# Beam 1.0 501B-A23B

Reflection AI · Open Weight · rank 107 · bench-align-v5

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/models/reflection-beam  
JSON: https://modelchoice.dev/api/model/reflection-beam

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `reflection-beam` | — |
| Overall score | 46.9 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 68 | Observed 2026-11-21 · source benchlm:models |
| Context window | 1M tokens | Observed 2026-11-21 · source benchlm:models |
| Release date | 2026-10-16 | Observed 2026-11-21 · source benchlm:models |
| Access type | Open Weight | — |
| Blended $/1M (75% input / 25% output) | Unavailable | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero. Beside each score is BenchLM's separate verified score for that axis; the two are published side by side and are not interchangeable.

| Axis | Score | Evidence | Verified (BenchLM) | Verified evidence |
| --- | --- | --- | --- | --- |
| Agentic | Unavailable | Unavailable · source benchlm:models | 60.5 | Observed 2026-11-21 · source benchlm:models |
| Coding | Unavailable | Unavailable · source benchlm:models | 64.9 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 48.8 | Observed 2026-11-21 · source benchlm:models | 54.2 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 77.9 | Observed 2026-11-21 · source benchlm:models | 79.1 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models | 88 | Observed 2026-11-21 · source benchlm:models |
| Math | Unavailable | Unavailable · source benchlm:models | 84.6 | Observed 2026-11-21 · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | 9.56 s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |
| Throughput | 259 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Output / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache read / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | Unavailable | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Unavailable · source livebench:table |

**Pricing note.** Reflection publishes downloadable Apache 2.0 weights and, per the October 16, 2026 launch post, serves Beam-1.0-501B-A23B through its API in public beta, free to start. No per-token tariff is published; the account-gated platform pricing page shows none. Hardware costs for self-hosting are separate. The model id and request limits are documented on the developer Models page.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | Unavailable |
| Modelled tokens | Unavailable |
| Reason | The applicable input rate is unavailable. |

## Benchmark record

41 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA-D (GPQA Diamond) | 90.6 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| Artificial Analysis Intelligence Index | 17.7 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-HLE (Artificial Analysis Humanity's Last Exam) | 34.7 | Expert-level questions | Frontier expert reasoning | [Artificial Analysis Humanity's Last Exam Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/hle) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | 2.3 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 30.7 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 41.0 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| HLE w/o tools (Humanity's Last Exam without tools) | 36 | Expert-level questions | Frontier expert level | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.1 | 80.1 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 81.6 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| SWE-bench Pro | 66.1 | 1,865 repository problems | Long-horizon professional engineering | [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://arxiv.org/abs/2509.16941) |
| SWE Multilingual | 78.3 | Multilingual software-engineering tasks | Professional software engineering | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| SWE-Atlas Codebase QnA | 31.8 | 124 codebase questions across 11 repositories | Production codebase comprehension | [Muse Spark 1.3 Evaluation Methodology](https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology) |
| SciCode (Scientific Code Benchmark) | 49.2 | — | — | [BenchLM](https://benchlm.ai/benchmarks/scicode) |
| AA-SciCode (Artificial Analysis SciCode) | 48.5 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |
| DeepSWE | 43.3 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | [DeepSWE benchmark blog](https://deepswe.datacurve.ai/blog) |
| VulcanBench Frontier v4 | 64.7 | 23 behavioural-reconstruction coding tasks | Professional multi-file software engineering | [VulcanBench Frontier v4 leaderboard](https://vulcanbench.com/leaderboard.html) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AIME26 (AIME 2026) | 97.7 | Competition math problems | Olympiad-style mathematics | [Qwen3.6 launch benchmarks](https://qwen.ai/blog?id=qwen3.6) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| LongBench v2 | 67.5 | Long-context tasks | Hard long-context | [LongBench v2](https://arxiv.org/abs/2412.15204) |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 78.2 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| MLCR-AA (Medical Long Context Reasoning (MLCR-AA)) | 17.8 | Long, fragmented medical-record reasoning | Long-context medical reasoning | [Medical Long Context Reasoning (MLCR-AA)](https://artificialanalysis.ai/evaluations/mlcr-aa) |
| CritPt (Critical Physics Tasks) | 16.3 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| IFBench (Instruction Following Benchmark) | 79.6 | — | — | [BenchLM](https://benchlm.ai/benchmarks/ifbench) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA Briefcase (Artificial Analysis Briefcase) | 976 | Professional knowledge-work tasks | Professional work | [Artificial Analysis Briefcase Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) |
| AA AutomationBench (Artificial Analysis AutomationBench) | 48.5 | Business-process automation tasks | Agentic automation | [Artificial Analysis AutomationBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) |
| Terminal-Bench 2.1 | 80.1 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| BrowseComp | 76.8 | Research questions requiring browsing | Hard web research | [BrowseComp](https://openai.com/index/browsecomp/) |
| HLE w/ tools (Humanity's Last Exam with tools) | 51.1 | Expert questions with tool use | Frontier tool-augmented reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA | 1177 | Agentic real-world work tasks | Professional agentic workflows | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA (GDPval-AA normalized) | 33.9 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Terminal-Bench 4.0 (Artificial Analysis Terminal-Bench v4.0) | 3.0 | Terminal-based agent tasks | Agentic software engineering | [Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/terminalbench-v4-0) |
| GDP.pdf (Artificial Analysis GDP.pdf) | 11.6 | Professional document-production tasks | Professional knowledge work | [GDP.pdf Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) |
| MCP Atlas | 80.8 | Tool-integrated agent tasks | Advanced tool use | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| DeepSearchQA | 80.5 | Agentic browsing and list-answer questions | Agentic web research | [Muse Spark Eval Methodology](https://ai.meta.com/static-resource/muse-spark-eval-methodology) |
| τ³-bench results (τ³-Bench Tool-Agent-User Evaluation) | 36.1 | Corrected customer-service tasks plus knowledge and voice evaluation modes | Long-horizon, multimodal, and knowledge-aware tool use | [Official τ³-bench repository and release notes](https://github.com/sierra-research/tau2-bench) |
| Terminal-Bench 4.1 | 6.40 | 66 professional computer-work tasks | Frontier autonomous knowledge work | [Terminal-Bench 4.1](https://www.tbench.ai/news/terminal-bench-4-1) |
| AA Cyber Index (Artificial Analysis Cyber Index) | 33.7 | Three defensive cybersecurity evaluations | Real-world vulnerability discovery and patching | [Artificial Analysis Cyber Index](https://artificialanalysis.ai/evaluations/artificial-analysis-cyber-index) |
| CWE-Bench-AA (Artificial Analysis CWE-Bench-AA) | 49.2 | Real-world vulnerability patching tasks | Automated vulnerability remediation | [CWE-Bench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/cwe-bench-aa) |
| DeepsecBench-AA (Artificial Analysis DeepsecBench-AA) | 6.9 | Vulnerability discovery in real codebases | Security code review | [DeepsecBench-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/deepsecbench-aa) |
| CyberGym-E2E-AA (Artificial Analysis CyberGym-E2E-AA) | 45.0 | 131 end-to-end vulnerability reproduction and patching tasks | Real-world cybersecurity | [CyberGym-E2E-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/cybergym-e2e-aa) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Design Arena Website (Design Arena Website Elo) | 1232 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| StealthMark (StealthMark Intelligence Benchmarks (overall score)) | 31.9 | 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon | Chained physical reasoning, planning without tools and precise visual construction | [StealthMark: The AI Benchmark Explained (Stealth Models)](https://stealthmodels.com/stealthmark) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

No lifecycle event references this model. That is not evidence the model has no lifecycle plan — only that this source published none.

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-11-21 04:17 UTC.
