# Beam 1.0 - BenchAudit True Index Profile

**Integrity Profile: Clean Generalization**

> The Verdict: Performs Better on Fresh Private Evals Than Legacy Tests. Beam 1.0 (evaluated at default effort) outperforms its legacy benchmark standing (10.1p) when moved to private, leak-resistant evaluations (18.3p), posting a -3.7p Low-Tier Boost across 3 matched domains, particularly in Math & Scientific Reasoning (-10.0p boost)—a strong indicator of genuine generalization.

- **Canonical URL:** https://benchaudit.org/models/reflection-beam/
- **True Index Rank:** #41 of 44
- **Creator:** Reflection
- **Weights:** Open Weights
- **Clean Evals Avg (Tiers S & A):** 18.3p (8 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 10.1p (6 evals)
- **Low-Tier Boost (Matched Delta):** -3.7p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #42 | 8.2p | 2 |
| Coding & SWE | #42 | 5.4p | 3 |
| Math & Scientific Reasoning | #36 | 28.2p | 2 |

## Head-to-Head: Clean Evals vs. Legacy Benchmarks

| Capability Domain | Clean Evals (Tiers S & A) | Legacy Benchmarks (Tiers C & D) | Public Lift (Boost) |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | 2 (8.2p) | 2 (6.1p) | -2.1p |
| Coding & SWE | 3 (5.4p) | 1 (6.1p) | +0.7p |
| Math & Scientific Reasoning | 2 (28.2p) | 3 (18.2p) | -10.0p |

## Audited Benchmark Performance of Beam 1.0

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #30/46 | 38.8p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #33/47 | 31.6p |
| [Autoform-Hard](https://benchaudit.org/benchmarks/autoform-hard/) | Public / Aging | Math & Scientific Reasoning | #7/8 | 27.0p |
| [CritPt v2](https://benchaudit.org/benchmarks/critpt-v2/) | Private / Fresh | Math & Scientific Reasoning | #32/40 | 17.6p |
| [BioMysteryBench](https://benchaudit.org/benchmarks/biomysterybench/) | Public / Aging | Math & Scientific Reasoning | #23/23 | 16.9p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #42/50 | 16.3p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #44/50 | 12.2p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #38/41 | 10.7p |
| [Code2Video-AA](https://benchaudit.org/benchmarks/code2video-aa/) | Private / Fresh | Coding & SWE | #23/23 | 8.0p |
| [Code Migration v1.1](https://benchaudit.org/benchmarks/code-migration-v1-1/) | Private / Fresh | Coding & SWE | #23/24 | 7.6p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #46/49 | 6.2p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #47/50 | 6.1p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #46/46 | 0.7p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #50/50 | 0.0p |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #42/43 | 0.0p |
