# GPT-5.4 mini vs Ornith-1.5-9B

> Side-by-side benchmark comparison for GPT-5.4 mini and Ornith-1.5-9B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-4-mini-vs-ornith-1-5-9b
- Last updated: October 2, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

GPT-5.4 mini leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- GPT-5.4 mini has the higher overall point estimate 55.64 to 28.63. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in knowledge, where the averages are 48.6 for GPT-5.4 mini and 30.6 for Ornith-1.5-9B.
- The biggest single benchmark swing is HLE in Knowledge, with scores of 41.5% and 20.2%.
- Ornith-1.5-9B is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GPT-5.4 mini also has the larger context window at 400K.

## Model Snapshot

| Property | GPT-5.4 mini | Ornith-1.5-9B |
|----------|----------|----------|
| Creator | OpenAI | Ornith AI |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 400K | 262K |
| Overall Score | 55.64 | 28.63 |
| Benchmarks Covered | 21 | 16 |
| Pricing (input/output) | $0.75 / $4.50 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- GPT-5.4 mini public-lane score: 34.1 (Supported · #73/119)
- Ornith-1.5-9B public-lane score: 18 (Estimated · #101/119)

| Benchmark | GPT-5.4 mini | Ornith-1.5-9B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 60% | Coming soon | Coming soon |
| OSWorld-Verified | 72.1% | Coming soon | Coming soon |
| MCP Atlas | 57.7% | 54.2% | GPT-5.4 mini |
| Toolathlon | 42.9% | Coming soon | Coming soon |
| τ²-bench results | 93.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 54.7% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 46.2% | Coming soon |
| HLE w/ tools | Coming soon | 30.5% | Coming soon |
| Toolathlon-Verified | Coming soon | 41.2% | Coming soon |
| WideResearch | Coming soon | 59.5% | Coming soon |
| BrowseComp | Coming soon | 56.4% | Coming soon |
| Claw-Eval | Coming soon | 66.5% | Coming soon |

### Coding

- Winner: Not comparable
- GPT-5.4 mini public-lane score: 36.9 (Supported · #73/144)
- Ornith-1.5-9B public-lane score: Coming soon

| Benchmark | GPT-5.4 mini | Ornith-1.5-9B | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 47.97% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 27.0% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 81.5% | Coming soon | Coming soon |
| SWE-bench (Vals) | 73.0% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 46.2% | Coming soon |
| SWE-bench Verified | Coming soon | 70.6% | Coming soon |
| SWE-bench Pro | Coming soon | 47.5% | Coming soon |
| SWE Multilingual | Coming soon | 54.4% | Coming soon |
| NL2Repo | Coming soon | 32.4% | Coming soon |

### Reasoning

- Winner: Not comparable
- GPT-5.4 mini public-lane score: 40 (Unranked · 4 rankable rows)
- Ornith-1.5-9B public-lane score: Coming soon

| Benchmark | GPT-5.4 mini | Ornith-1.5-9B | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | 63.70% | Coming soon | Coming soon |
| ARC-AGI-2 | 18.9% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- GPT-5.4 mini public-lane score: 58.3 (#32/49)
- Ornith-1.5-9B public-lane score: Coming soon

| Benchmark | GPT-5.4 mini | Ornith-1.5-9B | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 76.6% | Coming soon | Coming soon |
| MMMU-Pro w/ Python | 78% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- GPT-5.4 mini public-lane score: 48.6 (Supported · #70/171)
- Ornith-1.5-9B public-lane score: 30.6 (Estimated · #134/171)

| Benchmark | GPT-5.4 mini | Ornith-1.5-9B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 88% | 86.4% | GPT-5.4 mini |
| HLE | 41.5% | 20.2% | GPT-5.4 mini |
| HLE w/o tools | 28.2% | 20.2% | GPT-5.4 mini |
| GPQA Diamond (Vals) | 83.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 84.6% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 86.4% | Coming soon |

### Instruction Following

- Winner: Not comparable
- GPT-5.4 mini public-lane score: 88.5 (#24/125)
- Ornith-1.5-9B public-lane score: Coming soon

### Mathematics

- Winner: Not comparable
- GPT-5.4 mini public-lane score: 44.3 (Unranked · 2 rankable rows)
- Ornith-1.5-9B public-lane score: Coming soon

| Benchmark | GPT-5.4 mini | Ornith-1.5-9B | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 28.280% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 2.080% | Coming soon | Coming soon |

## FAQ

### Which is better overall, GPT-5.4 mini or Ornith-1.5-9B?

GPT-5.4 mini has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between GPT-5.4 mini and Ornith-1.5-9B?

The widest category gap is in knowledge, where the averages are 48.6 for GPT-5.4 mini and 30.6 for Ornith-1.5-9B.

### How many benchmarks does GPT-5.4 mini cover on BenchLM?

GPT-5.4 mini currently has 21 sourced benchmark scores on BenchLM.

### How many benchmarks does Ornith-1.5-9B cover on BenchLM?

Ornith-1.5-9B currently has 16 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GPT-5.4 mini vs GPT-5.4 Pro](/compare/gpt-5-4-mini-vs-gpt-5-4-pro)
- [Ornith-1.5-9B vs GPT-5.4 Pro](/compare/gpt-5-4-pro-vs-ornith-1-5-9b)
- [GPT-5.4 mini vs GPT-5.4](/compare/gpt-5-4-vs-gpt-5-4-mini)
- [Ornith-1.5-9B vs GPT-5.4](/compare/gpt-5-4-vs-ornith-1-5-9b)

## Explore More

- [GPT-5.4 mini profile](/models/gpt-5-4-mini)
- [Ornith-1.5-9B profile](/models/ornith-1-5-9b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)