2% | 77.5% | Ornith-1.0-397B leads |
Frequently Asked Questions (3)
Which is better, Ornith-1.0-35B or Ornith-1.0-397B?
Ornith-1.0-35B and Ornith-1.0-397B are sibling variants in the Ornith 1.0 family, so the right pick depends on whether you value the better benchmark line, cheaper tokens, or the larger context window. Ornith-1.0-397B is ahead on BenchLM's BenchAlign leaderboard 72 to 62.
Which is better for coding, Ornith-1.0-35B or Ornith-1.0-397B?
Ornith-1.0-397B has the edge for coding in this comparison, averaging 74.6 versus 65.9. Inside this category, NL2Repo is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Ornith-1.0-35B or Ornith-1.0-397B?
Ornith-1.0-397B has the edge for agentic tasks in this comparison, averaging 77.5 versus 64.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.