pi-free 2.0.7 → 2.0.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +540 -458
- package/README.md +572 -495
- package/config.ts +58 -11
- package/constants.ts +12 -0
- package/index.ts +66 -2
- package/lib/model-detection.ts +1 -0
- package/lib/model-enhancer.ts +20 -20
- package/lib/open-browser.ts +1 -1
- package/lib/quota-monitor.ts +123 -0
- package/lib/types.ts +101 -101
- package/lib/util.ts +460 -351
- package/package.json +68 -68
- package/provider-failover/benchmark-lookup.ts +743 -702
- package/provider-failover/benchmarks-chunk-0.ts +48 -48
- package/provider-failover/benchmarks-chunk-1.ts +44 -44
- package/provider-failover/benchmarks-chunk-2.ts +39 -39
- package/provider-failover/benchmarks-chunk-3.ts +41 -41
- package/provider-failover/benchmarks-chunk-4.ts +33 -33
- package/providers/cline/cline-auth.ts +473 -473
- package/providers/cline/cline-models.ts +2 -2
- package/providers/cline/cline.ts +1 -1
- package/providers/codestral/codestral.ts +139 -0
- package/providers/crofai/crofai.ts +14 -85
- package/providers/deepinfra/deepinfra.ts +109 -0
- package/providers/kilo/kilo-auth.ts +155 -155
- package/providers/kilo/kilo.ts +1 -1
- package/providers/llm7/llm7.ts +156 -0
- package/providers/model-fetcher.ts +2 -2
- package/providers/nvidia/nvidia.ts +4 -4
- package/providers/ollama/ollama.ts +1 -1
- package/providers/opencode-session.ts +1 -1
- package/providers/qwen/qwen-models.ts +101 -101
- package/providers/qwen/qwen.ts +1 -1
- package/providers/sambanova/sambanova.ts +109 -0
- package/providers/zenmux/zenmux.ts +5 -2
- package/scripts/check-extensions.mjs +6 -4
|
@@ -34,7 +34,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
34
34
|
|
|
35
35
|
// AA specific benchmarks
|
|
36
36
|
codingIndex: 11.3,
|
|
37
|
-
mathIndex: 30
|
|
37
|
+
mathIndex: 30,
|
|
38
38
|
|
|
39
39
|
// Academic benchmarks
|
|
40
40
|
mmluPro: 0.75,
|
|
@@ -78,7 +78,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
78
78
|
|
|
79
79
|
// AA specific benchmarks
|
|
80
80
|
codingIndex: 10.8,
|
|
81
|
-
mathIndex: 11
|
|
81
|
+
mathIndex: 11,
|
|
82
82
|
|
|
83
83
|
// Academic benchmarks
|
|
84
84
|
mmluPro: 0.69,
|
|
@@ -183,7 +183,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
183
183
|
},
|
|
184
184
|
"nvidia-nemotron-3-super-120b-a12b-reasoning": {
|
|
185
185
|
// AA Intelligence Index (composite score)
|
|
186
|
-
intelligenceIndex: 36
|
|
186
|
+
intelligenceIndex: 36,
|
|
187
187
|
normalizedScore: 51,
|
|
188
188
|
|
|
189
189
|
// AA specific benchmarks
|
|
@@ -227,7 +227,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
227
227
|
},
|
|
228
228
|
"llama-3.1-nemotron-ultra-253b-v1-reasoning": {
|
|
229
229
|
// AA Intelligence Index (composite score)
|
|
230
|
-
intelligenceIndex: 15
|
|
230
|
+
intelligenceIndex: 15,
|
|
231
231
|
normalizedScore: 21,
|
|
232
232
|
|
|
233
233
|
// AA specific benchmarks
|
|
@@ -254,7 +254,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
254
254
|
|
|
255
255
|
// AA specific benchmarks
|
|
256
256
|
codingIndex: undefined,
|
|
257
|
-
mathIndex: 50
|
|
257
|
+
mathIndex: 50,
|
|
258
258
|
|
|
259
259
|
// Academic benchmarks
|
|
260
260
|
mmluPro: 0.556,
|
|
@@ -276,7 +276,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
276
276
|
|
|
277
277
|
// AA specific benchmarks
|
|
278
278
|
codingIndex: 11.8,
|
|
279
|
-
mathIndex: 75
|
|
279
|
+
mathIndex: 75,
|
|
280
280
|
|
|
281
281
|
// Academic benchmarks
|
|
282
282
|
mmluPro: 0.759,
|
|
@@ -341,8 +341,8 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
341
341
|
normalizedScore: 35,
|
|
342
342
|
|
|
343
343
|
// AA specific benchmarks
|
|
344
|
-
codingIndex: 19
|
|
345
|
-
mathIndex: 91
|
|
344
|
+
codingIndex: 19,
|
|
345
|
+
mathIndex: 91,
|
|
346
346
|
|
|
347
347
|
// Academic benchmarks
|
|
348
348
|
mmluPro: 0.794,
|
|
@@ -385,7 +385,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
385
385
|
normalizedScore: 21,
|
|
386
386
|
|
|
387
387
|
// AA specific benchmarks
|
|
388
|
-
codingIndex: 10
|
|
388
|
+
codingIndex: 10,
|
|
389
389
|
mathIndex: undefined,
|
|
390
390
|
|
|
391
391
|
// Academic benchmarks
|
|
@@ -408,7 +408,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
408
408
|
|
|
409
409
|
// AA specific benchmarks
|
|
410
410
|
codingIndex: 10.5,
|
|
411
|
-
mathIndex: 8
|
|
411
|
+
mathIndex: 8,
|
|
412
412
|
|
|
413
413
|
// Academic benchmarks
|
|
414
414
|
mmluPro: 0.692,
|
|
@@ -628,7 +628,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
628
628
|
|
|
629
629
|
// AA specific benchmarks
|
|
630
630
|
codingIndex: 1.2,
|
|
631
|
-
mathIndex: 0
|
|
631
|
+
mathIndex: 0,
|
|
632
632
|
|
|
633
633
|
// Academic benchmarks
|
|
634
634
|
mmluPro: 0.371,
|
|
@@ -665,7 +665,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
665
665
|
// Metadata
|
|
666
666
|
lastUpdated: "2026-04-06",
|
|
667
667
|
},
|
|
668
|
-
"granite-4
|
|
668
|
+
"granite-4-1b": {
|
|
669
669
|
// AA Intelligence Index (composite score)
|
|
670
670
|
intelligenceIndex: 7.3,
|
|
671
671
|
normalizedScore: 10,
|
|
@@ -687,14 +687,14 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
687
687
|
// Metadata
|
|
688
688
|
lastUpdated: "2026-04-06",
|
|
689
689
|
},
|
|
690
|
-
"granite-4
|
|
690
|
+
"granite-4-micro": {
|
|
691
691
|
// AA Intelligence Index (composite score)
|
|
692
692
|
intelligenceIndex: 7.7,
|
|
693
693
|
normalizedScore: 11,
|
|
694
694
|
|
|
695
695
|
// AA specific benchmarks
|
|
696
|
-
codingIndex: 5
|
|
697
|
-
mathIndex: 6
|
|
696
|
+
codingIndex: 5,
|
|
697
|
+
mathIndex: 6,
|
|
698
698
|
|
|
699
699
|
// Academic benchmarks
|
|
700
700
|
mmluPro: 0.447,
|
|
@@ -709,7 +709,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
709
709
|
// Metadata
|
|
710
710
|
lastUpdated: "2026-04-06",
|
|
711
711
|
},
|
|
712
|
-
"granite-4
|
|
712
|
+
"granite-4-h-350m": {
|
|
713
713
|
// AA Intelligence Index (composite score)
|
|
714
714
|
intelligenceIndex: 5.4,
|
|
715
715
|
normalizedScore: 8,
|
|
@@ -753,7 +753,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
753
753
|
// Metadata
|
|
754
754
|
lastUpdated: "2026-04-06",
|
|
755
755
|
},
|
|
756
|
-
"granite-4
|
|
756
|
+
"granite-4-h-small": {
|
|
757
757
|
// AA Intelligence Index (composite score)
|
|
758
758
|
intelligenceIndex: 10.8,
|
|
759
759
|
normalizedScore: 15,
|
|
@@ -775,9 +775,9 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
775
775
|
// Metadata
|
|
776
776
|
lastUpdated: "2026-04-06",
|
|
777
777
|
},
|
|
778
|
-
"granite-4
|
|
778
|
+
"granite-4-h-1b": {
|
|
779
779
|
// AA Intelligence Index (composite score)
|
|
780
|
-
intelligenceIndex: 8
|
|
780
|
+
intelligenceIndex: 8,
|
|
781
781
|
normalizedScore: 11,
|
|
782
782
|
|
|
783
783
|
// AA specific benchmarks
|
|
@@ -797,14 +797,14 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
797
797
|
// Metadata
|
|
798
798
|
lastUpdated: "2026-04-06",
|
|
799
799
|
},
|
|
800
|
-
"granite-4
|
|
800
|
+
"granite-4-350m": {
|
|
801
801
|
// AA Intelligence Index (composite score)
|
|
802
802
|
intelligenceIndex: 6.1,
|
|
803
803
|
normalizedScore: 9,
|
|
804
804
|
|
|
805
805
|
// AA specific benchmarks
|
|
806
806
|
codingIndex: 0.3,
|
|
807
|
-
mathIndex: 0
|
|
807
|
+
mathIndex: 0,
|
|
808
808
|
|
|
809
809
|
// Academic benchmarks
|
|
810
810
|
mmluPro: 0.124,
|
|
@@ -891,7 +891,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
891
891
|
normalizedScore: 27,
|
|
892
892
|
|
|
893
893
|
// AA specific benchmarks
|
|
894
|
-
codingIndex: 16
|
|
894
|
+
codingIndex: 16,
|
|
895
895
|
mathIndex: 69.7,
|
|
896
896
|
|
|
897
897
|
// Academic benchmarks
|
|
@@ -931,7 +931,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
931
931
|
},
|
|
932
932
|
"hermes-4---llama-3.1-70b-reasoning": {
|
|
933
933
|
// AA Intelligence Index (composite score)
|
|
934
|
-
intelligenceIndex: 16
|
|
934
|
+
intelligenceIndex: 16,
|
|
935
935
|
normalizedScore: 23,
|
|
936
936
|
|
|
937
937
|
// AA specific benchmarks
|
|
@@ -1002,7 +1002,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1002
1002
|
|
|
1003
1003
|
// AA specific benchmarks
|
|
1004
1004
|
codingIndex: 13.5,
|
|
1005
|
-
mathIndex: 44
|
|
1005
|
+
mathIndex: 44,
|
|
1006
1006
|
|
|
1007
1007
|
// Academic benchmarks
|
|
1008
1008
|
mmluPro: 0.81,
|
|
@@ -1017,7 +1017,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1017
1017
|
// Metadata
|
|
1018
1018
|
lastUpdated: "2026-04-06",
|
|
1019
1019
|
},
|
|
1020
|
-
"exaone-4
|
|
1020
|
+
"exaone-4-32b-non-reasoning": {
|
|
1021
1021
|
// AA Intelligence Index (composite score)
|
|
1022
1022
|
intelligenceIndex: 11.7,
|
|
1023
1023
|
normalizedScore: 17,
|
|
@@ -1045,7 +1045,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1045
1045
|
normalizedScore: 46,
|
|
1046
1046
|
|
|
1047
1047
|
// AA specific benchmarks
|
|
1048
|
-
codingIndex: 27
|
|
1048
|
+
codingIndex: 27,
|
|
1049
1049
|
mathIndex: 90.3,
|
|
1050
1050
|
|
|
1051
1051
|
// Academic benchmarks
|
|
@@ -1061,14 +1061,14 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1061
1061
|
// Metadata
|
|
1062
1062
|
lastUpdated: "2026-04-06",
|
|
1063
1063
|
},
|
|
1064
|
-
"exaone-4
|
|
1064
|
+
"exaone-4-1.2b-non-reasoning": {
|
|
1065
1065
|
// AA Intelligence Index (composite score)
|
|
1066
1066
|
intelligenceIndex: 8.1,
|
|
1067
1067
|
normalizedScore: 12,
|
|
1068
1068
|
|
|
1069
1069
|
// AA specific benchmarks
|
|
1070
1070
|
codingIndex: 2.5,
|
|
1071
|
-
mathIndex: 24
|
|
1071
|
+
mathIndex: 24,
|
|
1072
1072
|
|
|
1073
1073
|
// Academic benchmarks
|
|
1074
1074
|
mmluPro: 0.5,
|
|
@@ -1083,14 +1083,14 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1083
1083
|
// Metadata
|
|
1084
1084
|
lastUpdated: "2026-04-06",
|
|
1085
1085
|
},
|
|
1086
|
-
"exaone-4
|
|
1086
|
+
"exaone-4-32b-reasoning": {
|
|
1087
1087
|
// AA Intelligence Index (composite score)
|
|
1088
1088
|
intelligenceIndex: 16.7,
|
|
1089
1089
|
normalizedScore: 24,
|
|
1090
1090
|
|
|
1091
1091
|
// AA specific benchmarks
|
|
1092
|
-
codingIndex: 14
|
|
1093
|
-
mathIndex: 80
|
|
1092
|
+
codingIndex: 14,
|
|
1093
|
+
mathIndex: 80,
|
|
1094
1094
|
|
|
1095
1095
|
// Academic benchmarks
|
|
1096
1096
|
mmluPro: 0.818,
|
|
@@ -1105,7 +1105,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1105
1105
|
// Metadata
|
|
1106
1106
|
lastUpdated: "2026-04-06",
|
|
1107
1107
|
},
|
|
1108
|
-
"exaone-4
|
|
1108
|
+
"exaone-4-1.2b-reasoning": {
|
|
1109
1109
|
// AA Intelligence Index (composite score)
|
|
1110
1110
|
intelligenceIndex: 8.3,
|
|
1111
1111
|
normalizedScore: 12,
|
|
@@ -1217,7 +1217,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1217
1217
|
},
|
|
1218
1218
|
"ernie-4.5-300b-a47b": {
|
|
1219
1219
|
// AA Intelligence Index (composite score)
|
|
1220
|
-
intelligenceIndex: 15
|
|
1220
|
+
intelligenceIndex: 15,
|
|
1221
1221
|
normalizedScore: 21,
|
|
1222
1222
|
|
|
1223
1223
|
// AA specific benchmarks
|
|
@@ -1237,14 +1237,14 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1237
1237
|
// Metadata
|
|
1238
1238
|
lastUpdated: "2026-04-06",
|
|
1239
1239
|
},
|
|
1240
|
-
"ernie-5
|
|
1240
|
+
"ernie-5-thinking-preview": {
|
|
1241
1241
|
// AA Intelligence Index (composite score)
|
|
1242
1242
|
intelligenceIndex: 29.1,
|
|
1243
1243
|
normalizedScore: 42,
|
|
1244
1244
|
|
|
1245
1245
|
// AA specific benchmarks
|
|
1246
1246
|
codingIndex: 29.2,
|
|
1247
|
-
mathIndex: 85
|
|
1247
|
+
mathIndex: 85,
|
|
1248
1248
|
|
|
1249
1249
|
// Academic benchmarks
|
|
1250
1250
|
mmluPro: 0.83,
|
|
@@ -1305,7 +1305,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1305
1305
|
},
|
|
1306
1306
|
"kat-coder-pro-v1": {
|
|
1307
1307
|
// AA Intelligence Index (composite score)
|
|
1308
|
-
intelligenceIndex: 36
|
|
1308
|
+
intelligenceIndex: 36,
|
|
1309
1309
|
normalizedScore: 51,
|
|
1310
1310
|
|
|
1311
1311
|
// AA specific benchmarks
|
|
@@ -1354,7 +1354,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1354
1354
|
|
|
1355
1355
|
// AA specific benchmarks
|
|
1356
1356
|
codingIndex: 19.1,
|
|
1357
|
-
mathIndex: 88
|
|
1357
|
+
mathIndex: 88,
|
|
1358
1358
|
|
|
1359
1359
|
// Academic benchmarks
|
|
1360
1360
|
mmluPro: 0.822,
|
|
@@ -1419,7 +1419,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1419
1419
|
normalizedScore: 27,
|
|
1420
1420
|
|
|
1421
1421
|
// AA specific benchmarks
|
|
1422
|
-
codingIndex: 14
|
|
1422
|
+
codingIndex: 14,
|
|
1423
1423
|
mathIndex: 64.7,
|
|
1424
1424
|
|
|
1425
1425
|
// Academic benchmarks
|
|
@@ -1508,7 +1508,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1508
1508
|
|
|
1509
1509
|
// AA specific benchmarks
|
|
1510
1510
|
codingIndex: 17.5,
|
|
1511
|
-
mathIndex: 59
|
|
1511
|
+
mathIndex: 59,
|
|
1512
1512
|
|
|
1513
1513
|
// Academic benchmarks
|
|
1514
1514
|
mmluPro: 0.785,
|
|
@@ -1569,7 +1569,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1569
1569
|
},
|
|
1570
1570
|
"tri-21b-think-preview": {
|
|
1571
1571
|
// AA Intelligence Index (composite score)
|
|
1572
|
-
intelligenceIndex: 20
|
|
1572
|
+
intelligenceIndex: 20,
|
|
1573
1573
|
normalizedScore: 29,
|
|
1574
1574
|
|
|
1575
1575
|
// AA specific benchmarks
|
|
@@ -1749,7 +1749,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1749
1749
|
normalizedScore: 58,
|
|
1750
1750
|
|
|
1751
1751
|
// AA specific benchmarks
|
|
1752
|
-
codingIndex: 39
|
|
1752
|
+
codingIndex: 39,
|
|
1753
1753
|
mathIndex: undefined,
|
|
1754
1754
|
|
|
1755
1755
|
// Academic benchmarks
|
|
@@ -1838,7 +1838,7 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1838
1838
|
|
|
1839
1839
|
// AA specific benchmarks
|
|
1840
1840
|
codingIndex: 9.9,
|
|
1841
|
-
mathIndex: 13
|
|
1841
|
+
mathIndex: 13,
|
|
1842
1842
|
|
|
1843
1843
|
// Academic benchmarks
|
|
1844
1844
|
mmluPro: 0.712,
|
|
@@ -1859,8 +1859,8 @@ export const BENCHMARKS_CHUNK_1: Record<string, HardcodedBenchmark> = {
|
|
|
1859
1859
|
normalizedScore: 39,
|
|
1860
1860
|
|
|
1861
1861
|
// AA specific benchmarks
|
|
1862
|
-
codingIndex: 22
|
|
1863
|
-
mathIndex: 88
|
|
1862
|
+
codingIndex: 22,
|
|
1863
|
+
mathIndex: 88,
|
|
1864
1864
|
|
|
1865
1865
|
// Academic benchmarks
|
|
1866
1866
|
mmluPro: 0.79,
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
// Auto-generated benchmark data chunk 2
|
|
2
|
-
// Models: qwen3.5-122b-a10b-reasoning .. gemini-1
|
|
2
|
+
// Models: qwen3.5-122b-a10b-reasoning .. gemini-1-pro (90 entries)
|
|
3
3
|
// DO NOT EDIT MANUALLY — generated by scripts/update-benchmarks.ts
|
|
4
4
|
|
|
5
5
|
import type { HardcodedBenchmark } from "./hardcoded-benchmarks.ts";
|
|
@@ -51,7 +51,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
51
51
|
},
|
|
52
52
|
"qwen3.5-397b-a17b-reasoning": {
|
|
53
53
|
// AA Intelligence Index (composite score)
|
|
54
|
-
intelligenceIndex: 45
|
|
54
|
+
intelligenceIndex: 45,
|
|
55
55
|
normalizedScore: 64,
|
|
56
56
|
|
|
57
57
|
// AA specific benchmarks
|
|
@@ -165,7 +165,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
165
165
|
normalizedScore: 14,
|
|
166
166
|
|
|
167
167
|
// AA specific benchmarks
|
|
168
|
-
codingIndex: 1
|
|
168
|
+
codingIndex: 1,
|
|
169
169
|
mathIndex: undefined,
|
|
170
170
|
|
|
171
171
|
// Academic benchmarks
|
|
@@ -341,7 +341,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
341
341
|
normalizedScore: 15,
|
|
342
342
|
|
|
343
343
|
// AA specific benchmarks
|
|
344
|
-
codingIndex: 0
|
|
344
|
+
codingIndex: 0,
|
|
345
345
|
mathIndex: undefined,
|
|
346
346
|
|
|
347
347
|
// Academic benchmarks
|
|
@@ -364,7 +364,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
364
364
|
|
|
365
365
|
// AA specific benchmarks
|
|
366
366
|
codingIndex: 12.7,
|
|
367
|
-
mathIndex: 74
|
|
367
|
+
mathIndex: 74,
|
|
368
368
|
|
|
369
369
|
// Academic benchmarks
|
|
370
370
|
mmluPro: 0.792,
|
|
@@ -489,13 +489,13 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
489
489
|
// Metadata
|
|
490
490
|
lastUpdated: "2026-04-06",
|
|
491
491
|
},
|
|
492
|
-
"ling-mini-2
|
|
492
|
+
"ling-mini-2": {
|
|
493
493
|
// AA Intelligence Index (composite score)
|
|
494
494
|
intelligenceIndex: 9.2,
|
|
495
495
|
normalizedScore: 13,
|
|
496
496
|
|
|
497
497
|
// AA specific benchmarks
|
|
498
|
-
codingIndex: 5
|
|
498
|
+
codingIndex: 5,
|
|
499
499
|
mathIndex: 49.3,
|
|
500
500
|
|
|
501
501
|
// Academic benchmarks
|
|
@@ -535,7 +535,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
535
535
|
},
|
|
536
536
|
"ling-1t": {
|
|
537
537
|
// AA Intelligence Index (composite score)
|
|
538
|
-
intelligenceIndex: 19
|
|
538
|
+
intelligenceIndex: 19,
|
|
539
539
|
normalizedScore: 27,
|
|
540
540
|
|
|
541
541
|
// AA specific benchmarks
|
|
@@ -555,9 +555,9 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
555
555
|
// Metadata
|
|
556
556
|
lastUpdated: "2026-04-06",
|
|
557
557
|
},
|
|
558
|
-
"ring-flash-2
|
|
558
|
+
"ring-flash-2": {
|
|
559
559
|
// AA Intelligence Index (composite score)
|
|
560
|
-
intelligenceIndex: 14
|
|
560
|
+
intelligenceIndex: 14,
|
|
561
561
|
normalizedScore: 20,
|
|
562
562
|
|
|
563
563
|
// AA specific benchmarks
|
|
@@ -577,7 +577,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
577
577
|
// Metadata
|
|
578
578
|
lastUpdated: "2026-04-06",
|
|
579
579
|
},
|
|
580
|
-
"ling-flash-2
|
|
580
|
+
"ling-flash-2": {
|
|
581
581
|
// AA Intelligence Index (composite score)
|
|
582
582
|
intelligenceIndex: 15.7,
|
|
583
583
|
normalizedScore: 22,
|
|
@@ -649,7 +649,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
649
649
|
normalizedScore: 34,
|
|
650
650
|
|
|
651
651
|
// AA specific benchmarks
|
|
652
|
-
codingIndex: 34
|
|
652
|
+
codingIndex: 34,
|
|
653
653
|
mathIndex: undefined,
|
|
654
654
|
|
|
655
655
|
// Academic benchmarks
|
|
@@ -760,7 +760,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
760
760
|
|
|
761
761
|
// AA specific benchmarks
|
|
762
762
|
codingIndex: 16.7,
|
|
763
|
-
mathIndex: 6
|
|
763
|
+
mathIndex: 6,
|
|
764
764
|
|
|
765
765
|
// Academic benchmarks
|
|
766
766
|
mmluPro: 0.748,
|
|
@@ -799,7 +799,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
799
799
|
},
|
|
800
800
|
"gpt-3.5-turbo": {
|
|
801
801
|
// AA Intelligence Index (composite score)
|
|
802
|
-
intelligenceIndex: 9
|
|
802
|
+
intelligenceIndex: 9,
|
|
803
803
|
normalizedScore: 13,
|
|
804
804
|
|
|
805
805
|
// AA specific benchmarks
|
|
@@ -826,7 +826,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
826
826
|
|
|
827
827
|
// AA specific benchmarks
|
|
828
828
|
codingIndex: 32.9,
|
|
829
|
-
mathIndex: 85
|
|
829
|
+
mathIndex: 85,
|
|
830
830
|
|
|
831
831
|
// Academic benchmarks
|
|
832
832
|
mmluPro: 0.828,
|
|
@@ -958,7 +958,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
958
958
|
|
|
959
959
|
// AA specific benchmarks
|
|
960
960
|
codingIndex: 34.7,
|
|
961
|
-
mathIndex: 51
|
|
961
|
+
mathIndex: 51,
|
|
962
962
|
|
|
963
963
|
// Academic benchmarks
|
|
964
964
|
mmluPro: 0.814,
|
|
@@ -1002,7 +1002,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1002
1002
|
|
|
1003
1003
|
// AA specific benchmarks
|
|
1004
1004
|
codingIndex: 48.7,
|
|
1005
|
-
mathIndex: 99
|
|
1005
|
+
mathIndex: 99,
|
|
1006
1006
|
|
|
1007
1007
|
// Academic benchmarks
|
|
1008
1008
|
mmluPro: 0.874,
|
|
@@ -1046,7 +1046,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1046
1046
|
|
|
1047
1047
|
// AA specific benchmarks
|
|
1048
1048
|
codingIndex: 30.7,
|
|
1049
|
-
mathIndex: 83
|
|
1049
|
+
mathIndex: 83,
|
|
1050
1050
|
|
|
1051
1051
|
// Academic benchmarks
|
|
1052
1052
|
mmluPro: 0.86,
|
|
@@ -1068,7 +1068,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1068
1068
|
|
|
1069
1069
|
// AA specific benchmarks
|
|
1070
1070
|
codingIndex: 44.7,
|
|
1071
|
-
mathIndex: 94
|
|
1071
|
+
mathIndex: 94,
|
|
1072
1072
|
|
|
1073
1073
|
// Academic benchmarks
|
|
1074
1074
|
mmluPro: 0.87,
|
|
@@ -1107,11 +1107,11 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1107
1107
|
},
|
|
1108
1108
|
"gpt-5.2-codex-xhigh": {
|
|
1109
1109
|
// AA Intelligence Index (composite score)
|
|
1110
|
-
intelligenceIndex: 49
|
|
1110
|
+
intelligenceIndex: 49,
|
|
1111
1111
|
normalizedScore: 70,
|
|
1112
1112
|
|
|
1113
1113
|
// AA specific benchmarks
|
|
1114
|
-
codingIndex: 43
|
|
1114
|
+
codingIndex: 43,
|
|
1115
1115
|
mathIndex: undefined,
|
|
1116
1116
|
|
|
1117
1117
|
// Academic benchmarks
|
|
@@ -1151,12 +1151,12 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1151
1151
|
},
|
|
1152
1152
|
"gpt-4.1-nano": {
|
|
1153
1153
|
// AA Intelligence Index (composite score)
|
|
1154
|
-
intelligenceIndex: 13
|
|
1154
|
+
intelligenceIndex: 13,
|
|
1155
1155
|
normalizedScore: 19,
|
|
1156
1156
|
|
|
1157
1157
|
// AA specific benchmarks
|
|
1158
1158
|
codingIndex: 11.2,
|
|
1159
|
-
mathIndex: 24
|
|
1159
|
+
mathIndex: 24,
|
|
1160
1160
|
|
|
1161
1161
|
// Academic benchmarks
|
|
1162
1162
|
mmluPro: 0.657,
|
|
@@ -1239,11 +1239,11 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1239
1239
|
},
|
|
1240
1240
|
"gpt-5-medium": {
|
|
1241
1241
|
// AA Intelligence Index (composite score)
|
|
1242
|
-
intelligenceIndex: 42
|
|
1242
|
+
intelligenceIndex: 42,
|
|
1243
1243
|
normalizedScore: 60,
|
|
1244
1244
|
|
|
1245
1245
|
// AA specific benchmarks
|
|
1246
|
-
codingIndex: 39
|
|
1246
|
+
codingIndex: 39,
|
|
1247
1247
|
mathIndex: 91.7,
|
|
1248
1248
|
|
|
1249
1249
|
// Academic benchmarks
|
|
@@ -1309,7 +1309,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1309
1309
|
normalizedScore: 64,
|
|
1310
1310
|
|
|
1311
1311
|
// AA specific benchmarks
|
|
1312
|
-
codingIndex: 36
|
|
1312
|
+
codingIndex: 36,
|
|
1313
1313
|
mathIndex: 94.3,
|
|
1314
1314
|
|
|
1315
1315
|
// Academic benchmarks
|
|
@@ -1464,7 +1464,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1464
1464
|
|
|
1465
1465
|
// AA specific benchmarks
|
|
1466
1466
|
codingIndex: 27.3,
|
|
1467
|
-
mathIndex: 38
|
|
1467
|
+
mathIndex: 38,
|
|
1468
1468
|
|
|
1469
1469
|
// Academic benchmarks
|
|
1470
1470
|
mmluPro: 0.801,
|
|
@@ -1503,7 +1503,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1503
1503
|
},
|
|
1504
1504
|
"gpt-4.5-preview": {
|
|
1505
1505
|
// AA Intelligence Index (composite score)
|
|
1506
|
-
intelligenceIndex: 20
|
|
1506
|
+
intelligenceIndex: 20,
|
|
1507
1507
|
normalizedScore: 29,
|
|
1508
1508
|
|
|
1509
1509
|
// AA specific benchmarks
|
|
@@ -1530,7 +1530,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1530
1530
|
|
|
1531
1531
|
// AA specific benchmarks
|
|
1532
1532
|
codingIndex: 10.9,
|
|
1533
|
-
mathIndex: 4
|
|
1533
|
+
mathIndex: 4,
|
|
1534
1534
|
|
|
1535
1535
|
// Academic benchmarks
|
|
1536
1536
|
mmluPro: 0.676,
|
|
@@ -1617,7 +1617,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1617
1617
|
normalizedScore: 9,
|
|
1618
1618
|
|
|
1619
1619
|
// AA specific benchmarks
|
|
1620
|
-
codingIndex: 4
|
|
1620
|
+
codingIndex: 4,
|
|
1621
1621
|
mathIndex: undefined,
|
|
1622
1622
|
|
|
1623
1623
|
// Academic benchmarks
|
|
@@ -1640,7 +1640,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1640
1640
|
|
|
1641
1641
|
// AA specific benchmarks
|
|
1642
1642
|
codingIndex: 0.6,
|
|
1643
|
-
mathIndex: 0
|
|
1643
|
+
mathIndex: 0,
|
|
1644
1644
|
|
|
1645
1645
|
// Academic benchmarks
|
|
1646
1646
|
mmluPro: 0.2,
|
|
@@ -1721,7 +1721,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1721
1721
|
// Metadata
|
|
1722
1722
|
lastUpdated: "2026-04-06",
|
|
1723
1723
|
},
|
|
1724
|
-
"gemini-2
|
|
1724
|
+
"gemini-2-pro-experimental-feb-25": {
|
|
1725
1725
|
// AA Intelligence Index (composite score)
|
|
1726
1726
|
intelligenceIndex: 18.1,
|
|
1727
1727
|
normalizedScore: 26,
|
|
@@ -1743,7 +1743,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1743
1743
|
// Metadata
|
|
1744
1744
|
lastUpdated: "2026-04-06",
|
|
1745
1745
|
},
|
|
1746
|
-
"gemini-2
|
|
1746
|
+
"gemini-2-flash-experimental": {
|
|
1747
1747
|
// AA Intelligence Index (composite score)
|
|
1748
1748
|
intelligenceIndex: 16.8,
|
|
1749
1749
|
normalizedScore: 24,
|
|
@@ -1767,7 +1767,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1767
1767
|
},
|
|
1768
1768
|
"gemini-1.5-pro-sep-24": {
|
|
1769
1769
|
// AA Intelligence Index (composite score)
|
|
1770
|
-
intelligenceIndex: 16
|
|
1770
|
+
intelligenceIndex: 16,
|
|
1771
1771
|
normalizedScore: 23,
|
|
1772
1772
|
|
|
1773
1773
|
// AA specific benchmarks
|
|
@@ -1787,7 +1787,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1787
1787
|
// Metadata
|
|
1788
1788
|
lastUpdated: "2026-04-06",
|
|
1789
1789
|
},
|
|
1790
|
-
"gemini-2
|
|
1790
|
+
"gemini-2-flash-lite-preview": {
|
|
1791
1791
|
// AA Intelligence Index (composite score)
|
|
1792
1792
|
intelligenceIndex: 14.5,
|
|
1793
1793
|
normalizedScore: 21,
|
|
@@ -1809,7 +1809,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1809
1809
|
// Metadata
|
|
1810
1810
|
lastUpdated: "2026-04-06",
|
|
1811
1811
|
},
|
|
1812
|
-
"gemini-2
|
|
1812
|
+
"gemini-2-flash-feb-25": {
|
|
1813
1813
|
// AA Intelligence Index (composite score)
|
|
1814
1814
|
intelligenceIndex: 18.5,
|
|
1815
1815
|
normalizedScore: 26,
|
|
@@ -1875,7 +1875,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1875
1875
|
// Metadata
|
|
1876
1876
|
lastUpdated: "2026-04-06",
|
|
1877
1877
|
},
|
|
1878
|
-
"gemini-2
|
|
1878
|
+
"gemini-2-flash-thinking-experimental-jan-25": {
|
|
1879
1879
|
// AA Intelligence Index (composite score)
|
|
1880
1880
|
intelligenceIndex: 19.6,
|
|
1881
1881
|
normalizedScore: 28,
|
|
@@ -1941,7 +1941,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1941
1941
|
// Metadata
|
|
1942
1942
|
lastUpdated: "2026-04-06",
|
|
1943
1943
|
},
|
|
1944
|
-
"gemini-2
|
|
1944
|
+
"gemini-2-flash-thinking-experimental-dec-24": {
|
|
1945
1945
|
// AA Intelligence Index (composite score)
|
|
1946
1946
|
intelligenceIndex: 12.3,
|
|
1947
1947
|
normalizedScore: 18,
|
|
@@ -1985,7 +1985,7 @@ export const BENCHMARKS_CHUNK_2: Record<string, HardcodedBenchmark> = {
|
|
|
1985
1985
|
// Metadata
|
|
1986
1986
|
lastUpdated: "2026-04-06",
|
|
1987
1987
|
},
|
|
1988
|
-
"gemini-1
|
|
1988
|
+
"gemini-1-pro": {
|
|
1989
1989
|
// AA Intelligence Index (composite score)
|
|
1990
1990
|
intelligenceIndex: 8.5,
|
|
1991
1991
|
normalizedScore: 12,
|