# Beam 1.0 501B-A23B vs Beam 1.0 501B-A23B FP8

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

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

- Shared sourced benchmarks: 19
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Beam 1.0 501B-A23B if you want the stronger benchmark profile. Beam 1.0 501B-A23B FP8 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Beam 1.0 501B-A23B leads overall 73 to 71.
- The clearest category separation is in reasoning, where the averages are 79.6 for Beam 1.0 501B-A23B and 85.8 for Beam 1.0 501B-A23B FP8.
- The biggest single benchmark swing is SWE-bench Verified in Coding, with scores of 81.6% and 80.2%.

## Model Snapshot

| Property | Beam 1.0 501B-A23B | Beam 1.0 501B-A23B FP8 |
|----------|----------|----------|
| Creator | Reflection AI | Reflection AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | null | null |
| Benchmarks Covered | 19 | 19 |
| Pricing (input/output) | Pricing unavailable / Pricing unavailable | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Beam 1.0 501B-A23B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Beam 1.0 501B-A23B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| τ³-bench results | 36.1% | 36.8% | Beam 1.0 501B-A23B FP8 |
| HLE w/ tools | 51.1% | 51.1% | Tie |
| Terminal-Bench 2.1 | 80.1% | 78.9% | Beam 1.0 501B-A23B |
| MCP Atlas | 80.8% | 81.5% | Beam 1.0 501B-A23B FP8 |
| BrowseComp | 76.8% | 76.7% | Beam 1.0 501B-A23B |
| DeepSearchQA | 80.5% | 79.6% | Beam 1.0 501B-A23B |

### Coding

- Winner: Not comparable
- Beam 1.0 501B-A23B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Beam 1.0 501B-A23B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| DeepSWE | 43.3% | 43.0% | Beam 1.0 501B-A23B |
| SWE-bench Pro | 66.1% | 65.9% | Beam 1.0 501B-A23B |
| Terminal-Bench 2.1 | 80.1% | 78.9% | Beam 1.0 501B-A23B |
| SWE-Atlas Codebase QnA | 31.8% | 32.2% | Beam 1.0 501B-A23B FP8 |
| SWE Multilingual | 78.3% | 78.1% | Beam 1.0 501B-A23B |
| SWE-bench Verified | 81.6% | 80.2% | Beam 1.0 501B-A23B |
| SciCode | 49.2% | 48.3% | Beam 1.0 501B-A23B |

### Reasoning

- Winner: Not comparable
- Beam 1.0 501B-A23B public-lane score: 79.6 (Unranked · 2 rankable rows)
- Beam 1.0 501B-A23B FP8 public-lane score: 85.8 (Unranked · 3 rankable rows)

| Benchmark | Beam 1.0 501B-A23B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| CritPt | 16.3% | 17.4% | Beam 1.0 501B-A23B FP8 |
| LongBench v2 | 67.5% | 67.6% | Beam 1.0 501B-A23B FP8 |

### Knowledge

- Winner: Not comparable
- Beam 1.0 501B-A23B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Beam 1.0 501B-A23B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| GPQA-D | 90.6% | 90.3% | Beam 1.0 501B-A23B |
| HLE w/o tools | 36% | 36% | Tie |

### Instruction Following

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

| Benchmark | Beam 1.0 501B-A23B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 79.6% | 80.7% | Beam 1.0 501B-A23B FP8 |

### Mathematics

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

| Benchmark | Beam 1.0 501B-A23B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 97.7% | 98.0% | Beam 1.0 501B-A23B FP8 |

## FAQ

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

Beam 1.0 501B-A23B is ahead overall on BenchLM right now.

### Where is the biggest gap between Beam 1.0 501B-A23B and Beam 1.0 501B-A23B FP8?

The widest category gap is in reasoning, where the averages are 79.6 for Beam 1.0 501B-A23B and 85.8 for Beam 1.0 501B-A23B FP8.

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

Beam 1.0 501B-A23B currently has 19 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

- [Beam 1.0 501B-A23B vs Beam 1.0 501B-A23B NVFP4](/compare/reflection-beam-vs-reflection-beam-nvfp4)
- [Beam 1.0 501B-A23B FP8 vs Beam 1.0 501B-A23B NVFP4](/compare/reflection-beam-fp8-vs-reflection-beam-nvfp4)
- [Beam 1.0 501B-A23B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-reflection-beam)
- [Beam 1.0 501B-A23B FP8 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-reflection-beam-fp8)

## Explore More

- [Beam 1.0 501B-A23B profile](/models/reflection-beam)
- [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)