Model comparison
Ornith-1.0-397B vs ZAYA1-74B-Preview
Head-to-head evidence from 1 shared benchmark result across 1 category. Overall scores shown here use the public BenchAlign v5 ranking lane.
Evidence parity. Ornith-1.0-397B and ZAYA1-74B-Preview share 1 comparable benchmark result. 1 of 8 categories are comparable. 6 results are unique to Ornith-1.0-397B; 6 to ZAYA1-74B-Preview.
Updated July 18, 2026- Shared results
- 1
- Ornith-1.0-397B only
- 6
- ZAYA1-74B-Preview only
- 6
- Comparable categories
- 1 / 8
Treat this as a split decision. Ornith-1.0-397B makes more sense if coding is the priority; ZAYA1-74B-Preview is the better fit if its strengths line up with your actual workload.
Confidence note. This is a partial-evidence comparison with 1 shared benchmark result across 1 evidence category; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Ornith-1.0-397B and ZAYA1-74B-Preview finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
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-1.0-397B | Δ | ZAYA1-74B-Preview |
|---|---|---|---|
| Coding | Ornith-1.0-397B74.6 | Margin← 21.4 | ZAYA1-74B-Preview53.2 |
| Agentic | Ornith-1.0-397B77.5 | MarginNo overlap | ZAYA1-74B-PreviewNot measured |
| Knowledge | Ornith-1.0-397BNot measured | MarginNo overlap | ZAYA1-74B-Preview66.1 |
| Math | Ornith-1.0-397BNot measured | MarginNo overlap | ZAYA1-74B-Preview76.4 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 82.4%B 53.2%Winner: Ornith-1.0-397BΔ 29.2SWE-bench Verified: Ornith-1.0-397B scored 82.4%; ZAYA1-74B-Preview scored 53.2%. 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-1.0-397B | ZAYA1-74B-Preview | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Ornith-1.0-397B$0 input / $0 output | ZAYA1-74B-Preview$0 input / $0 output | Listed prices are equal. |
| Generation speedtokens per second | Ornith-1.0-397BNot available | ZAYA1-74B-PreviewNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Ornith-1.0-397BNot available | ZAYA1-74B-PreviewNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Ornith-1.0-397B256K | ZAYA1-74B-Preview256K | Listed context windows are equal. |
Benchmark Deep Dive
Agentic3 benchmarks
CodingOrnith-1.0-397B wins6 benchmarks
| Benchmark | Ornith-1.0-397B | ZAYA1-74B-Preview | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 82.4% | 53.2% | Ornith-1.0-397B leads |
| SWE-bench ProSource | 62.2% | — | Not comparable |
| SWE MultilingualSource | 78.9% | — | Not comparable |
| NL2RepoSource | 48.2% | — | Not comparable |
| Terminal-Bench 2.0Source | 77.5% | — | Not comparable |
| LiveCodeBench v6Source | — | 65.7% | Not comparable |
Knowledge3 benchmarks
Math1 benchmarks
| Benchmark | Ornith-1.0-397B | ZAYA1-74B-Preview | Result |
|---|---|---|---|
| AIME26Source | — | 76.4% | Not comparable |
Frequently Asked Questions (2)
Which is better, Ornith-1.0-397B or ZAYA1-74B-Preview?
Ornith-1.0-397B and ZAYA1-74B-Preview are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for coding, Ornith-1.0-397B or ZAYA1-74B-Preview?
Ornith-1.0-397B has the edge for coding in this comparison, averaging 74.6 versus 53.2. Inside this category, SWE-bench Verified 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.