Studio-level card: key art, verdict, results and case-file panels (28 Oct 2026)

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+panels/case.webp filter=lfs diff=lfs merge=lfs -text
+panels/results.webp filter=lfs diff=lfs merge=lfs -text
+panels/verdict.webp filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,63 +1,58 @@
----
-pipeline_tag: text-generation
-license: cc-by-4.0
-tags:
-  - cat-jam
-  - beam
-  - stealth-model
-  - stealthmark
-  - coding
-  - reasoning
-  - tool-use
-  - long-context
-thumbnail: https://stealthmodels.com/cat-jam/assets/social-card.png
-new_version: reflection/Beam-1.0-501B-A23B
----
-
-<table>
-  <tr>
-    <td width="65%" valign="middle">
-      <h1>Cat Jam</h1>
-      <p><em>Jamming is hard.</em></p>
-      <p><strong>Revealed as a preview of Reflection's Beam.</strong></p>
-      <p>Cat Jam was a coding preview with reasoning, tool use and a 1M-token context, and Reflection named it a Beam preview on 16 October.</p>
-      <p><a href="https://stealthmodels.com/cat-jam/"><strong>Meet Cat Jam ↗</strong></a></p>
-    </td>
-    <td width="35%" align="center" valign="middle">
-      <a href="https://stealthmodels.com/cat-jam/">
-        <img src="https://stealthmodels.com/_shared/artwork/cat-jam-thirteen.webp" width="260" alt="Cat Jam, the serious white jam cat.">
-      </a>
-    </td>
-  </tr>
-</table>
-
-> Independent benchmark card by [Stealth Models](https://stealthmodels.com/): our test results and findings for this model.
-
-## Facts
-| First seen | Revealed | Developer | Context | Input | Tool calls | Speed in our tests | Access |
-|---|---|---|---|---|---|---|---|
-| 13 Oct 2026 | 16 Oct 2026 | Reflection AI | 1,048,576 tokens | Text | Yes | unknown | Preview ended; the released Beam is available |
-
-## StealthMark results
-StealthMark results for the released Beam 1.0:
-
-| Model | Benchmark score | General Intelligence | Visual Intelligence |
-|---|---|---|---|
-| Beam 1.0 501B A23B (released) | 31.9 | 30.9 | 33.8 |
-
-Beam's highest result is Foresight, which tests anticipating threats and planning ahead: 49.4 out of 100.
-StealthMark 1.8.8, results read 28 October 2026. [Beam's full results](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b) · [On the map](https://stealthmodels.com/benchmarks/map)
-
-<img src="https://stealthmodels.com/benchmarks/media/6dea244dd66e5ac6.png" width="360" alt="The released Beam's Beach result, scored at 52.4 out of 100.">
-
-## How it was revealed
-- **16 Oct 2026:** Reflection's [Beam release post](https://reflection.ai/blog/beam-is-available) names the earlier Cat Jam demo as its model, and the Beam weights are available under Apache 2.0.
-- **16 Oct 2026:** Our token-count comparison matched all 24 phrase counts between Cat Jam and Beam. MiMo-V2.6-Pro, MiMo-V2.6-Flash and MISSINGNO. share the pattern. [Details on the model guide](https://stealthmodels.com/cat-jam/).
-- **13 Oct 2026:** Cat Jam appeared as a stealth model for fast agentic coding, with no developer named.
-
-## Run it
-Official weights of the released Beam [reflection/Beam-1.0-501B-A23B](https://huggingface.co/reflection/Beam-1.0-501B-A23B) · license: Apache 2.0, [read it](https://huggingface.co/reflection/Beam-1.0-501B-A23B/blob/main/LICENSE) · GGUF: [Unsloth](https://huggingface.co/unsloth/Beam-1.0-501B-A23B-GGUF) · Local: 501B parameters, 23B active; this needs a large multi-GPU server.
-
----
-[Model guide](https://stealthmodels.com/cat-jam/) · [StealthMark](https://stealthmodels.com/stealthmark) · [Play the benchmarks](https://stealthmodels.com/play) · [Follow for new reveals](https://huggingface.co/stealth-model)
-This card and its images: CC BY 4.0, credit stealthmodels.com. The model's weights have their own license. Updated 28 October 2026.
+---
+pipeline_tag: text-generation
+license: cc-by-4.0
+tags:
+  - cat-jam
+  - beam
+  - stealth-model
+  - stealthmark
+  - coding
+  - reasoning
+  - tool-use
+  - long-context
+thumbnail: https://stealthmodels.com/cat-jam/assets/social-card.png
+new_version: reflection/Beam-1.0-501B-A23B
+---
+
+<a href="https://stealthmodels.com/cat-jam/?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card"><img src="https://huggingface.co/stealth-model/cat-jam/resolve/main/panels/hero.webp" alt="Cat Jam Free, an ivory-white cat concentrating on the beat beside 1M context and free-preview labels."></a>
+
+**Cat Jam was a coding preview with reasoning, tool use and a 1M-token context, and Reflection named it a Beam preview on 16 October.**
+
+*Independent benchmark card by [Stealth Models](https://stealthmodels.com/?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card): our test results and findings for this model.*
+
+StealthMark results for the released Beam 1.0:
+
+<a href="https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card"><img src="https://huggingface.co/stealth-model/cat-jam/resolve/main/panels/verdict.webp" alt="StealthMark 1.8.8 results for the released Beam 1.0: benchmark score 31.9 out of 100, General Intelligence 30.9, Visual Intelligence 33.8. Beam, the model behind Cat Jam, is strongest at composing a whole scene: 52.4 on Beach."></a>
+
+<a href="https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card"><img src="https://huggingface.co/stealth-model/cat-jam/resolve/main/panels/results.webp" alt="Every StealthMark result of the released Beam 1.0: Beach 52.4, Foresight 49.4, Raccoon 46.3, Selfie 45.4, Latch 37.3, Ground Truth 27.9, Newton's Mirror 21.7, Mona Lisa 0.7."></a>
+
+**Open each result** · Visual Intelligence: [Beach&nbsp;52.4](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b/beach?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card) · [Raccoon&nbsp;46.3](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b/raccoon?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card) · [Selfie&nbsp;45.4](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b/selfie?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card) · [Mona&nbsp;Lisa&nbsp;0.7](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b/mona-lisa?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card)<br>
+General Intelligence: [Foresight&nbsp;49.4](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card#game-foresight-self-improvement) · [Latch&nbsp;37.3](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card#game-latch-five-levels) · [Ground&nbsp;Truth&nbsp;27.9](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b/ground-truth?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card) · [Newton's&nbsp;Mirror&nbsp;21.7](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b/newtons-mirror?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card)
+
+**[All results and comparisons on stealthmodels.com ↗](https://stealthmodels.com/benchmarks/models/beam-1.0-501b-a23b?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card)**
+
+<a href="https://stealthmodels.com/cat-jam/?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card"><img src="https://huggingface.co/stealth-model/cat-jam/resolve/main/panels/case.webp" alt="The case file. First seen 13 Oct 2026, revealed 16 Oct 2026, developer Reflection AI, context 1,048,576 tokens, input Text, tool calls Yes, speed in our tests unknown. 13 Oct 2026: Appears as a stealth model for fast agentic coding, with no developer named. 15 Oct 2026, our finding: Our token-count test matches its 24 counts to MISSINGNO. 16 Oct 2026: Reflection names the Cat Jam demo as a Beam preview and releases Beam 1.0 under Apache 2.0."></a>
+
+Sources: [Reflection's Beam release post](https://reflection.ai/blog/beam-is-available) · [our token-count comparison](https://stealthmodels.com/cat-jam/?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card)
+
+<details><summary>Facts as text</summary>
+
+| Fact | Value |
+|---|---|
+| First seen | 13 Oct 2026 |
+| Revealed | 16 Oct 2026 |
+| Developer | Reflection AI |
+| Context | 1,048,576 tokens |
+| Input | Text |
+| Tool calls | Yes |
+| Speed in our tests | unknown |
+| Access | Preview ended; the released Beam is available |
+
+</details>
+
+## Run it
+Official weights of the released Beam [reflection/Beam-1.0-501B-A23B](https://huggingface.co/reflection/Beam-1.0-501B-A23B) · license: Apache 2.0, [read it](https://huggingface.co/reflection/Beam-1.0-501B-A23B/blob/main/LICENSE) · GGUF: [Unsloth](https://huggingface.co/unsloth/Beam-1.0-501B-A23B-GGUF) · Local: 501B parameters, 23B active; this needs a large multi-GPU server.
+
+---
+[Model guide](https://stealthmodels.com/cat-jam/?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card) · [StealthMark](https://stealthmodels.com/stealthmark?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card) · [Play the benchmarks](https://stealthmodels.com/play?utm_source=huggingface&utm_medium=referral&utm_campaign=cat-jam-card) · [Follow for new reveals](https://huggingface.co/stealth-model)<br>
+This card and its images: CC BY 4.0, credit stealthmodels.com. The model's weights have their own license. Updated 28 October 2026.