pi-free 2.0.13 → 2.0.14

package/provider-failover/benchmarks-chunk-0.ts

@@ -1,15 +1,50 @@
 // Auto-generated benchmark data chunk 0
-// Models: gpt-oss-120b-high .. solar-open-100b-reasoning (90 entries)
+// Models: gpt-oss-20b-low .. lfm2-8b-a1b (90 entries)
+// Last updated: 2026-06-01
 // DO NOT EDIT MANUALLY — generated by scripts/update-benchmarks.ts
 
 import type { HardcodedBenchmark } from "./hardcoded-benchmarks.ts";
 
 export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
-	"gpt-oss-120b-high": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 33.3,
-		normalizedScore: 48,
+	"gpt-oss-20b-low": {
+		// AA specific benchmarks
+		codingIndex: 14.4,
+		mathIndex: 62.3,
+
+		// Academic benchmarks
+		mmluPro: 0.718,
+		gpqa: 0.611,
+		hle: 0.051,
+
+		// Capabilities
+		contextWindow: 8192,
+		supportsReasoning: false,
+		supportsVision: false,
+
+		// Metadata
+		lastUpdated: "2026-06-01",
+		originalModel: "gpt-oss-20B (low)",
+	},
+	"gpt-oss-20b-high": {
+		// AA specific benchmarks
+		codingIndex: 18.5,
+		mathIndex: 89.3,
+
+		// Academic benchmarks
+		mmluPro: 0.748,
+		gpqa: 0.688,
+		hle: 0.098,
+
+		// Capabilities
+		contextWindow: 8192,
+		supportsReasoning: false,
+		supportsVision: false,
 
+		// Metadata
+		lastUpdated: "2026-06-01",
+		originalModel: "gpt-oss-20B (high)",
+	},
+	"gpt-oss-120b-high": {
 		// AA specific benchmarks
 		codingIndex: 28.6,
 		mathIndex: 93.4,
@@ -25,13 +60,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "gpt-oss-120b (high)",
 	},
 	"gpt-5.4-mini-xhigh": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 48.1,
-		normalizedScore: 69,
-
 		// AA specific benchmarks
 		codingIndex: 51.5,
 		mathIndex: undefined,
@@ -47,13 +79,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.4 mini (xhigh)",
 	},
 	"gpt-5.4-nano-xhigh": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 44.4,
-		normalizedScore: 63,
-
 		// AA specific benchmarks
 		codingIndex: 43.9,
 		mathIndex: undefined,
@@ -69,13 +98,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.4 nano (xhigh)",
 	},
 	"gpt-oss-120b-low": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 24.5,
-		normalizedScore: 35,
-
 		// AA specific benchmarks
 		codingIndex: 15.5,
 		mathIndex: 66.7,
@@ -91,21 +117,37 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "gpt-oss-120b (low)",
 	},
-	"gpt-5.4-nano-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 24.4,
-		normalizedScore: 35,
+	"o3": {
+		// AA specific benchmarks
+		codingIndex: 38.4,
+		mathIndex: 88.3,
+
+		// Academic benchmarks
+		mmluPro: 0.853,
+		gpqa: 0.827,
+		hle: 0.2,
+
+		// Capabilities
+		contextWindow: 8192,
+		supportsReasoning: false,
+		supportsVision: false,
 
+		// Metadata
+		lastUpdated: "2026-06-01",
+		originalModel: "o3",
+	},
+	"grok-1": {
 		// AA specific benchmarks
-		codingIndex: 27.9,
+		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.558,
-		hle: 0.042,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -113,21 +155,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok-1",
 	},
-	"gpt-5.4-nano-medium": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 38.1,
-		normalizedScore: 54,
-
+	"gpt-5.4-mini-medium": {
 		// AA specific benchmarks
-		codingIndex: 35,
+		codingIndex: 37.5,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.761,
-		hle: 0.147,
+		gpqa: 0.823,
+		hle: 0.171,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -135,13 +174,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.4 mini (medium)",
 	},
 	"gpt-5.4-mini-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 23.3,
-		normalizedScore: 33,
-
 		// AA specific benchmarks
 		codingIndex: 25.3,
 		mathIndex: undefined,
@@ -157,21 +193,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.4 mini (Non-Reasoning)",
 	},
-	"gpt-5.4-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 35.4,
-		normalizedScore: 51,
-
+	"gpt-5.5-instant-may-2026": {
 		// AA specific benchmarks
-		codingIndex: 41,
+		codingIndex: 45.1,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.748,
-		hle: 0.106,
+		gpqa: 0.846,
+		hle: 0.203,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -179,21 +212,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.5 Instant (May 2026)",
 	},
-	"gpt-5.4-mini-medium": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 37.7,
-		normalizedScore: 54,
-
+	"gpt-5.5-low": {
 		// AA specific benchmarks
-		codingIndex: 37.5,
+		codingIndex: 52.1,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.823,
-		hle: 0.171,
+		gpqa: 0.91,
+		hle: 0.31,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -201,21 +231,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.5 (low)",
 	},
-	"gpt-oss-20b-high": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 24.5,
-		normalizedScore: 35,
-
+	"gpt-5.4-nano-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 18.5,
-		mathIndex: 89.3,
+		codingIndex: 27.9,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.748,
-		gpqa: 0.688,
-		hle: 0.098,
+		mmluPro: undefined,
+		gpqa: 0.558,
+		hle: 0.042,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -223,21 +250,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.4 nano (Non-Reasoning)",
 	},
-	"gpt-5.4-xhigh": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 57.2,
-		normalizedScore: 82,
-
+	"gpt-5.5-high": {
 		// AA specific benchmarks
-		codingIndex: 57.3,
+		codingIndex: 58.5,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.92,
-		hle: 0.416,
+		gpqa: 0.932,
+		hle: 0.43,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -245,21 +269,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.5 (high)",
 	},
-	"grok-1": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 11.7,
-		normalizedScore: 17,
-
+	"gpt-5.4-nano-medium": {
 		// AA specific benchmarks
-		codingIndex: undefined,
+		codingIndex: 35,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: undefined,
-		hle: undefined,
+		gpqa: 0.761,
+		hle: 0.147,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -267,21 +288,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.4 nano (medium)",
 	},
-	"gpt-oss-20b-low": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 20.8,
-		normalizedScore: 30,
-
+	"gpt-5.5-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 14.4,
-		mathIndex: 62.3,
+		codingIndex: 48.6,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.718,
-		gpqa: 0.611,
-		hle: 0.051,
+		mmluPro: undefined,
+		gpqa: 0.768,
+		hle: 0.126,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -289,21 +307,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.5 (Non-reasoning)",
 	},
-	o3: {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 38.4,
-		normalizedScore: 55,
-
+	"gpt-5.5-medium": {
 		// AA specific benchmarks
-		codingIndex: 38.4,
-		mathIndex: 88.3,
+		codingIndex: 56.2,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.853,
-		gpqa: 0.827,
-		hle: 0.2,
+		mmluPro: undefined,
+		gpqa: 0.926,
+		hle: 0.406,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -311,13 +326,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.5 (medium)",
 	},
 	"gpt-5.3-codex-xhigh": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 54,
-		normalizedScore: 77,
-
 		// AA specific benchmarks
 		codingIndex: 53.1,
 		mathIndex: undefined,
@@ -333,13 +345,29 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.3 Codex (xhigh)",
 	},
-	"llama-3.3-instruct-70b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 14.5,
-		normalizedScore: 21,
+	"gpt-5.5-xhigh": {
+		// AA specific benchmarks
+		codingIndex: 59.1,
+		mathIndex: undefined,
+
+		// Academic benchmarks
+		mmluPro: undefined,
+		gpqa: 0.935,
+		hle: 0.443,
 
+		// Capabilities
+		contextWindow: 8192,
+		supportsReasoning: false,
+		supportsVision: false,
+
+		// Metadata
+		lastUpdated: "2026-06-01",
+		originalModel: "GPT-5.5 (xhigh)",
+	},
+	"llama-3.3-instruct-70b": {
 		// AA specific benchmarks
 		codingIndex: 10.7,
 		mathIndex: 7.7,
@@ -355,13 +383,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 3.3 Instruct 70B",
 	},
 	"llama-3.1-instruct-405b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 17.4,
-		normalizedScore: 25,
-
 		// AA specific benchmarks
 		codingIndex: 14.5,
 		mathIndex: 3,
@@ -377,13 +402,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 3.1 Instruct 405B",
 	},
 	"llama-3.2-instruct-90b-vision": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 11.9,
-		normalizedScore: 17,
-
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
@@ -399,15 +421,12 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 3.2 Instruct 90B (Vision)",
 	},
 	"llama-3.2-instruct-11b-vision": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.7,
-		normalizedScore: 12,
-
 		// AA specific benchmarks
-		codingIndex: 4.3,
+		codingIndex: 4.2,
 		mathIndex: 1.7,
 
 		// Academic benchmarks
@@ -421,13 +440,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 3.2 Instruct 11B (Vision)",
 	},
 	"llama-4-maverick": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 18.4,
-		normalizedScore: 26,
-
 		// AA specific benchmarks
 		codingIndex: 15.6,
 		mathIndex: 19.3,
@@ -443,13 +459,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 4 Maverick",
 	},
 	"llama-4-scout": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 13.5,
-		normalizedScore: 19,
-
 		// AA specific benchmarks
 		codingIndex: 6.7,
 		mathIndex: 14,
@@ -465,21 +478,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 4 Scout",
 	},
-	"gemma-3-12b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.8,
-		normalizedScore: 13,
-
+	"muse-spark": {
 		// AA specific benchmarks
-		codingIndex: 6.3,
-		mathIndex: 18.3,
+		codingIndex: 47.5,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.595,
-		gpqa: 0.349,
-		hle: 0.048,
+		mmluPro: undefined,
+		gpqa: 0.884,
+		hle: 0.399,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -487,21 +497,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Muse Spark",
 	},
-	"gemini-3-flash-preview-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 35,
-		normalizedScore: 50,
-
+	"gemini-3.1-pro-preview": {
 		// AA specific benchmarks
-		codingIndex: 37.8,
-		mathIndex: 55.7,
+		codingIndex: 55.5,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.882,
-		gpqa: 0.812,
-		hle: 0.141,
+		mmluPro: undefined,
+		gpqa: 0.941,
+		hle: 0.447,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -509,21 +516,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemini 3.1 Pro Preview",
 	},
-	"gemma-3-27b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.3,
-		normalizedScore: 15,
-
+	"gemma-4-26b-a4b-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 9.6,
-		mathIndex: 20.7,
+		codingIndex: 29.1,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.669,
-		gpqa: 0.428,
-		hle: 0.047,
+		mmluPro: undefined,
+		gpqa: 0.714,
+		hle: 0.107,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -531,21 +535,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 4 26B A4B (Non-reasoning)",
 	},
-	"gemma-4-31b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 39.2,
-		normalizedScore: 56,
-
+	"gemini-3.5-flash-medium": {
 		// AA specific benchmarks
-		codingIndex: 38.7,
+		codingIndex: 43.9,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.857,
-		hle: 0.227,
+		gpqa: 0.921,
+		hle: 0.399,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -553,21 +554,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemini 3.5 Flash (medium)",
 	},
-	"gemma-3-4b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 6.3,
-		normalizedScore: 9,
-
+	"gemma-4-e2b-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 2.9,
-		mathIndex: 12.7,
+		codingIndex: 8.3,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.417,
-		gpqa: 0.291,
-		hle: 0.052,
+		mmluPro: undefined,
+		gpqa: 0.405,
+		hle: 0.045,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -575,21 +573,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 4 E2B (Non-reasoning)",
 	},
-	"gemma-4-e4b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 18.8,
-		normalizedScore: 27,
-
+	"gemma-4-31b-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 13.7,
+		codingIndex: 38.7,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.576,
-		hle: 0.037,
+		gpqa: 0.857,
+		hle: 0.227,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -597,21 +592,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 4 31B (Reasoning)",
 	},
-	"gemini-3-pro-preview-low": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 41.3,
-		normalizedScore: 59,
-
+	"gemma-4-31b-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 39.4,
-		mathIndex: 86.7,
+		codingIndex: 33.9,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.895,
-		gpqa: 0.887,
-		hle: 0.276,
+		mmluPro: undefined,
+		gpqa: 0.763,
+		hle: 0.115,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -619,21 +611,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 4 31B (Non-reasoning)",
 	},
-	"gemma-3-1b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 5.5,
-		normalizedScore: 8,
-
+	"gemma-4-26b-a4b-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 0.2,
-		mathIndex: 3.3,
+		codingIndex: 22.4,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.135,
-		gpqa: 0.237,
-		hle: 0.052,
+		mmluPro: undefined,
+		gpqa: 0.792,
+		hle: 0.183,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -641,21 +630,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 4 26B A4B (Reasoning)",
 	},
-	"gemma-4-26b-a4b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 31.2,
-		normalizedScore: 45,
-
+	"gemini-3.1-flash-lite": {
 		// AA specific benchmarks
-		codingIndex: 22.4,
+		codingIndex: 30.1,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.792,
-		hle: 0.183,
+		gpqa: 0.822,
+		hle: 0.162,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -663,21 +649,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemini 3.1 Flash-Lite",
 	},
-	"gemma-4-e2b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 15.2,
-		normalizedScore: 22,
-
+	"gemma-4-e4b-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 9,
+		codingIndex: 6.4,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.433,
-		hle: 0.048,
+		gpqa: 0.549,
+		hle: 0.047,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -685,21 +668,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 4 E4B (Non-reasoning)",
 	},
-	"gemini-3.1-pro-preview": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 57.2,
-		normalizedScore: 82,
-
+	"gemma-3-270m": {
 		// AA specific benchmarks
-		codingIndex: 55.5,
-		mathIndex: undefined,
+		codingIndex: 0,
+		mathIndex: 2.3,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.941,
-		hle: 0.447,
+		mmluPro: 0.055,
+		gpqa: 0.224,
+		hle: 0.042,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -707,21 +687,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 3 270M",
 	},
-	"gemini-3-flash-preview-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 46.4,
-		normalizedScore: 66,
-
+	"gemma-4-e4b-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 42.6,
-		mathIndex: 97,
+		codingIndex: 13.7,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.89,
-		gpqa: 0.898,
-		hle: 0.347,
+		mmluPro: undefined,
+		gpqa: 0.576,
+		hle: 0.037,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -729,21 +706,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 4 E4B (Reasoning)",
 	},
-	"gemma-3n-e4b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 6.4,
-		normalizedScore: 9,
-
+	"gemini-3.5-flash-high": {
 		// AA specific benchmarks
-		codingIndex: 4.2,
-		mathIndex: 14.3,
+		codingIndex: 45,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.488,
-		gpqa: 0.296,
-		hle: 0.044,
+		mmluPro: undefined,
+		gpqa: 0.922,
+		hle: 0.41,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -751,21 +725,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemini 3.5 Flash (high)",
 	},
-	"gemini-2.5-flash-lite-preview-sep-25-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 19.4,
-		normalizedScore: 28,
-
+	"gemini-3.5-flash-minimal": {
 		// AA specific benchmarks
-		codingIndex: 14.5,
-		mathIndex: 46.7,
+		codingIndex: 47.1,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.796,
-		gpqa: 0.651,
-		hle: 0.046,
+		mmluPro: undefined,
+		gpqa: 0.828,
+		hle: 0.231,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -773,21 +744,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemini 3.5 Flash (minimal)",
 	},
-	"gemma-3n-e2b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 4.8,
-		normalizedScore: 7,
-
+	"gemma-4-e2b-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 2.2,
-		mathIndex: 10.3,
+		codingIndex: 9,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.378,
-		gpqa: 0.229,
-		hle: 0.04,
+		mmluPro: undefined,
+		gpqa: 0.433,
+		hle: 0.048,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -795,15 +763,12 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemma 4 E2B (Reasoning)",
 	},
 	"gemini-2.5-pro": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 34.6,
-		normalizedScore: 49,
-
 		// AA specific benchmarks
-		codingIndex: 31.9,
+		codingIndex: 32,
 		mathIndex: 87.7,
 
 		// Academic benchmarks
@@ -817,21 +782,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Gemini 2.5 Pro",
 	},
-	"gemma-3-270m": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 7.7,
-		normalizedScore: 11,
-
+	"claude-sonnet-4.6-non-reasoning-high-effort": {
 		// AA specific benchmarks
-		codingIndex: 0,
-		mathIndex: 2.3,
+		codingIndex: 46.4,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.055,
-		gpqa: 0.224,
-		hle: 0.042,
+		mmluPro: undefined,
+		gpqa: 0.799,
+		hle: 0.132,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -839,43 +801,37 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Claude Sonnet 4.6 (Non-reasoning, High Effort)",
 	},
-	"gemini-2.5-flash-lite-preview-sep-25-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 21.6,
-		normalizedScore: 31,
-
+	"claude-opus-4.8-adaptive-reasoning-max-effort": {
 		// AA specific benchmarks
-		codingIndex: 18.1,
-		mathIndex: 68.7,
+		codingIndex: 56.7,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.808,
-		gpqa: 0.709,
-		hle: 0.066,
-
+		mmluPro: undefined,
+		gpqa: 0.92,
+		hle: 0.457,
+
 		// Capabilities
 		contextWindow: 8192,
 		supportsReasoning: false,
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Claude Opus 4.8 (Adaptive Reasoning, Max Effort)",
 	},
-	"gemini-3.1-flash-lite-preview": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 33.5,
-		normalizedScore: 48,
-
+	"claude-4.5-haiku-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 30.1,
-		mathIndex: undefined,
+		codingIndex: 32.6,
+		mathIndex: 83.7,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.822,
-		hle: 0.162,
+		mmluPro: 0.76,
+		gpqa: 0.672,
+		hle: 0.097,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -883,21 +839,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Claude 4.5 Haiku (Reasoning)",
 	},
-	"claude-4.5-haiku-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 31.1,
-		normalizedScore: 44,
-
+	"claude-opus-4.7-adaptive-reasoning-max-effort": {
 		// AA specific benchmarks
-		codingIndex: 29.6,
-		mathIndex: 39,
+		codingIndex: 52.5,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.8,
-		gpqa: 0.646,
-		hle: 0.043,
+		mmluPro: undefined,
+		gpqa: 0.914,
+		hle: 0.396,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -905,21 +858,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Claude Opus 4.7 (Adaptive Reasoning, Max Effort)",
 	},
-	"claude-4.5-haiku-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 37.1,
-		normalizedScore: 53,
-
+	"claude-opus-4.7-non-reasoning-high-effort": {
 		// AA specific benchmarks
-		codingIndex: 32.6,
-		mathIndex: 83.7,
+		codingIndex: 53.1,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.76,
-		gpqa: 0.672,
-		hle: 0.097,
+		mmluPro: undefined,
+		gpqa: 0.885,
+		hle: 0.312,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -927,21 +877,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Claude Opus 4.7 (Non-reasoning, High Effort)",
 	},
-	"claude-opus-4.6-non-reasoning-high-effort": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 46.5,
-		normalizedScore: 66,
-
+	"claude-sonnet-4.6-non-reasoning-low-effort": {
 		// AA specific benchmarks
-		codingIndex: 47.6,
+		codingIndex: 43,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.84,
-		hle: 0.186,
+		gpqa: 0.797,
+		hle: 0.108,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -949,21 +896,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Claude Sonnet 4.6 (Non-reasoning, Low Effort)",
 	},
-	"claude-opus-4.6-adaptive-reasoning-max-effort": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 53,
-		normalizedScore: 76,
-
+	"claude-4.5-haiku-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 48.1,
-		mathIndex: undefined,
+		codingIndex: 29.6,
+		mathIndex: 39,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.896,
-		hle: 0.367,
+		mmluPro: 0.8,
+		gpqa: 0.646,
+		hle: 0.043,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -971,21 +915,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Claude 4.5 Haiku (Non-reasoning)",
 	},
-	"claude-sonnet-4.6-non-reasoning-high-effort": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 44.4,
-		normalizedScore: 63,
-
+	"claude-sonnet-4.6-adaptive-reasoning-max-effort": {
 		// AA specific benchmarks
-		codingIndex: 46.4,
+		codingIndex: 50.9,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.799,
-		hle: 0.132,
+		gpqa: 0.875,
+		hle: 0.3,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -993,21 +934,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)",
 	},
-	"claude-sonnet-4.6-adaptive-reasoning-max-effort": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 51.7,
-		normalizedScore: 74,
-
+	"magistral-small-1.2": {
 		// AA specific benchmarks
-		codingIndex: 50.9,
-		mathIndex: undefined,
+		codingIndex: 14.8,
+		mathIndex: 80.3,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.875,
-		hle: 0.3,
+		mmluPro: 0.768,
+		gpqa: 0.663,
+		hle: 0.061,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1015,21 +953,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Magistral Small 1.2",
 	},
-	"claude-sonnet-4.6-non-reasoning-low-effort": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 42.6,
-		normalizedScore: 61,
-
+	"mistral-medium-3.5": {
 		// AA specific benchmarks
-		codingIndex: 43,
+		codingIndex: 35.4,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.797,
-		hle: 0.108,
+		gpqa: 0.748,
+		hle: 0.128,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1037,21 +972,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Mistral Medium 3.5",
 	},
-	"mistral-large-3": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 22.8,
-		normalizedScore: 33,
-
+	"devstral-small-2": {
 		// AA specific benchmarks
-		codingIndex: 22.7,
-		mathIndex: 38,
+		codingIndex: 20.7,
+		mathIndex: 34.3,
 
 		// Academic benchmarks
-		mmluPro: 0.807,
-		gpqa: 0.68,
-		hle: 0.041,
+		mmluPro: 0.678,
+		gpqa: 0.532,
+		hle: 0.034,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1059,21 +991,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Devstral Small 2",
 	},
-	"devstral-2": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 22,
-		normalizedScore: 31,
-
+	"ministral-3-8b": {
 		// AA specific benchmarks
-		codingIndex: 23.7,
-		mathIndex: 36.7,
+		codingIndex: 10,
+		mathIndex: 31.7,
 
 		// Academic benchmarks
-		mmluPro: 0.762,
-		gpqa: 0.594,
-		hle: 0.036,
+		mmluPro: 0.642,
+		gpqa: 0.471,
+		hle: 0.043,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1081,21 +1010,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Ministral 3 8B",
 	},
-	"mistral-small-4-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 27.2,
-		normalizedScore: 39,
-
+	"magistral-medium-1.2": {
 		// AA specific benchmarks
-		codingIndex: 24.3,
-		mathIndex: undefined,
+		codingIndex: 21.7,
+		mathIndex: 82,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.769,
-		hle: 0.095,
+		mmluPro: 0.815,
+		gpqa: 0.739,
+		hle: 0.096,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1103,21 +1029,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Magistral Medium 1.2",
 	},
-	"ministral-3-8b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 14.8,
-		normalizedScore: 21,
-
+	"mistral-large-3": {
 		// AA specific benchmarks
-		codingIndex: 10,
-		mathIndex: 31.7,
+		codingIndex: 22.7,
+		mathIndex: 38,
 
 		// Academic benchmarks
-		mmluPro: 0.642,
-		gpqa: 0.471,
-		hle: 0.043,
+		mmluPro: 0.807,
+		gpqa: 0.68,
+		hle: 0.041,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1125,13 +1048,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Mistral Large 3",
 	},
 	"ministral-3-14b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16,
-		normalizedScore: 23,
-
 		// AA specific benchmarks
 		codingIndex: 10.9,
 		mathIndex: 30,
@@ -1147,21 +1067,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Ministral 3 14B",
 	},
-	"magistral-medium-1.2": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 27.1,
-		normalizedScore: 39,
-
+	"mistral-small-4-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 21.7,
-		mathIndex: 82,
+		codingIndex: 24.3,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.815,
-		gpqa: 0.739,
-		hle: 0.096,
+		mmluPro: undefined,
+		gpqa: 0.769,
+		hle: 0.095,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1169,13 +1086,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Mistral Small 4 (Reasoning)",
 	},
 	"mistral-small-4-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 18.6,
-		normalizedScore: 27,
-
 		// AA specific benchmarks
 		codingIndex: 16.4,
 		mathIndex: undefined,
@@ -1191,21 +1105,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Mistral Small 4 (Non-reasoning)",
 	},
-	"magistral-small-1.2": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 18.2,
-		normalizedScore: 26,
-
+	"devstral-2": {
 		// AA specific benchmarks
-		codingIndex: 14.8,
-		mathIndex: 80.3,
+		codingIndex: 23.7,
+		mathIndex: 36.7,
 
 		// Academic benchmarks
-		mmluPro: 0.768,
-		gpqa: 0.663,
-		hle: 0.061,
+		mmluPro: 0.762,
+		gpqa: 0.594,
+		hle: 0.036,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1213,13 +1124,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Devstral 2",
 	},
 	"ministral-3-3b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 11.2,
-		normalizedScore: 16,
-
 		// AA specific benchmarks
 		codingIndex: 4.8,
 		mathIndex: 22,
@@ -1235,65 +1143,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
-	},
-	"mistral-medium-3.1": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 21.3,
-		normalizedScore: 30,
-
-		// AA specific benchmarks
-		codingIndex: 18.3,
-		mathIndex: 38.3,
-
-		// Academic benchmarks
-		mmluPro: 0.683,
-		gpqa: 0.588,
-		hle: 0.044,
-
-		// Capabilities
-		contextWindow: 8192,
-		supportsReasoning: false,
-		supportsVision: false,
-
-		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Ministral 3 3B",
 	},
-	"devstral-small-2": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 19.5,
-		normalizedScore: 28,
-
+	"deepseek-v4-pro-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 20.7,
-		mathIndex: 34.3,
-
-		// Academic benchmarks
-		mmluPro: 0.678,
-		gpqa: 0.532,
-		hle: 0.034,
-
-		// Capabilities
-		contextWindow: 8192,
-		supportsReasoning: false,
-		supportsVision: false,
-
-		// Metadata
-		lastUpdated: "2026-04-06",
-	},
-	"deepseek-r1-distill-llama-70b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16,
-		normalizedScore: 23,
-
-		// AA specific benchmarks
-		codingIndex: 11.4,
-		mathIndex: 53.7,
+		codingIndex: 38.4,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.795,
-		gpqa: 0.402,
-		hle: 0.061,
+		mmluPro: undefined,
+		gpqa: 0.717,
+		hle: 0.077,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1301,21 +1162,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V4 Pro (Non-reasoning)",
 	},
-	"deepseek-r1-0528-may-25": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 27.1,
-		normalizedScore: 39,
-
+	"deepseek-v4-pro-reasoning-high-effort": {
 		// AA specific benchmarks
-		codingIndex: 24,
-		mathIndex: 76,
+		codingIndex: 43.2,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.849,
-		gpqa: 0.813,
-		hle: 0.149,
+		mmluPro: undefined,
+		gpqa: 0.905,
+		hle: 0.335,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1323,21 +1181,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V4 Pro (Reasoning, High Effort)",
 	},
-	"deepseek-v3.2-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 32.1,
-		normalizedScore: 46,
-
+	"deepseek-v4-pro-reasoning-max-effort": {
 		// AA specific benchmarks
-		codingIndex: 34.6,
-		mathIndex: 59,
+		codingIndex: 47.5,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.837,
-		gpqa: 0.751,
-		hle: 0.105,
+		mmluPro: undefined,
+		gpqa: 0.888,
+		hle: 0.359,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1345,21 +1200,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V4 Pro (Reasoning, Max Effort)",
 	},
-	"deepseek-v3.2-speciale": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 29.4,
-		normalizedScore: 42,
-
+	"deepseek-v4-flash-reasoning-max-effort": {
 		// AA specific benchmarks
-		codingIndex: 37.9,
-		mathIndex: 96.7,
+		codingIndex: 38.7,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.863,
-		gpqa: 0.871,
-		hle: 0.261,
+		mmluPro: undefined,
+		gpqa: 0.894,
+		hle: 0.321,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1367,21 +1219,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V4 Flash (Reasoning, Max Effort)",
 	},
-	"deepseek-r1-0528-qwen3-8b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16.4,
-		normalizedScore: 23,
-
+	"deepseek-v4-flash-reasoning-high-effort": {
 		// AA specific benchmarks
-		codingIndex: 7.8,
-		mathIndex: 63.7,
+		codingIndex: 39.8,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.739,
-		gpqa: 0.612,
-		hle: 0.056,
+		mmluPro: undefined,
+		gpqa: 0.867,
+		hle: 0.278,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1389,21 +1238,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V4 Flash (Reasoning, High Effort)",
 	},
-	"deepseek-v3.2-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 41.7,
-		normalizedScore: 60,
-
+	"deepseek-v4-flash-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 36.7,
-		mathIndex: 92,
+		codingIndex: 35.2,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.862,
-		gpqa: 0.84,
-		hle: 0.222,
+		mmluPro: undefined,
+		gpqa: 0.716,
+		hle: 0.07,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1411,13 +1257,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V4 Flash (Non-reasoning)",
 	},
 	"r1-1776": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12,
-		normalizedScore: 17,
-
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
@@ -1433,13 +1276,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "R1 1776",
 	},
 	"falcon-h1r-7b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 15.8,
-		normalizedScore: 23,
-
 		// AA specific benchmarks
 		codingIndex: 9.8,
 		mathIndex: 80,
@@ -1455,21 +1295,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Falcon-H1R-7B",
 	},
-	"grok-4.20-beta-0309-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 48.5,
-		normalizedScore: 69,
-
+	"grok-4.3-medium": {
 		// AA specific benchmarks
-		codingIndex: 42.2,
+		codingIndex: 35.1,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.885,
-		hle: 0.3,
+		gpqa: 0.89,
+		hle: 0.281,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1477,21 +1314,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.3 (medium)",
 	},
-	"grok-4.20-beta-0309-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 29.7,
-		normalizedScore: 42,
-
+	"grok-4.3-low": {
 		// AA specific benchmarks
-		codingIndex: 25.4,
+		codingIndex: 31.6,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.785,
-		hle: 0.225,
+		gpqa: 0.843,
+		hle: 0.173,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1499,21 +1333,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.3 (low)",
 	},
-	"grok-code-fast-1": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 28.7,
-		normalizedScore: 41,
-
+	"grok-4.3-high": {
 		// AA specific benchmarks
-		codingIndex: 23.7,
-		mathIndex: 43.3,
+		codingIndex: 41,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.793,
-		gpqa: 0.727,
-		hle: 0.075,
+		mmluPro: undefined,
+		gpqa: 0.901,
+		hle: 0.35,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1521,21 +1352,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.3 (high)",
 	},
-	"grok-3-mini-reasoning-high": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 32.1,
-		normalizedScore: 46,
-
+	"grok-4.3-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 25.2,
-		mathIndex: 84.7,
+		codingIndex: 25.1,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.828,
-		gpqa: 0.791,
-		hle: 0.111,
+		mmluPro: undefined,
+		gpqa: 0.658,
+		hle: 0.065,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1543,13 +1371,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.3 (Non-reasoning)",
 	},
 	"nova-micro": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.3,
-		normalizedScore: 15,
-
 		// AA specific benchmarks
 		codingIndex: 4.1,
 		mathIndex: 6,
@@ -1565,21 +1390,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova Micro",
 	},
-	"nova-premier": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 19,
-		normalizedScore: 27,
-
+	"nova-2.0-omni-low": {
 		// AA specific benchmarks
-		codingIndex: 13.8,
-		mathIndex: 17.3,
+		codingIndex: 13.9,
+		mathIndex: 56,
 
 		// Academic benchmarks
-		mmluPro: 0.733,
-		gpqa: 0.569,
-		hle: 0.047,
+		mmluPro: 0.798,
+		gpqa: 0.699,
+		hle: 0.04,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1587,21 +1409,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Omni (low)",
 	},
-	"nova-2-lite-low": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 24.6,
-		normalizedScore: 35,
-
+	"nova-2.0-pro-preview-medium": {
 		// AA specific benchmarks
-		codingIndex: 13.6,
-		mathIndex: 46.7,
+		codingIndex: 30.4,
+		mathIndex: 89,
 
 		// Academic benchmarks
-		mmluPro: 0.788,
-		gpqa: 0.698,
-		hle: 0.042,
+		mmluPro: 0.83,
+		gpqa: 0.785,
+		hle: 0.089,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1609,13 +1428,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Pro Preview (medium)",
 	},
-	"nova-2-lite-medium": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 29.7,
-		normalizedScore: 42,
-
+	"nova-2.0-lite-medium": {
 		// AA specific benchmarks
 		codingIndex: 23.9,
 		mathIndex: 88.7,
@@ -1631,21 +1447,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Lite (medium)",
 	},
-	"nova-2-pro-preview-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 23.1,
-		normalizedScore: 33,
-
+	"nova-2.0-lite-high": {
 		// AA specific benchmarks
-		codingIndex: 20.5,
-		mathIndex: 30.7,
+		codingIndex: 23.4,
+		mathIndex: 94.3,
 
 		// Academic benchmarks
-		mmluPro: 0.772,
-		gpqa: 0.636,
-		hle: 0.04,
+		mmluPro: 0.818,
+		gpqa: 0.811,
+		hle: 0.109,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1653,21 +1466,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Lite (high)",
 	},
-	"nova-2-pro-preview-low": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 31.9,
-		normalizedScore: 46,
-
+	"nova-2.0-pro-preview-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 24.5,
-		mathIndex: 63.3,
+		codingIndex: 20.5,
+		mathIndex: 30.7,
 
 		// Academic benchmarks
-		mmluPro: 0.822,
-		gpqa: 0.751,
-		hle: 0.052,
+		mmluPro: 0.772,
+		gpqa: 0.636,
+		hle: 0.04,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1675,21 +1485,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Pro Preview (Non-reasoning)",
 	},
-	"nova-2-omni-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16.6,
-		normalizedScore: 24,
-
+	"nova-2.0-lite-low": {
 		// AA specific benchmarks
-		codingIndex: 13.8,
-		mathIndex: 37,
+		codingIndex: 13.6,
+		mathIndex: 46.7,
 
 		// Academic benchmarks
-		mmluPro: 0.719,
-		gpqa: 0.555,
-		hle: 0.039,
+		mmluPro: 0.788,
+		gpqa: 0.698,
+		hle: 0.042,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1697,13 +1504,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Lite (low)",
 	},
-	"nova-2-lite-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 18,
-		normalizedScore: 26,
-
+	"nova-2.0-lite-non-reasoning": {
 		// AA specific benchmarks
 		codingIndex: 12.5,
 		mathIndex: 33.7,
@@ -1719,21 +1523,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Lite (Non-reasoning)",
 	},
-	"nova-2-omni-medium": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 28,
-		normalizedScore: 40,
-
+	"nova-premier": {
 		// AA specific benchmarks
-		codingIndex: 15.1,
-		mathIndex: 89.7,
+		codingIndex: 13.8,
+		mathIndex: 17.3,
 
 		// Academic benchmarks
-		mmluPro: 0.809,
-		gpqa: 0.76,
-		hle: 0.068,
+		mmluPro: 0.733,
+		gpqa: 0.569,
+		hle: 0.047,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1741,21 +1542,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova Premier",
 	},
-	"nova-2-pro-preview-medium": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 35.7,
-		normalizedScore: 51,
-
+	"nova-2.0-omni-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 30.4,
-		mathIndex: 89,
+		codingIndex: 13.8,
+		mathIndex: 37,
 
 		// Academic benchmarks
-		mmluPro: 0.83,
-		gpqa: 0.785,
-		hle: 0.089,
+		mmluPro: 0.719,
+		gpqa: 0.555,
+		hle: 0.039,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1763,21 +1561,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Omni (Non-reasoning)",
 	},
-	"nova-2-omni-low": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 23.2,
-		normalizedScore: 33,
-
+	"nova-2.0-omni-medium": {
 		// AA specific benchmarks
-		codingIndex: 13.9,
-		mathIndex: 56,
+		codingIndex: 15.1,
+		mathIndex: 89.7,
 
 		// Academic benchmarks
-		mmluPro: 0.798,
-		gpqa: 0.699,
-		hle: 0.04,
+		mmluPro: 0.809,
+		gpqa: 0.76,
+		hle: 0.068,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1785,21 +1580,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Omni (medium)",
 	},
-	"phi-4": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.4,
-		normalizedScore: 15,
-
+	"nova-2.0-pro-preview-low": {
 		// AA specific benchmarks
-		codingIndex: 11.2,
-		mathIndex: 18,
+		codingIndex: 24.5,
+		mathIndex: 63.3,
 
 		// Academic benchmarks
-		mmluPro: 0.714,
-		gpqa: 0.575,
-		hle: 0.041,
+		mmluPro: 0.822,
+		gpqa: 0.751,
+		hle: 0.052,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1807,21 +1599,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova 2.0 Pro Preview (low)",
 	},
-	"phi-4-multimodal-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10,
-		normalizedScore: 14,
-
+	"phi-4": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 11.2,
+		mathIndex: 18,
 
 		// Academic benchmarks
-		mmluPro: 0.485,
-		gpqa: 0.315,
-		hle: 0.044,
+		mmluPro: 0.714,
+		gpqa: 0.575,
+		hle: 0.041,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1829,13 +1618,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Phi-4",
 	},
 	"phi-4-mini-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.4,
-		normalizedScore: 12,
-
 		// AA specific benchmarks
 		codingIndex: 3.6,
 		mathIndex: 6.7,
@@ -1851,43 +1637,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Phi-4 Mini Instruct",
 	},
-	"lfm2.5-1.2b-thinking": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.1,
-		normalizedScore: 12,
-
+	"phi-4-multimodal-instruct": {
 		// AA specific benchmarks
-		codingIndex: 1.4,
+		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.339,
-		hle: 0.061,
-
-		// Capabilities
-		contextWindow: 8192,
-		supportsReasoning: false,
-		supportsVision: false,
-
-		// Metadata
-		lastUpdated: "2026-04-06",
-	},
-	"lfm2-8b-a1b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 7,
-		normalizedScore: 10,
-
-		// AA specific benchmarks
-		codingIndex: 2.3,
-		mathIndex: 25.3,
-
-		// Academic benchmarks
-		mmluPro: 0.505,
-		gpqa: 0.344,
-		hle: 0.049,
+		mmluPro: 0.485,
+		gpqa: 0.315,
+		hle: 0.044,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1895,21 +1656,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Phi-4 Multimodal Instruct",
 	},
-	"lfm2.5-1.2b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8,
-		normalizedScore: 11,
-
+	"lfm2.5-vl-1.6b": {
 		// AA specific benchmarks
-		codingIndex: 0.8,
+		codingIndex: 1,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.326,
-		hle: 0.068,
+		gpqa: 0.289,
+		hle: 0.051,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1917,13 +1675,10 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "LFM2.5-VL-1.6B",
 	},
 	"lfm2-24b-a2b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.5,
-		normalizedScore: 15,
-
 		// AA specific benchmarks
 		codingIndex: 3.6,
 		mathIndex: undefined,
@@ -1939,65 +1694,18 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
-	},
-	"lfm2-2.6b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8,
-		normalizedScore: 11,
-
-		// AA specific benchmarks
-		codingIndex: 1.4,
-		mathIndex: 8.3,
-
-		// Academic benchmarks
-		mmluPro: 0.298,
-		gpqa: 0.306,
-		hle: 0.052,
-
-		// Capabilities
-		contextWindow: 8192,
-		supportsReasoning: false,
-		supportsVision: false,
-
-		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "LFM2 24B A2B",
 	},
-	"lfm2.5-vl-1.6b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 6.2,
-		normalizedScore: 9,
-
-		// AA specific benchmarks
-		codingIndex: 1,
-		mathIndex: undefined,
-
-		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.289,
-		hle: 0.051,
-
-		// Capabilities
-		contextWindow: 8192,
-		supportsReasoning: false,
-		supportsVision: false,
-
-		// Metadata
-		lastUpdated: "2026-04-06",
-	},
-	"solar-open-100b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 21.7,
-		normalizedScore: 31,
-
+	"lfm2-8b-a1b": {
 		// AA specific benchmarks
-		codingIndex: 10.5,
-		mathIndex: undefined,
+		codingIndex: 2.3,
+		mathIndex: 25.3,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.657,
-		hle: 0.092,
+		mmluPro: 0.505,
+		gpqa: 0.344,
+		hle: 0.049,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -2005,6 +1713,7 @@ export const BENCHMARKS_CHUNK_0: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "LFM2 8B A1B",
 	},
 };