# Ornith-1.5-397B vs Beam 1.0 501B-A23B FP8

> Side-by-side benchmark comparison for Ornith-1.5-397B and Beam 1.0 501B-A23B FP8 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/ornith-1-5-397b-vs-reflection-beam-fp8
- Last updated: October 16, 2026

- Shared sourced benchmarks: 11
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Beam 1.0 501B-A23B FP8 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Beam 1.0 501B-A23B FP8 has the higher overall point estimate 71 to 62.33. Conditional score ranges do not establish rank confidence.
- The biggest single benchmark swing is DeepSWE in Coding, with scores of 56.0% and 43.0%.
- Beam 1.0 501B-A23B FP8 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Beam 1.0 501B-A23B FP8 also has the larger context window at 1M.

## Model Snapshot

| Property | Ornith-1.5-397B | Beam 1.0 501B-A23B FP8 |
|----------|----------|----------|
| Creator | Ornith AI | Reflection AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 1M |
| Overall Score | 62.33 | null |
| Benchmarks Covered | 18 | 19 |
| Pricing (input/output) | $0.00 / $0.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Ornith-1.5-397B public-lane score: 58.6 (Estimated · #32/128)
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Ornith-1.5-397B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 86.1% | 78.9% | Ornith-1.5-397B |
| HLE w/ tools | 56.1% | 51.1% | Ornith-1.5-397B |
| MCP Atlas | 80% | 81.5% | Beam 1.0 501B-A23B FP8 |
| Toolathlon-Verified | 71.2% | Coming soon | Coming soon |
| WideResearch | 80.8% | Coming soon | Coming soon |
| BrowseComp | 86.6% | 76.7% | Ornith-1.5-397B |
| Claw-Eval | 81.4% | Coming soon | Coming soon |
| τ³-bench results | Coming soon | 36.8% | Coming soon |
| DeepSearchQA | Coming soon | 79.6% | Coming soon |

### Coding

- Winner: Not comparable
- Ornith-1.5-397B public-lane score: 53.4 (Estimated · #36/150)
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Ornith-1.5-397B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 86.1% | 78.9% | Ornith-1.5-397B |
| SWE-bench Verified | 86% | 80.2% | Ornith-1.5-397B |
| SWE-bench Pro | 65.1% | 65.9% | Beam 1.0 501B-A23B FP8 |
| SWE Multilingual | 79.6% | 78.1% | Ornith-1.5-397B |
| DeepSWE | 56.0% | 43.0% | Ornith-1.5-397B |
| frontierBench | 13.5% | Coming soon | Coming soon |
| NL2Repo | 59.5% | Coming soon | Coming soon |
| SWE-Atlas Codebase QnA | Coming soon | 32.2% | Coming soon |
| SciCode | Coming soon | 48.3% | Coming soon |

### Reasoning

- Winner: Not comparable
- Ornith-1.5-397B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: 85.8 (Unranked · 3 rankable rows)

| Benchmark | Ornith-1.5-397B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| CritPt | Coming soon | 17.4% | Coming soon |
| LongBench v2 | Coming soon | 67.6% | Coming soon |

### Knowledge

- Winner: Not comparable
- Ornith-1.5-397B public-lane score: 64.6 (Estimated · #39/184)
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Ornith-1.5-397B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 92.8% | Coming soon | Coming soon |
| GPQA-D | 92.8% | 90.3% | Ornith-1.5-397B |
| HLE | 44.6% | Coming soon | Coming soon |
| HLE w/o tools | 44.6% | 36% | Ornith-1.5-397B |

### Instruction Following

- Winner: Not comparable
- Ornith-1.5-397B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: 89.8 (#28/148)

| Benchmark | Ornith-1.5-397B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 80.7% | Coming soon |

### Mathematics

- Winner: Not comparable
- Ornith-1.5-397B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: 87.9 (Unranked · 1 rankable row)

| Benchmark | Ornith-1.5-397B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | Coming soon | 98.0% | Coming soon |

## FAQ

### Which is better overall, Ornith-1.5-397B or Beam 1.0 501B-A23B FP8?

Beam 1.0 501B-A23B FP8 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### How many benchmarks does Ornith-1.5-397B cover on BenchLM?

Ornith-1.5-397B currently has 18 sourced benchmark scores on BenchLM.

### How many benchmarks does Beam 1.0 501B-A23B FP8 cover on BenchLM?

Beam 1.0 501B-A23B FP8 currently has 19 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Ornith-1.5-397B vs Ornith-1.5-35B-A3B](/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-397b)
- [Beam 1.0 501B-A23B FP8 vs Ornith-1.5-35B-A3B](/compare/ornith-1-5-35b-a3b-vs-reflection-beam-fp8)
- [Ornith-1.5-397B vs Ornith-1.5-9B](/compare/ornith-1-5-397b-vs-ornith-1-5-9b)
- [Beam 1.0 501B-A23B FP8 vs Ornith-1.5-9B](/compare/ornith-1-5-9b-vs-reflection-beam-fp8)

## Explore More

- [Ornith-1.5-397B profile](/models/ornith-1-5-397b)
- [Beam 1.0 501B-A23B FP8 profile](/models/reflection-beam-fp8)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)