pi-free 2.0.13 → 2.0.15

package/provider-failover/benchmarks-chunk-4.ts

@@ -1,23 +1,20 @@
 // Auto-generated benchmark data chunk 4
-// Models: lfm-40b .. seed-oss-36b-instruct (89 entries)
+// Models: mistral-medium-3.1 .. glm-4.5v-reasoning (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_4: Record<string, HardcodedBenchmark> = {
-	"lfm-40b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.8,
-		normalizedScore: 13,
-
+	"mistral-medium-3.1": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 18.3,
+		mathIndex: 38.3,
 
 		// Academic benchmarks
-		mmluPro: 0.425,
-		gpqa: 0.327,
-		hle: 0.049,
+		mmluPro: 0.683,
+		gpqa: 0.588,
+		hle: 0.044,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -25,21 +22,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Mistral Medium 3.1",
 	},
-	"lfm2-1.2b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 6.3,
-		normalizedScore: 9,
-
+	"deepseek-r1-distill-llama-70b": {
 		// AA specific benchmarks
-		codingIndex: 0.8,
-		mathIndex: 3.3,
+		codingIndex: 11.4,
+		mathIndex: 53.7,
 
 		// Academic benchmarks
-		mmluPro: 0.257,
-		gpqa: 0.228,
-		hle: 0.057,
+		mmluPro: 0.795,
+		gpqa: 0.402,
+		hle: 0.061,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -47,21 +41,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek R1 Distill Llama 70B",
 	},
-	"solar-mini": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 11.9,
-		normalizedScore: 17,
-
+	"deepseek-r1-distill-qwen-32b": {
 		// AA specific benchmarks
 		codingIndex: undefined,
-		mathIndex: undefined,
+		mathIndex: 63,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: undefined,
-		hle: undefined,
+		mmluPro: 0.739,
+		gpqa: 0.615,
+		hle: 0.055,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -69,21 +60,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek R1 Distill Qwen 32B",
 	},
-	"solar-pro-2-preview-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16,
-		normalizedScore: 23,
-
+	"deepseek-v3-dec-24": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 16.4,
+		mathIndex: 26,
 
 		// Academic benchmarks
-		mmluPro: 0.725,
-		gpqa: 0.544,
-		hle: 0.038,
+		mmluPro: 0.752,
+		gpqa: 0.557,
+		hle: 0.036,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -91,21 +79,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3 (Dec '24)",
 	},
-	"solar-pro-2-preview-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 18.8,
-		normalizedScore: 27,
-
+	"deepseek-r1-distill-qwen-14b": {
 		// AA specific benchmarks
 		codingIndex: undefined,
-		mathIndex: undefined,
+		mathIndex: 55.7,
 
 		// Academic benchmarks
-		mmluPro: 0.768,
-		gpqa: 0.578,
-		hle: 0.057,
+		mmluPro: 0.74,
+		gpqa: 0.484,
+		hle: 0.044,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -113,21 +98,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek R1 Distill Qwen 14B",
 	},
-	"dbrx-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.3,
-		normalizedScore: 12,
-
+	"deepseek-v2.5-dec-24": {
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.397,
-		gpqa: 0.331,
-		hle: 0.066,
+		mmluPro: undefined,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -135,21 +117,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek-V2.5 (Dec '24)",
 	},
-	"minimax-m2.5": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 41.9,
-		normalizedScore: 60,
-
+	"deepseek-coder-v2": {
 		// AA specific benchmarks
-		codingIndex: 37.4,
+		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
 		mmluPro: undefined,
-		gpqa: 0.848,
-		hle: 0.191,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -157,21 +136,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek-Coder-V2",
 	},
-	"minimax-m2.1": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 39.4,
-		normalizedScore: 56,
-
+	"deepseek-r1-distill-llama-8b": {
 		// AA specific benchmarks
-		codingIndex: 32.8,
-		mathIndex: 82.7,
+		codingIndex: undefined,
+		mathIndex: 41.3,
 
 		// Academic benchmarks
-		mmluPro: 0.875,
-		gpqa: 0.83,
-		hle: 0.222,
+		mmluPro: 0.543,
+		gpqa: 0.302,
+		hle: 0.042,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -179,21 +155,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek R1 Distill Llama 8B",
 	},
-	"minimax-m1-80k": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 24.4,
-		normalizedScore: 35,
-
+	"deepseek-llm-67b-chat-v1": {
 		// AA specific benchmarks
-		codingIndex: 14.5,
-		mathIndex: 61,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.816,
-		gpqa: 0.697,
-		hle: 0.082,
+		mmluPro: undefined,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -201,21 +174,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek LLM 67B Chat (V1)",
 	},
-	"minimax-m2": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 36.1,
-		normalizedScore: 52,
-
+	"deepseek-r1-distill-qwen-1.5b": {
 		// AA specific benchmarks
-		codingIndex: 29.2,
-		mathIndex: 78.3,
+		codingIndex: undefined,
+		mathIndex: 22,
 
 		// Academic benchmarks
-		mmluPro: 0.82,
-		gpqa: 0.777,
-		hle: 0.125,
+		mmluPro: 0.269,
+		gpqa: 0.098,
+		hle: 0.033,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -223,21 +193,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek R1 Distill Qwen 1.5B",
 	},
-	"minimax-m1-40k": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 20.9,
-		normalizedScore: 30,
-
+	"deepseek-v3-0324": {
 		// AA specific benchmarks
-		codingIndex: 14.1,
-		mathIndex: 13.7,
+		codingIndex: 22,
+		mathIndex: 41,
 
 		// Academic benchmarks
-		mmluPro: 0.808,
-		gpqa: 0.682,
-		hle: 0.075,
+		mmluPro: 0.819,
+		gpqa: 0.655,
+		hle: 0.052,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -245,21 +212,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3 0324",
 	},
-	"kimi-k2-thinking": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 40.9,
-		normalizedScore: 58,
-
+	"deepseek-v3.2-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 34.8,
-		mathIndex: 94.7,
+		codingIndex: 36.7,
+		mathIndex: 92,
 
 		// Academic benchmarks
-		mmluPro: 0.848,
-		gpqa: 0.838,
-		hle: 0.223,
+		mmluPro: 0.862,
+		gpqa: 0.84,
+		hle: 0.222,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -267,21 +231,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.2 (Reasoning)",
 	},
-	"kimi-k2-0905": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 30.9,
-		normalizedScore: 44,
-
+	"deepseek-v3.2-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 25.9,
-		mathIndex: 57.3,
+		codingIndex: 34.6,
+		mathIndex: 59,
 
 		// Academic benchmarks
-		mmluPro: 0.819,
-		gpqa: 0.767,
-		hle: 0.063,
+		mmluPro: 0.837,
+		gpqa: 0.751,
+		hle: 0.105,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -289,21 +250,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.2 (Non-reasoning)",
 	},
-	"kimi-k2": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 26.3,
-		normalizedScore: 38,
-
+	"deepseek-r1-jan-25": {
 		// AA specific benchmarks
-		codingIndex: 22.1,
-		mathIndex: 57,
+		codingIndex: 15.9,
+		mathIndex: 68,
 
 		// Academic benchmarks
-		mmluPro: 0.824,
-		gpqa: 0.766,
-		hle: 0.07,
+		mmluPro: 0.844,
+		gpqa: 0.708,
+		hle: 0.093,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -311,21 +269,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek R1 (Jan '25)",
 	},
-	"llama-3.1-tulu3-405b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 14.1,
-		normalizedScore: 20,
-
+	"deepseek-v3.1-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 28.4,
+		mathIndex: 49.7,
 
 		// Academic benchmarks
-		mmluPro: 0.716,
-		gpqa: 0.516,
-		hle: 0.035,
+		mmluPro: 0.833,
+		gpqa: 0.735,
+		hle: 0.063,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -333,21 +288,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.1 (Non-reasoning)",
 	},
-	"olmo-2-7b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 9.3,
-		normalizedScore: 13,
-
+	"deepseek-r1-0528-may-25": {
 		// AA specific benchmarks
-		codingIndex: 1.2,
-		mathIndex: 0.7,
+		codingIndex: 24,
+		mathIndex: 76,
 
 		// Academic benchmarks
-		mmluPro: 0.282,
-		gpqa: 0.288,
-		hle: 0.055,
+		mmluPro: 0.849,
+		gpqa: 0.813,
+		hle: 0.149,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -355,21 +307,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek R1 0528 (May '25)",
 	},
-	"olmo-2-32b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.6,
-		normalizedScore: 15,
-
+	"deepseek-v3.1-terminus-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 2.7,
-		mathIndex: 3.3,
+		codingIndex: 31.9,
+		mathIndex: 53.7,
 
 		// Academic benchmarks
-		mmluPro: 0.511,
-		gpqa: 0.328,
-		hle: 0.037,
+		mmluPro: 0.836,
+		gpqa: 0.751,
+		hle: 0.084,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -377,21 +326,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.1 Terminus (Non-reasoning)",
 	},
-	"olmo-3-32b-think": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12.1,
-		normalizedScore: 17,
-
+	"deepseek-v3.1-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 10.5,
-		mathIndex: 73.7,
+		codingIndex: 29.7,
+		mathIndex: 89.7,
 
 		// Academic benchmarks
-		mmluPro: 0.759,
-		gpqa: 0.61,
-		hle: 0.059,
+		mmluPro: 0.851,
+		gpqa: 0.779,
+		hle: 0.13,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -399,21 +345,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.1 (Reasoning)",
 	},
-	"granite-3.3-8b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 7,
-		normalizedScore: 10,
-
+	"deepseek-v3.1-terminus-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 3.4,
-		mathIndex: 6.7,
+		codingIndex: 33.7,
+		mathIndex: 89.7,
 
 		// Academic benchmarks
-		mmluPro: 0.468,
-		gpqa: 0.338,
-		hle: 0.042,
+		mmluPro: 0.851,
+		gpqa: 0.792,
+		hle: 0.152,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -421,13 +364,29 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.1 Terminus (Reasoning)",
 	},
-	"reka-flash-sep-24": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12,
-		normalizedScore: 17,
+	"deepseek-v3.2-exp-non-reasoning": {
+		// AA specific benchmarks
+		codingIndex: 30,
+		mathIndex: 57.7,
+
+		// Academic benchmarks
+		mmluPro: 0.836,
+		gpqa: 0.738,
+		hle: 0.086,
+
+		// Capabilities
+		contextWindow: 8192,
+		supportsReasoning: false,
+		supportsVision: false,
 
+		// Metadata
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.2 Exp (Non-reasoning)",
+	},
+	"deepseek-v2.5": {
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
@@ -443,21 +402,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek-V2.5",
 	},
-	"hermes-3---llama-3.1-70b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.6,
-		normalizedScore: 15,
-
+	"deepseek-coder-v2-lite-instruct": {
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.571,
-		gpqa: 0.401,
-		hle: 0.041,
+		mmluPro: 0.429,
+		gpqa: 0.319,
+		hle: 0.053,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -465,21 +421,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek Coder V2 Lite Instruct",
 	},
-	"mimo-v2-flash-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 39.2,
-		normalizedScore: 56,
-
+	"deepseek-r1-0528-qwen3-8b": {
 		// AA specific benchmarks
-		codingIndex: 31.8,
-		mathIndex: 96.3,
+		codingIndex: 7.8,
+		mathIndex: 63.7,
 
 		// Academic benchmarks
-		mmluPro: 0.843,
-		gpqa: 0.846,
-		hle: 0.211,
+		mmluPro: 0.739,
+		gpqa: 0.612,
+		hle: 0.056,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -487,21 +440,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek R1 0528 Qwen3 8B",
 	},
-	"sarvam-m-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.4,
-		normalizedScore: 12,
-
+	"deepseek-v3.2-exp-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 7.5,
-		mathIndex: undefined,
+		codingIndex: 33.3,
+		mathIndex: 87.7,
 
 		// Academic benchmarks
-		mmluPro: 0.696,
-		gpqa: 0.416,
-		hle: 0.033,
+		mmluPro: 0.85,
+		gpqa: 0.797,
+		hle: 0.138,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -509,21 +459,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.2 Exp (Reasoning)",
 	},
-	"glm-4.6-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 30.2,
-		normalizedScore: 43,
-
+	"deepseek-v3.2-speciale": {
 		// AA specific benchmarks
-		codingIndex: 30.2,
-		mathIndex: 44.3,
+		codingIndex: 37.9,
+		mathIndex: 96.7,
 
 		// Academic benchmarks
-		mmluPro: 0.784,
-		gpqa: 0.632,
-		hle: 0.052,
+		mmluPro: 0.863,
+		gpqa: 0.871,
+		hle: 0.261,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -531,21 +478,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek V3.2 Speciale",
 	},
-	"glm-4.7-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 42.1,
-		normalizedScore: 60,
-
+	"deepseek-v2-chat": {
 		// AA specific benchmarks
-		codingIndex: 36.3,
-		mathIndex: 95,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.856,
-		gpqa: 0.859,
-		hle: 0.251,
+		mmluPro: undefined,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -553,21 +497,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DeepSeek-V2-Chat",
 	},
-	"glm-4.7-flash-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 22.1,
-		normalizedScore: 32,
-
+	"sonar-pro": {
 		// AA specific benchmarks
-		codingIndex: 11,
+		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.452,
-		hle: 0.049,
+		mmluPro: 0.755,
+		gpqa: 0.578,
+		hle: 0.079,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -575,21 +516,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Sonar Pro",
 	},
-	"glm-4.7-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 34.2,
-		normalizedScore: 49,
-
+	"sonar-reasoning-pro": {
 		// AA specific benchmarks
-		codingIndex: 32,
-		mathIndex: 48,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.794,
-		gpqa: 0.664,
-		hle: 0.061,
+		mmluPro: undefined,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -597,21 +535,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Sonar Reasoning Pro",
 	},
-	"glm-4.5v-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12.7,
-		normalizedScore: 18,
-
+	"sonar-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 10.8,
-		mathIndex: 15.3,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.751,
-		gpqa: 0.573,
-		hle: 0.036,
+		mmluPro: undefined,
+		gpqa: 0.623,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -619,21 +554,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Sonar Reasoning",
 	},
-	"glm-4.5-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 26.4,
-		normalizedScore: 38,
-
+	"sonar": {
 		// AA specific benchmarks
-		codingIndex: 26.3,
-		mathIndex: 73.7,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.835,
-		gpqa: 0.782,
-		hle: 0.122,
+		mmluPro: 0.689,
+		gpqa: 0.471,
+		hle: 0.073,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -641,21 +573,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Sonar",
 	},
-	"glm-4.6-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 32.5,
-		normalizedScore: 46,
-
+	"grok-beta": {
 		// AA specific benchmarks
-		codingIndex: 29.5,
-		mathIndex: 86,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.829,
-		gpqa: 0.78,
-		hle: 0.133,
+		mmluPro: 0.703,
+		gpqa: 0.471,
+		hle: 0.047,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -663,21 +592,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok Beta",
 	},
-	"glm-4.7-flash-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 30.1,
-		normalizedScore: 43,
-
+	"grok-3": {
 		// AA specific benchmarks
-		codingIndex: 25.9,
-		mathIndex: undefined,
+		codingIndex: 19.8,
+		mathIndex: 58,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.581,
-		hle: 0.071,
+		mmluPro: 0.799,
+		gpqa: 0.693,
+		hle: 0.051,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -685,21 +611,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 3",
 	},
-	"glm-4.5v-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 15.1,
-		normalizedScore: 22,
-
+	"grok-3-mini-reasoning-high": {
 		// AA specific benchmarks
-		codingIndex: 10.9,
-		mathIndex: 73,
+		codingIndex: 25.2,
+		mathIndex: 84.7,
 
 		// Academic benchmarks
-		mmluPro: 0.788,
-		gpqa: 0.684,
-		hle: 0.059,
+		mmluPro: 0.828,
+		gpqa: 0.791,
+		hle: 0.111,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -707,21 +630,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 3 mini Reasoning (high)",
 	},
-	"glm-4.5-air": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 23.2,
-		normalizedScore: 33,
-
+	"grok-4.20-0309-v2-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 23.8,
-		mathIndex: 80.7,
+		codingIndex: 40.5,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.815,
-		gpqa: 0.733,
-		hle: 0.068,
+		mmluPro: undefined,
+		gpqa: 0.911,
+		hle: 0.322,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -729,21 +649,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.20 0309 v2 (Reasoning)",
 	},
-	"command-r-apr-24": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.3,
-		normalizedScore: 12,
-
+	"grok-4": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 40.5,
+		mathIndex: 92.7,
 
 		// Academic benchmarks
-		mmluPro: 0.432,
-		gpqa: 0.323,
-		hle: 0.045,
+		mmluPro: 0.866,
+		gpqa: 0.877,
+		hle: 0.239,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -751,21 +668,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4",
 	},
-	"command-r-mar-24": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 7.4,
-		normalizedScore: 11,
-
+	"grok-4-fast-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 19,
+		mathIndex: 41.3,
 
 		// Academic benchmarks
-		mmluPro: 0.338,
-		gpqa: 0.284,
-		hle: 0.048,
+		mmluPro: 0.73,
+		gpqa: 0.606,
+		hle: 0.05,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -773,21 +687,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4 Fast (Non-reasoning)",
 	},
-	"apriel-v1.5-15b-thinker": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 28.3,
-		normalizedScore: 40,
-
+	"grok-4-fast-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 18.7,
-		mathIndex: 87.5,
+		codingIndex: 27.4,
+		mathIndex: 89.7,
 
 		// Academic benchmarks
-		mmluPro: 0.773,
-		gpqa: 0.713,
-		hle: 0.12,
+		mmluPro: 0.85,
+		gpqa: 0.847,
+		hle: 0.17,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -795,21 +706,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4 Fast (Reasoning)",
 	},
-	"jamba-1.6-large": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.6,
-		normalizedScore: 15,
-
+	"grok-code-fast-1": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 23.7,
+		mathIndex: 43.3,
 
 		// Academic benchmarks
-		mmluPro: 0.565,
-		gpqa: 0.387,
-		hle: 0.04,
+		mmluPro: 0.793,
+		gpqa: 0.727,
+		hle: 0.075,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -817,21 +725,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok Code Fast 1",
 	},
-	"jamba-1.5-large": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.7,
-		normalizedScore: 15,
-
+	"grok-3-reasoning-beta": {
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.572,
-		gpqa: 0.427,
-		hle: 0.04,
+		mmluPro: undefined,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -839,21 +744,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 3 Reasoning Beta",
 	},
-	"jamba-1.5-mini": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8,
-		normalizedScore: 11,
-
+	"grok-4.20-0309-reasoning": {
 		// AA specific benchmarks
-		codingIndex: undefined,
+		codingIndex: 42.2,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.371,
-		gpqa: 0.302,
-		hle: 0.051,
+		mmluPro: undefined,
+		gpqa: 0.885,
+		hle: 0.3,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -861,21 +763,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.20 0309 (Reasoning)",
 	},
-	"jamba-1.6-mini": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 7.9,
-		normalizedScore: 11,
-
+	"grok-4.1-fast-reasoning": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 30.9,
+		mathIndex: 89.3,
 
 		// Academic benchmarks
-		mmluPro: 0.367,
-		gpqa: 0.3,
-		hle: 0.046,
+		mmluPro: 0.854,
+		gpqa: 0.853,
+		hle: 0.176,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -883,21 +782,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.1 Fast (Reasoning)",
 	},
-	"arctic-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.8,
-		normalizedScore: 13,
-
+	"grok-2-dec-24": {
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: undefined,
-		hle: undefined,
+		mmluPro: 0.709,
+		gpqa: 0.51,
+		hle: 0.038,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -905,21 +801,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 2 (Dec '24)",
 	},
-	"qwen2.5-max": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16.3,
-		normalizedScore: 23,
-
+	"grok-4.1-fast-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 19.5,
+		mathIndex: 34.3,
 
 		// Academic benchmarks
-		mmluPro: 0.762,
-		gpqa: 0.587,
-		hle: 0.045,
+		mmluPro: 0.743,
+		gpqa: 0.637,
+		hle: 0.05,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -927,21 +820,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.1 Fast (Non-reasoning)",
 	},
-	"qwen2.5-instruct-72b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 15.6,
-		normalizedScore: 22,
-
+	"grok-4.20-0309-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 11.9,
-		mathIndex: 14,
+		codingIndex: 25.4,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.72,
-		gpqa: 0.491,
-		hle: 0.042,
+		mmluPro: undefined,
+		gpqa: 0.785,
+		hle: 0.225,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -949,21 +839,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.20 0309 (Non-reasoning)",
 	},
-	"qwen2.5-coder-instruct-32b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12.9,
-		normalizedScore: 18,
-
+	"grok-4.20-0309-v2-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: undefined,
+		codingIndex: 22,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.635,
-		gpqa: 0.417,
-		hle: 0.038,
+		mmluPro: undefined,
+		gpqa: 0.776,
+		hle: 0.242,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -971,21 +858,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Grok 4.20 0309 v2 (Non-reasoning)",
 	},
-	"qwen2.5-turbo": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12,
-		normalizedScore: 17,
-
+	"openchat-3.5-1210": {
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.633,
-		gpqa: 0.41,
-		hle: 0.042,
+		mmluPro: 0.31,
+		gpqa: 0.23,
+		hle: 0.048,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -993,21 +877,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "OpenChat 3.5 (1210)",
 	},
-	"qwen2-instruct-72b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 11.7,
-		normalizedScore: 17,
-
+	"nova-pro": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 11,
+		mathIndex: 7,
 
 		// Academic benchmarks
-		mmluPro: 0.622,
-		gpqa: 0.371,
-		hle: 0.037,
+		mmluPro: 0.691,
+		gpqa: 0.499,
+		hle: 0.034,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1015,21 +896,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova Pro",
 	},
-	"qwen3-vl-30b-a3b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16.1,
-		normalizedScore: 23,
-
+	"nova-lite": {
 		// AA specific benchmarks
-		codingIndex: 14.3,
-		mathIndex: 72.3,
+		codingIndex: 5.1,
+		mathIndex: 7,
 
 		// Academic benchmarks
-		mmluPro: 0.764,
-		gpqa: 0.695,
-		hle: 0.064,
+		mmluPro: 0.59,
+		gpqa: 0.433,
+		hle: 0.046,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1037,21 +915,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Nova Lite",
 	},
-	"qwen3-235b-a22b-2507-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 25,
-		normalizedScore: 36,
-
+	"phi-3-mini-instruct-3.8b": {
 		// AA specific benchmarks
-		codingIndex: 22.1,
-		mathIndex: 71.7,
+		codingIndex: 3,
+		mathIndex: 0.3,
 
 		// Academic benchmarks
-		mmluPro: 0.828,
-		gpqa: 0.753,
-		hle: 0.106,
+		mmluPro: 0.435,
+		gpqa: 0.319,
+		hle: 0.044,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1059,21 +934,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Phi-3 Mini Instruct 3.8B",
 	},
-	"qwen3-32b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 14.5,
-		normalizedScore: 21,
-
+	"lfm-40b": {
 		// AA specific benchmarks
 		codingIndex: undefined,
-		mathIndex: 19.7,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.727,
-		gpqa: 0.535,
-		hle: 0.043,
+		mmluPro: 0.425,
+		gpqa: 0.327,
+		hle: 0.049,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1081,21 +953,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "LFM 40B",
 	},
-	"qwen3-235b-a22b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 19.8,
-		normalizedScore: 28,
-
+	"lfm2-1.2b": {
 		// AA specific benchmarks
-		codingIndex: 17.4,
-		mathIndex: 82,
+		codingIndex: 0.8,
+		mathIndex: 3.3,
 
 		// Academic benchmarks
-		mmluPro: 0.828,
-		gpqa: 0.7,
-		hle: 0.117,
+		mmluPro: 0.257,
+		gpqa: 0.228,
+		hle: 0.057,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1103,21 +972,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "LFM2 1.2B",
 	},
-	"qwen3-235b-a22b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 17,
-		normalizedScore: 24,
-
+	"solar-mini": {
 		// AA specific benchmarks
-		codingIndex: 14,
-		mathIndex: 23.7,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.762,
-		gpqa: 0.613,
-		hle: 0.047,
+		mmluPro: undefined,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1125,21 +991,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Solar Mini",
 	},
-	"qwen3-30b-a3b-2507-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 22.4,
-		normalizedScore: 32,
-
+	"solar-pro-2-preview-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 14.7,
-		mathIndex: 56.3,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.805,
-		gpqa: 0.707,
-		hle: 0.098,
+		mmluPro: 0.768,
+		gpqa: 0.578,
+		hle: 0.057,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1147,21 +1010,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Solar Pro 2 (Preview) (Reasoning)",
 	},
-	"qwen3-vl-235b-a22b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 20.8,
-		normalizedScore: 30,
-
+	"solar-pro-2-preview-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 16.5,
-		mathIndex: 70.7,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.823,
-		gpqa: 0.712,
-		hle: 0.063,
+		mmluPro: 0.725,
+		gpqa: 0.544,
+		hle: 0.038,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1169,21 +1029,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Solar Pro 2 (Preview) (Non-reasoning)",
 	},
-	"qwen3-0.6b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 6.5,
-		normalizedScore: 9,
-
+	"dbrx-instruct": {
 		// AA specific benchmarks
-		codingIndex: 0.9,
-		mathIndex: 18,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.347,
-		gpqa: 0.239,
-		hle: 0.057,
+		mmluPro: 0.397,
+		gpqa: 0.331,
+		hle: 0.066,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1191,21 +1048,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "DBRX Instruct",
 	},
-	"qwen3-235b-a22b-2507-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 29.5,
-		normalizedScore: 42,
-
+	"minimax-m2.1": {
 		// AA specific benchmarks
-		codingIndex: 23.2,
-		mathIndex: 91,
+		codingIndex: 32.8,
+		mathIndex: 82.7,
 
 		// Academic benchmarks
-		mmluPro: 0.843,
-		gpqa: 0.79,
-		hle: 0.15,
+		mmluPro: 0.875,
+		gpqa: 0.83,
+		hle: 0.222,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1213,21 +1067,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "MiniMax-M2.1",
 	},
-	"qwen3-8b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10.6,
-		normalizedScore: 15,
-
+	"minimax-m2.5": {
 		// AA specific benchmarks
-		codingIndex: 7.1,
-		mathIndex: 24.3,
+		codingIndex: 37.4,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.643,
-		gpqa: 0.452,
-		hle: 0.028,
+		mmluPro: undefined,
+		gpqa: 0.848,
+		hle: 0.191,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1235,21 +1086,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "MiniMax-M2.5",
 	},
-	"qwen3-4b-2507-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 18.2,
-		normalizedScore: 26,
-
+	"minimax-m2": {
 		// AA specific benchmarks
-		codingIndex: 9.5,
-		mathIndex: 82.7,
+		codingIndex: 29.2,
+		mathIndex: 78.3,
 
 		// Academic benchmarks
-		mmluPro: 0.743,
-		gpqa: 0.667,
-		hle: 0.059,
+		mmluPro: 0.82,
+		gpqa: 0.777,
+		hle: 0.125,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1257,20 +1105,17 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "MiniMax-M2",
 	},
-	"qwq-32b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 19.7,
-		normalizedScore: 28,
-
+	"minimax-m1-80k": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: 29,
+		codingIndex: 14.5,
+		mathIndex: 61,
 
 		// Academic benchmarks
-		mmluPro: 0.764,
-		gpqa: 0.593,
+		mmluPro: 0.816,
+		gpqa: 0.697,
 		hle: 0.082,
 
 		// Capabilities
@@ -1279,21 +1124,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "MiniMax M1 80k",
 	},
-	"qwen3-32b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16.5,
-		normalizedScore: 24,
-
+	"minimax-m1-40k": {
 		// AA specific benchmarks
-		codingIndex: 13.8,
-		mathIndex: 73,
+		codingIndex: 14.1,
+		mathIndex: 13.7,
 
 		// Academic benchmarks
-		mmluPro: 0.798,
-		gpqa: 0.668,
-		hle: 0.083,
+		mmluPro: 0.808,
+		gpqa: 0.682,
+		hle: 0.075,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1301,21 +1143,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "MiniMax M1 40k",
 	},
-	"qwen3-4b-2507-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12.9,
-		normalizedScore: 18,
-
+	"llama-3.3-nemotron-super-49b-v1-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 9.1,
-		mathIndex: 52.3,
+		codingIndex: 9.4,
+		mathIndex: 54.7,
 
 		// Academic benchmarks
-		mmluPro: 0.672,
-		gpqa: 0.517,
-		hle: 0.047,
+		mmluPro: 0.785,
+		gpqa: 0.643,
+		hle: 0.065,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1323,21 +1162,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 3.3 Nemotron Super 49B v1 (Reasoning)",
 	},
-	"qwen3-30b-a3b-2507-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 15,
-		normalizedScore: 21,
-
+	"llama-3.3-nemotron-super-49b-v1-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 14.2,
-		mathIndex: 66.3,
+		codingIndex: 7.6,
+		mathIndex: 7.7,
 
 		// Academic benchmarks
-		mmluPro: 0.777,
-		gpqa: 0.659,
-		hle: 0.068,
+		mmluPro: 0.698,
+		gpqa: 0.517,
+		hle: 0.035,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1345,21 +1181,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)",
 	},
-	"qwen3-14b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12.8,
-		normalizedScore: 18,
-
+	"llama-3.1-nemotron-nano-4b-v1.1-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 12.4,
-		mathIndex: 58,
+		codingIndex: undefined,
+		mathIndex: 50,
 
 		// Academic benchmarks
-		mmluPro: 0.675,
-		gpqa: 0.47,
-		hle: 0.042,
+		mmluPro: 0.556,
+		gpqa: 0.408,
+		hle: 0.051,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1367,21 +1200,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)",
 	},
-	"qwen3-vl-4b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 9.6,
-		normalizedScore: 14,
-
+	"kimi-k2.5-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 4.5,
-		mathIndex: 37,
+		codingIndex: 39.6,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.634,
-		gpqa: 0.371,
-		hle: 0.037,
+		mmluPro: undefined,
+		gpqa: 0.879,
+		hle: 0.294,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1389,21 +1219,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Kimi K2.5 (Reasoning)",
 	},
-	"qwen2.5-coder-instruct-7b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 10,
-		normalizedScore: 14,
-
+	"kimi-k2-0905": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 25.9,
+		mathIndex: 57.3,
 
 		// Academic benchmarks
-		mmluPro: 0.473,
-		gpqa: 0.339,
-		hle: 0.048,
+		mmluPro: 0.819,
+		gpqa: 0.767,
+		hle: 0.063,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1411,21 +1238,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Kimi K2 0905",
 	},
-	"qwen3-30b-a3b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 15.3,
-		normalizedScore: 22,
-
+	"kimi-k2": {
 		// AA specific benchmarks
-		codingIndex: 11,
-		mathIndex: 72.3,
+		codingIndex: 22.1,
+		mathIndex: 57,
 
 		// Academic benchmarks
-		mmluPro: 0.777,
-		gpqa: 0.616,
-		hle: 0.066,
+		mmluPro: 0.824,
+		gpqa: 0.766,
+		hle: 0.07,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1433,21 +1257,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Kimi K2",
 	},
-	"qwq-32b-preview": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 15.2,
-		normalizedScore: 22,
-
+	"kimi-k2-thinking": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 34.8,
+		mathIndex: 94.7,
 
 		// Academic benchmarks
-		mmluPro: 0.648,
-		gpqa: 0.557,
-		hle: 0.048,
+		mmluPro: 0.848,
+		gpqa: 0.838,
+		hle: 0.223,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1455,21 +1276,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Kimi K2 Thinking",
 	},
-	"qwen3-vl-32b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 17.2,
-		normalizedScore: 25,
-
+	"kimi-k2.5-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 15.6,
-		mathIndex: 68.3,
+		codingIndex: 25.8,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.791,
-		gpqa: 0.671,
-		hle: 0.063,
+		mmluPro: undefined,
+		gpqa: 0.789,
+		hle: 0.123,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1477,21 +1295,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Kimi K2.5 (Non-reasoning)",
 	},
-	"qwen3-1.7b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 6.8,
-		normalizedScore: 10,
-
+	"step-3.5-flash": {
 		// AA specific benchmarks
-		codingIndex: 2.3,
-		mathIndex: 7.3,
+		codingIndex: 31.6,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.411,
-		gpqa: 0.283,
-		hle: 0.052,
+		mmluPro: undefined,
+		gpqa: 0.831,
+		hle: 0.191,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1499,21 +1314,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Step 3.5 Flash",
 	},
-	"qwen2.5-instruct-32b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 13.2,
-		normalizedScore: 19,
-
+	"llama-3.1-tulu3-405b": {
 		// AA specific benchmarks
 		codingIndex: undefined,
 		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.697,
-		gpqa: 0.466,
-		hle: 0.038,
+		mmluPro: 0.716,
+		gpqa: 0.516,
+		hle: 0.035,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1521,21 +1333,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Llama 3.1 Tulu3 405B",
 	},
-	"qwen3-4b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12.5,
-		normalizedScore: 18,
-
+	"olmo-2-7b": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 1.2,
+		mathIndex: 0.7,
 
 		// Academic benchmarks
-		mmluPro: 0.586,
-		gpqa: 0.398,
-		hle: 0.037,
+		mmluPro: 0.282,
+		gpqa: 0.288,
+		hle: 0.055,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1543,21 +1352,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "OLMo 2 7B",
 	},
-	"qwen3-vl-30b-a3b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 19.7,
-		normalizedScore: 28,
-
+	"olmo-3-32b-think": {
 		// AA specific benchmarks
-		codingIndex: 13.1,
-		mathIndex: 82.3,
+		codingIndex: 10.5,
+		mathIndex: 73.7,
 
 		// Academic benchmarks
-		mmluPro: 0.807,
-		gpqa: 0.72,
-		hle: 0.087,
+		mmluPro: 0.759,
+		gpqa: 0.61,
+		hle: 0.059,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1565,21 +1371,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Olmo 3 32B Think",
 	},
-	"qwen3-vl-8b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16.7,
-		normalizedScore: 24,
-
+	"olmo-2-32b": {
 		// AA specific benchmarks
-		codingIndex: 9.8,
-		mathIndex: 30.7,
+		codingIndex: 2.7,
+		mathIndex: 3.3,
 
 		// Academic benchmarks
-		mmluPro: 0.749,
-		gpqa: 0.579,
-		hle: 0.033,
+		mmluPro: 0.511,
+		gpqa: 0.328,
+		hle: 0.037,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1587,20 +1390,17 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "OLMo 2 32B",
 	},
-	"qwen3-8b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 13.2,
-		normalizedScore: 19,
-
+	"granite-3.3-8b-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 9,
-		mathIndex: 19,
+		codingIndex: 3.4,
+		mathIndex: 6.7,
 
 		// Academic benchmarks
-		mmluPro: 0.743,
-		gpqa: 0.589,
+		mmluPro: 0.468,
+		gpqa: 0.338,
 		hle: 0.042,
 
 		// Capabilities
@@ -1609,21 +1409,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Granite 3.3 8B (Non-reasoning)",
 	},
-	"qwen3-vl-235b-a22b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 27.6,
-		normalizedScore: 39,
-
+	"reka-flash-sep-24": {
 		// AA specific benchmarks
-		codingIndex: 20.9,
-		mathIndex: 88.3,
+		codingIndex: undefined,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.836,
-		gpqa: 0.772,
-		hle: 0.101,
+		mmluPro: undefined,
+		gpqa: undefined,
+		hle: undefined,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1631,21 +1428,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Reka Flash (Sep '24)",
 	},
-	"qwen3-4b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 14.2,
-		normalizedScore: 20,
-
+	"hermes-3---llama-3.1-70b": {
 		// AA specific benchmarks
 		codingIndex: undefined,
-		mathIndex: 22.3,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.696,
-		gpqa: 0.522,
-		hle: 0.051,
+		mmluPro: 0.571,
+		gpqa: 0.401,
+		hle: 0.041,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1653,21 +1447,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Hermes 3 - Llama-3.1 70B",
 	},
-	"qwen3-0.6b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 5.7,
-		normalizedScore: 8,
-
+	"mimo-v2-flash-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 1.4,
-		mathIndex: 10.3,
+		codingIndex: 31.8,
+		mathIndex: 96.3,
 
 		// Academic benchmarks
-		mmluPro: 0.231,
-		gpqa: 0.231,
-		hle: 0.052,
+		mmluPro: 0.843,
+		gpqa: 0.846,
+		hle: 0.211,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1675,21 +1466,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "MiMo-V2-Flash (Reasoning)",
 	},
-	"qwen3-30b-a3b-non-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 12.5,
-		normalizedScore: 18,
-
+	"mimo-v2-pro": {
 		// AA specific benchmarks
-		codingIndex: 13.3,
-		mathIndex: 21.7,
+		codingIndex: 41.4,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.71,
-		gpqa: 0.515,
-		hle: 0.046,
+		mmluPro: undefined,
+		gpqa: 0.87,
+		hle: 0.283,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1697,21 +1485,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "MiMo-V2-Pro",
 	},
-	"qwen3-14b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 16.2,
-		normalizedScore: 23,
-
+	"sarvam-m-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 13.1,
-		mathIndex: 55.7,
+		codingIndex: 7.5,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.774,
-		gpqa: 0.604,
-		hle: 0.043,
+		mmluPro: 0.696,
+		gpqa: 0.416,
+		hle: 0.033,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1719,21 +1504,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "Sarvam M (Reasoning)",
 	},
-	"qwen3-1.7b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8,
-		normalizedScore: 11,
-
+	"glm-4.6-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 1.4,
-		mathIndex: 38.7,
+		codingIndex: 30.2,
+		mathIndex: 44.3,
 
 		// Academic benchmarks
-		mmluPro: 0.57,
-		gpqa: 0.356,
-		hle: 0.048,
+		mmluPro: 0.784,
+		gpqa: 0.632,
+		hle: 0.052,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1741,21 +1523,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.6 (Non-reasoning)",
 	},
-	"qwen3-max": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 31.4,
-		normalizedScore: 45,
-
+	"glm-4.7-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 26.4,
-		mathIndex: 80.7,
+		codingIndex: 36.3,
+		mathIndex: 95,
 
 		// Academic benchmarks
-		mmluPro: 0.841,
-		gpqa: 0.764,
-		hle: 0.111,
+		mmluPro: 0.856,
+		gpqa: 0.859,
+		hle: 0.251,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1763,21 +1542,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.7 (Reasoning)",
 	},
-	"qwen3-coder-30b-a3b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 20,
-		normalizedScore: 29,
-
+	"glm-5-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 19.4,
-		mathIndex: 29,
+		codingIndex: 44.2,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.706,
-		gpqa: 0.516,
-		hle: 0.04,
+		mmluPro: undefined,
+		gpqa: 0.82,
+		hle: 0.272,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1785,21 +1561,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-5 (Reasoning)",
 	},
-	"qwen3-vl-8b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 14.3,
-		normalizedScore: 20,
-
+	"glm-4.6-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 7.3,
-		mathIndex: 27.3,
+		codingIndex: 29.5,
+		mathIndex: 86,
 
 		// Academic benchmarks
-		mmluPro: 0.686,
-		gpqa: 0.427,
-		hle: 0.029,
+		mmluPro: 0.829,
+		gpqa: 0.78,
+		hle: 0.133,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1807,21 +1580,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.6 (Reasoning)",
 	},
-	"qwen1.5-chat-110b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 9.5,
-		normalizedScore: 14,
-
+	"glm-4.7-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 32,
+		mathIndex: 48,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: 0.289,
-		hle: undefined,
+		mmluPro: 0.794,
+		gpqa: 0.664,
+		hle: 0.061,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1829,21 +1599,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.7 (Non-reasoning)",
 	},
-	"qwen3-max-preview": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 26.1,
-		normalizedScore: 37,
-
+	"glm-4.5-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 25.5,
-		mathIndex: 75,
+		codingIndex: 26.3,
+		mathIndex: 73.7,
 
 		// Academic benchmarks
-		mmluPro: 0.838,
-		gpqa: 0.764,
-		hle: 0.093,
+		mmluPro: 0.835,
+		gpqa: 0.782,
+		hle: 0.122,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1851,21 +1618,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.5 (Reasoning)",
 	},
-	"qwen3-vl-4b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 13.7,
-		normalizedScore: 20,
-
+	"glm-4.7-flash-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 6.7,
-		mathIndex: 25.7,
+		codingIndex: 25.9,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.7,
-		gpqa: 0.494,
-		hle: 0.044,
+		mmluPro: undefined,
+		gpqa: 0.581,
+		hle: 0.071,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1873,21 +1637,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.7-Flash (Reasoning)",
 	},
-	"qwen3-max-thinking-preview": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 32.5,
-		normalizedScore: 46,
-
+	"glm-5-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 24.5,
-		mathIndex: 82.3,
+		codingIndex: 39,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.824,
-		gpqa: 0.776,
-		hle: 0.12,
+		mmluPro: undefined,
+		gpqa: 0.666,
+		hle: 0.072,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1895,21 +1656,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-5 (Non-reasoning)",
 	},
-	"qwen3-vl-32b-reasoning": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 24.7,
-		normalizedScore: 35,
-
+	"glm-4.7-flash-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 14.5,
-		mathIndex: 84.7,
+		codingIndex: 11,
+		mathIndex: undefined,
 
 		// Academic benchmarks
-		mmluPro: 0.818,
-		gpqa: 0.733,
-		hle: 0.096,
+		mmluPro: undefined,
+		gpqa: 0.452,
+		hle: 0.049,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1917,21 +1675,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.7-Flash (Non-reasoning)",
 	},
-	"qwen-chat-72b": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 8.8,
-		normalizedScore: 13,
-
+	"glm-4.6v-non-reasoning": {
 		// AA specific benchmarks
-		codingIndex: undefined,
-		mathIndex: undefined,
+		codingIndex: 11.1,
+		mathIndex: 26.3,
 
 		// Academic benchmarks
-		mmluPro: undefined,
-		gpqa: undefined,
-		hle: undefined,
+		mmluPro: 0.752,
+		gpqa: 0.566,
+		hle: 0.037,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1939,21 +1694,18 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.6V (Non-reasoning)",
 	},
-	"seed-oss-36b-instruct": {
-		// AA Intelligence Index (composite score)
-		intelligenceIndex: 25.2,
-		normalizedScore: 36,
-
+	"glm-4.5v-reasoning": {
 		// AA specific benchmarks
-		codingIndex: 16.7,
-		mathIndex: 84.7,
+		codingIndex: 10.9,
+		mathIndex: 73,
 
 		// Academic benchmarks
-		mmluPro: 0.815,
-		gpqa: 0.726,
-		hle: 0.091,
+		mmluPro: 0.788,
+		gpqa: 0.684,
+		hle: 0.059,
 
 		// Capabilities
 		contextWindow: 8192,
@@ -1961,9 +1713,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
 		supportsVision: false,
 
 		// Metadata
-		lastUpdated: "2026-04-06",
+		lastUpdated: "2026-06-01",
+		originalModel: "GLM-4.5V (Reasoning)",
 	},
-
-
-
 };