# Agents-A1-4B vs Beam 1.0 501B-A23B FP8

> Side-by-side benchmark comparison for Agents-A1-4B and Beam 1.0 501B-A23B FP8 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/agents-a1-4b-vs-reflection-beam-fp8
- Last updated: October 16, 2026

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

## Quick Verdict

Pick Beam 1.0 501B-A23B FP8 if you want the stronger benchmark profile. Agents-A1-4B 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 FP8 leads overall 71 to 0.
- The biggest single benchmark swing is SciCode in Coding, with scores of 29.6% and 48.3%.
- 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 | Agents-A1-4B | Beam 1.0 501B-A23B FP8 |
|----------|----------|----------|
| Creator | InternScience | Reflection AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 1M |
| Overall Score | null | null |
| Benchmarks Covered | 11 | 19 |
| Pricing (input/output) | $0.00 / $0.00 | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Agents-A1-4B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Agents-A1-4B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| BrowseComp | 66.8% | 76.7% | Beam 1.0 501B-A23B FP8 |
| GAIA | 95.1% | Coming soon | Coming soon |
| MLE-Bench Lite | 22.7% | Coming soon | Coming soon |
| τ²-bench results | 78.2% | Coming soon | Coming soon |
| VITA-Bench | 40.3% | Coming soon | Coming soon |
| τ³-bench results | Coming soon | 36.8% | Coming soon |
| HLE w/ tools | Coming soon | 51.1% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 78.9% | Coming soon |
| MCP Atlas | Coming soon | 81.5% | Coming soon |
| DeepSearchQA | Coming soon | 79.6% | Coming soon |

### Coding

- Winner: Not comparable
- Agents-A1-4B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Agents-A1-4B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| SciCode | 29.6% | 48.3% | Beam 1.0 501B-A23B FP8 |
| LiveCodeBench v6 | 59.6% | Coming soon | Coming soon |
| DeepSWE | Coming soon | 43.0% | Coming soon |
| SWE-bench Pro | Coming soon | 65.9% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 78.9% | Coming soon |
| SWE-Atlas Codebase QnA | Coming soon | 32.2% | Coming soon |
| SWE Multilingual | Coming soon | 78.1% | Coming soon |
| SWE-bench Verified | Coming soon | 80.2% | Coming soon |

### Reasoning

- Winner: Not comparable
- Agents-A1-4B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: 85.8 (Unranked · 3 rankable rows)

| Benchmark | Agents-A1-4B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 52.1% | 67.6% | Beam 1.0 501B-A23B FP8 |
| CritPt | Coming soon | 17.4% | Coming soon |

### Knowledge

- Winner: Not comparable
- Agents-A1-4B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: Coming soon

| Benchmark | Agents-A1-4B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| FrontierScience Research | 33.3% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 90.3% | Coming soon |
| HLE w/o tools | Coming soon | 36% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Agents-A1-4B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: 89.8 (#28/148)

| Benchmark | Agents-A1-4B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 69.1% | 80.7% | Beam 1.0 501B-A23B FP8 |
| IFEval | 94.8% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Agents-A1-4B public-lane score: Coming soon
- Beam 1.0 501B-A23B FP8 public-lane score: 87.9 (Unranked · 1 rankable row)

| Benchmark | Agents-A1-4B | Beam 1.0 501B-A23B FP8 | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | Coming soon | 98.0% | Coming soon |

## FAQ

### Which is better overall, Agents-A1-4B or Beam 1.0 501B-A23B FP8?

Beam 1.0 501B-A23B FP8 is ahead overall on BenchLM right now.

### How many benchmarks does Agents-A1-4B cover on BenchLM?

Agents-A1-4B currently has 11 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

- [Agents-A1-4B vs Agents-A1](/compare/agents-a1-vs-agents-a1-4b)
- [Beam 1.0 501B-A23B FP8 vs Agents-A1](/compare/agents-a1-vs-reflection-beam-fp8)
- [Agents-A1-4B vs Agents-A1-F16-GGUF](/compare/agents-a1-4b-vs-agents-a1-f16-gguf)
- [Beam 1.0 501B-A23B FP8 vs Agents-A1-F16-GGUF](/compare/agents-a1-f16-gguf-vs-reflection-beam-fp8)

## Explore More

- [Agents-A1-4B profile](/models/agents-a1-4b)
- [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)