feat(dashboard): expand Model dropdown labels with point releases + param counts

AGENTS.md

@@ -138,6 +138,31 @@ Plus the wrapper `interpolateMetricAtInteractivity` in `packages/app/src/compone
 
 The Python file has a header comment explaining the pipeline and a `_cli()` entrypoint for stdin/stdout JSON usage. When you update it, keep the structure 1:1 with the TS so future readers can diff the two files line by line. Run the helper against a known dataset and confirm the outputs match what the chart renders before merging.
 
+## Model Parameter Counts (verified)
+
+Authoritative total / active parameter counts for every model in the dashboard. Use these when updating `MODEL_CONFIG` labels in `packages/app/src/lib/data-mappings.ts` or any blog/docs prose. Verify against the HF model card before adding a new model — point releases (e.g. K2 → K2.5, GLM-4.5 → GLM-5) often keep or change sizes in non-obvious ways.
+
+| Model                  | Total | Active      | HF ID                               | Source                             |
+| ---------------------- | ----- | ----------- | ----------------------------------- | ---------------------------------- |
+| DeepSeek-R1-0528       | 671B  | 37B         | `deepseek-ai/DeepSeek-R1-0528`      | HF model card                      |
+| DeepSeek-V4-Pro        | 1.6T  | 49B         | `deepseek-ai/DeepSeek-V4-Pro`       | HF model card                      |
+| Kimi-K2.5              | 1T    | 32B         | `moonshotai/Kimi-K2.5`              | HF model card                      |
+| Kimi-K2.6              | 1T    | 32B         | `moonshotai/Kimi-K2.6`              | HF model card                      |
+| Qwen3.5-397B-A17B      | 397B  | 17B         | `Qwen/Qwen3.5-397B-A17B`            | HF model card                      |
+| GLM-5                  | 744B  | 40B         | `zai-org/GLM-5`                     | HF model card                      |
+| GLM-5.1                | 744B  | 40B         | `zai-org/GLM-5.1-FP8`               | HF model card (same base as GLM-5) |
+| MiniMax-M2.5           | 230B  | 10B         | `MiniMaxAI/MiniMax-M2.5`            | HF model card                      |
+| MiniMax-M2.7           | 230B  | 10B         | `MiniMaxAI/MiniMax-M2.7`            | NVIDIA M2.7 blog                   |
+| gpt-oss-120b           | 120B  | 5.1B        | `openai/gpt-oss-120b`               | HF model card                      |
+| Llama-3.3-70B-Instruct | 70B   | 70B (dense) | `meta-llama/Llama-3.3-70B-Instruct` | HF model card                      |
+
+**Common mislabel traps** (have all bitten this repo at least once — do not repeat):
+
+- **GLM-5 ≠ 355B.** 355B is GLM-4.5. GLM-5 jumped to 744B / 40B active (256-expert MoE with DSA).
+- **MiniMax-M2.5/M2.7 ≠ 456B.** 456B is the older MiniMax-Text-01 / M1 (32 large experts). The M2 series is a different architecture: 230B / 10B active, 256 small experts.
+- **DeepSeek-R1 is 671B, not 685B.** HF metadata shows 685B because the bundled MTP head adds ~14B; the core MoE is 671B / 37B active.
+- **Kimi K2.5 and K2.6 are post-training refinements**, not new pre-trained sizes. Same 1T / 32B / 384-expert backbone as the original K2.
+
 ## Common Development Tasks
 
 ### Modify chart appearance/behavior

packages/app/cypress/e2e/model-architecture.cy.ts

@@ -150,7 +150,7 @@ describe('Model Architecture Diagram', () => {
         doc.body.style.removeProperty('pointer-events');
       });
       cy.get('[role="combobox"]').filter(':visible').first().click();
-      cy.get('[role="option"]').contains('Kimi K2.5').click();
+      cy.get('[role="option"]').contains('Kimi K2.5/2.6').click();
 
       cy.get('[data-testid="model-architecture-toggle"]').should('be.visible');
       cy.get('body').then(($body) => {
@@ -198,7 +198,7 @@ describe('Model Architecture Diagram', () => {
         doc.body.style.removeProperty('pointer-events');
       });
       cy.get('[role="combobox"]').filter(':visible').first().click();
-      cy.get('[role="option"]').contains('MiniMax M2.5').click();
+      cy.get('[role="option"]').contains('MiniMax M2.5/2.7').click();
 
       cy.get('[data-testid="model-architecture-toggle"]').should('be.visible');
       cy.get('body').then(($body) => {

packages/app/src/components/about/faq-data.ts

@@ -31,7 +31,15 @@ const gpusByVendor = [...GPU_KEYS].reduce<Record<string, string[]>>((acc, key) =
   (acc[vendor] ??= []).push(key.toUpperCase());
   return acc;
 }, {});
-const modelNames = Object.values(DB_MODEL_TO_DISPLAY);
+// /about lists each DB bucket as its own bullet, so point releases that
+// elsewhere collapse under one display name (see DB_MODEL_TO_DISPLAY) are
+// expanded back out here.
+const modelNames = Object.values({
+  ...DB_MODEL_TO_DISPLAY,
+  'kimik2.6': 'Kimi-K2.6',
+  'minimaxm2.7': 'MiniMax-M2.7',
+  'glm5.1': 'GLM-5.1',
+});
 
 const frameworkNames = [...new Set(Object.values(FRAMEWORK_LABELS))].map((n) =>
   n.replace(/[¹²³⁴⁵⁶⁷⁸⁹⁰]+$/u, ''),

packages/app/src/lib/data-mappings.test.ts

@@ -184,12 +184,13 @@ describe('getModelLabel', () => {
   it('returns correct label for each known model', () => {
     expect(getModelLabel(Model.Llama3_3_70B)).toBe('Llama 3.3 70B Instruct');
     expect(getModelLabel(Model.Llama3_1_70B)).toBe('Llama 3.1 70B Instruct');
-    expect(getModelLabel(Model.DeepSeek_R1)).toBe('DeepSeek R1 0528');
+    expect(getModelLabel(Model.DeepSeek_R1)).toBe('DeepSeek R1 0528 670B');
+    expect(getModelLabel(Model.DeepSeek_V4_Pro)).toBe('DeepSeek V4 Pro 1.6T');
     expect(getModelLabel(Model.GptOss)).toBe('gpt-oss 120B');
-    expect(getModelLabel(Model.Qwen3_5)).toBe('Qwen3.5');
-    expect(getModelLabel(Model.Kimi_K2_5)).toBe('Kimi K2.5');
-    expect(getModelLabel(Model.GLM_5)).toBe('GLM5/5.1');
-    expect(getModelLabel(Model.MiniMax_M2_5)).toBe('MiniMax M2.5');
+    expect(getModelLabel(Model.Qwen3_5)).toBe('Qwen3.5 397B');
+    expect(getModelLabel(Model.Kimi_K2_5)).toBe('Kimi K2.5/2.6 1T');
+    expect(getModelLabel(Model.GLM_5)).toBe('GLM5/5.1 744B');
+    expect(getModelLabel(Model.MiniMax_M2_5)).toBe('MiniMax M2.5/2.7 230B');
   });
 
   it('falls back to the model value for unknown model', () => {

packages/app/src/lib/data-mappings.ts

@@ -48,23 +48,32 @@ interface ModelConfig {
   mtpEngineExclusion?: boolean;
 }
 
+// Total parameter counts appended to each label so users can compare model
+// scale at a glance in the dropdown. For Llama and gpt-oss the count is
+// already part of the canonical name (Llama 3.3 70B, gpt-oss 120B) so no
+// duplication needed.
 const MODEL_CONFIG: Record<Model, ModelConfig> = {
-  [Model.DeepSeek_R1]: { label: 'DeepSeek R1 0528', prefix: 'dsr1', category: 'default' },
+  [Model.DeepSeek_R1]: { label: 'DeepSeek R1 0528 670B', prefix: 'dsr1', category: 'default' },
   [Model.DeepSeek_V4_Pro]: {
-    label: 'DeepSeek V4 Pro',
+    label: 'DeepSeek V4 Pro 1.6T',
     prefix: 'dsv4',
     category: 'default',
     mtpEngineExclusion: true,
   },
   [Model.Kimi_K2_5]: {
-    label: 'Kimi K2.5',
+    // K2.5 and K2.6 share an architecture, so the dropdown surfaces both
+    // versions joined with a slash — matches the GLM5/5.1 pattern. The
+    // hyphenated `Model.Kimi_K2_5` enum value stays as-is for internal
+    // routing / DB key mapping.
+    label: 'Kimi K2.5/2.6 1T',
     prefix: 'kimik2.5',
     category: 'default',
   },
-  [Model.Qwen3_5]: { label: 'Qwen3.5', prefix: 'qwen3.5', category: 'default' },
-  [Model.GLM_5]: { label: 'GLM5/5.1', prefix: 'glm5', category: 'default' },
+  [Model.Qwen3_5]: { label: 'Qwen3.5 397B', prefix: 'qwen3.5', category: 'default' },
+  [Model.GLM_5]: { label: 'GLM5/5.1 744B', prefix: 'glm5', category: 'default' },
   [Model.MiniMax_M2_5]: {
-    label: 'MiniMax M2.5',
+    // M2.5 and M2.7 share an architecture — same GLM5/5.1 pattern as Kimi.
+    label: 'MiniMax M2.5/2.7 230B',
     prefix: 'minimaxm2.5',
     category: 'default',
   },