# Beam Benchmark Scores & Performance

> Beam by Reflection AI has 16 source-displayable benchmark rows but no public overall score. It remains unranked.

Canonical page: https://benchlm.ai/models/reflection-beam

Last updated: October 5, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Reflection AI |
| Source Type | Pending |
| Reasoning Type | Reasoning |
| Context Window | Coming soon |
| Overall Score | Not computed (unranked) |
| Overall Rank | Unranked |

## Family & Coverage

- Family: Beam
- Variant: preview (Early access)
- Benchmarks covered: 16 of 649
- Coverage note: Published evidence is shown below; no public overall score is assigned.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 80.1% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [MCP Atlas](/benchmarks/mcpatlas) | 78.7% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [BrowseComp](/benchmarks/browsecomp) | 77.4% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [DeepSearchQA](/benchmarks/deepsearchqa) | 80.1% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [DeepSWE](/benchmarks/deepswe) | 44.4% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [SWE-bench Pro](/benchmarks/swe-bench-pro) | 65.5% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [Terminal-Bench 2.1](/benchmarks/terminalbench21) | 80.1% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [SWE-Atlas Codebase QnA](/benchmarks/swe-atlas-codebase-qna) | 34.6% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 78% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 80.9% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [SciCode](/benchmarks/scicode) | 49.7% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [LongBench v2](/benchmarks/longbench-v2) | 65.5% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA-D](/benchmarks/gpqa-diamond) | 90.5% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |
| [HLE w/o tools](/benchmarks/hlenotools) | 36.2% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [IFBench](/benchmarks/ifbench) | 79.7% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AIME26](/benchmarks/aime2026) | 97.8% | [Reflection AI Beam launch table](https://reflection.ai/blog/introducing-beam) |