pi-free 2.0.6 → 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 -421
- 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
|
@@ -51,7 +51,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
51
51
|
},
|
|
52
52
|
"gemini-1.5-pro-may-24": {
|
|
53
53
|
// AA Intelligence Index (composite score)
|
|
54
|
-
intelligenceIndex: 12
|
|
54
|
+
intelligenceIndex: 12,
|
|
55
55
|
normalizedScore: 17,
|
|
56
56
|
|
|
57
57
|
// AA specific benchmarks
|
|
@@ -95,7 +95,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
95
95
|
},
|
|
96
96
|
"gemini-2.5-flash-reasoning": {
|
|
97
97
|
// AA Intelligence Index (composite score)
|
|
98
|
-
intelligenceIndex: 27
|
|
98
|
+
intelligenceIndex: 27,
|
|
99
99
|
normalizedScore: 39,
|
|
100
100
|
|
|
101
101
|
// AA specific benchmarks
|
|
@@ -203,7 +203,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
203
203
|
// Metadata
|
|
204
204
|
lastUpdated: "2026-04-06",
|
|
205
205
|
},
|
|
206
|
-
"gemini-2
|
|
206
|
+
"gemini-2-flash-lite-feb-25": {
|
|
207
207
|
// AA Intelligence Index (composite score)
|
|
208
208
|
intelligenceIndex: 14.7,
|
|
209
209
|
normalizedScore: 21,
|
|
@@ -269,7 +269,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
269
269
|
// Metadata
|
|
270
270
|
lastUpdated: "2026-04-06",
|
|
271
271
|
},
|
|
272
|
-
"gemini-1
|
|
272
|
+
"gemini-1-ultra": {
|
|
273
273
|
// AA Intelligence Index (composite score)
|
|
274
274
|
intelligenceIndex: 10.1,
|
|
275
275
|
normalizedScore: 14,
|
|
@@ -341,7 +341,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
341
341
|
normalizedScore: 20,
|
|
342
342
|
|
|
343
343
|
// AA specific benchmarks
|
|
344
|
-
codingIndex: 26
|
|
344
|
+
codingIndex: 26,
|
|
345
345
|
mathIndex: undefined,
|
|
346
346
|
|
|
347
347
|
// Academic benchmarks
|
|
@@ -359,7 +359,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
359
359
|
},
|
|
360
360
|
"claude-3-opus": {
|
|
361
361
|
// AA Intelligence Index (composite score)
|
|
362
|
-
intelligenceIndex: 18
|
|
362
|
+
intelligenceIndex: 18,
|
|
363
363
|
normalizedScore: 26,
|
|
364
364
|
|
|
365
365
|
// AA specific benchmarks
|
|
@@ -474,7 +474,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
474
474
|
|
|
475
475
|
// AA specific benchmarks
|
|
476
476
|
codingIndex: 26.7,
|
|
477
|
-
mathIndex: 21
|
|
477
|
+
mathIndex: 21,
|
|
478
478
|
|
|
479
479
|
// Academic benchmarks
|
|
480
480
|
mmluPro: 0.803,
|
|
@@ -495,7 +495,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
495
495
|
normalizedScore: 13,
|
|
496
496
|
|
|
497
497
|
// AA specific benchmarks
|
|
498
|
-
codingIndex: 14
|
|
498
|
+
codingIndex: 14,
|
|
499
499
|
mathIndex: undefined,
|
|
500
500
|
|
|
501
501
|
// Academic benchmarks
|
|
@@ -535,7 +535,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
535
535
|
},
|
|
536
536
|
"claude-4.1-opus-non-reasoning": {
|
|
537
537
|
// AA Intelligence Index (composite score)
|
|
538
|
-
intelligenceIndex: 36
|
|
538
|
+
intelligenceIndex: 36,
|
|
539
539
|
normalizedScore: 51,
|
|
540
540
|
|
|
541
541
|
// AA specific benchmarks
|
|
@@ -557,7 +557,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
557
557
|
},
|
|
558
558
|
"claude-4.1-opus-reasoning": {
|
|
559
559
|
// AA Intelligence Index (composite score)
|
|
560
|
-
intelligenceIndex: 42
|
|
560
|
+
intelligenceIndex: 42,
|
|
561
561
|
normalizedScore: 60,
|
|
562
562
|
|
|
563
563
|
// AA specific benchmarks
|
|
@@ -579,12 +579,12 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
579
579
|
},
|
|
580
580
|
"claude-4-sonnet-non-reasoning": {
|
|
581
581
|
// AA Intelligence Index (composite score)
|
|
582
|
-
intelligenceIndex: 33
|
|
582
|
+
intelligenceIndex: 33,
|
|
583
583
|
normalizedScore: 47,
|
|
584
584
|
|
|
585
585
|
// AA specific benchmarks
|
|
586
586
|
codingIndex: 30.6,
|
|
587
|
-
mathIndex: 38
|
|
587
|
+
mathIndex: 38,
|
|
588
588
|
|
|
589
589
|
// Academic benchmarks
|
|
590
590
|
mmluPro: 0.837,
|
|
@@ -601,7 +601,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
601
601
|
},
|
|
602
602
|
"claude-4-opus-non-reasoning": {
|
|
603
603
|
// AA Intelligence Index (composite score)
|
|
604
|
-
intelligenceIndex: 33
|
|
604
|
+
intelligenceIndex: 33,
|
|
605
605
|
normalizedScore: 47,
|
|
606
606
|
|
|
607
607
|
// AA specific benchmarks
|
|
@@ -689,11 +689,11 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
689
689
|
},
|
|
690
690
|
"claude-4-opus-reasoning": {
|
|
691
691
|
// AA Intelligence Index (composite score)
|
|
692
|
-
intelligenceIndex: 39
|
|
692
|
+
intelligenceIndex: 39,
|
|
693
693
|
normalizedScore: 56,
|
|
694
694
|
|
|
695
695
|
// AA specific benchmarks
|
|
696
|
-
codingIndex: 34
|
|
696
|
+
codingIndex: 34,
|
|
697
697
|
mathIndex: 73.3,
|
|
698
698
|
|
|
699
699
|
// Academic benchmarks
|
|
@@ -716,7 +716,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
716
716
|
|
|
717
717
|
// AA specific benchmarks
|
|
718
718
|
codingIndex: 33.5,
|
|
719
|
-
mathIndex: 37
|
|
719
|
+
mathIndex: 37,
|
|
720
720
|
|
|
721
721
|
// Academic benchmarks
|
|
722
722
|
mmluPro: 0.86,
|
|
@@ -733,12 +733,12 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
733
733
|
},
|
|
734
734
|
"claude-4.5-sonnet-reasoning": {
|
|
735
735
|
// AA Intelligence Index (composite score)
|
|
736
|
-
intelligenceIndex: 43
|
|
736
|
+
intelligenceIndex: 43,
|
|
737
737
|
normalizedScore: 61,
|
|
738
738
|
|
|
739
739
|
// AA specific benchmarks
|
|
740
740
|
codingIndex: 38.6,
|
|
741
|
-
mathIndex: 88
|
|
741
|
+
mathIndex: 88,
|
|
742
742
|
|
|
743
743
|
// Academic benchmarks
|
|
744
744
|
mmluPro: 0.875,
|
|
@@ -753,7 +753,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
753
753
|
// Metadata
|
|
754
754
|
lastUpdated: "2026-04-06",
|
|
755
755
|
},
|
|
756
|
-
"claude-2
|
|
756
|
+
"claude-2": {
|
|
757
757
|
// AA Intelligence Index (composite score)
|
|
758
758
|
intelligenceIndex: 9.1,
|
|
759
759
|
normalizedScore: 13,
|
|
@@ -782,7 +782,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
782
782
|
|
|
783
783
|
// AA specific benchmarks
|
|
784
784
|
codingIndex: 13.8,
|
|
785
|
-
mathIndex: 14
|
|
785
|
+
mathIndex: 14,
|
|
786
786
|
|
|
787
787
|
// Academic benchmarks
|
|
788
788
|
mmluPro: 0.697,
|
|
@@ -799,12 +799,12 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
799
799
|
},
|
|
800
800
|
"mistral-large-2-jul-24": {
|
|
801
801
|
// AA Intelligence Index (composite score)
|
|
802
|
-
intelligenceIndex: 13
|
|
802
|
+
intelligenceIndex: 13,
|
|
803
803
|
normalizedScore: 19,
|
|
804
804
|
|
|
805
805
|
// AA specific benchmarks
|
|
806
806
|
codingIndex: undefined,
|
|
807
|
-
mathIndex: 0
|
|
807
|
+
mathIndex: 0,
|
|
808
808
|
|
|
809
809
|
// Academic benchmarks
|
|
810
810
|
mmluPro: 0.683,
|
|
@@ -821,7 +821,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
821
821
|
},
|
|
822
822
|
"pixtral-large": {
|
|
823
823
|
// AA Intelligence Index (composite score)
|
|
824
|
-
intelligenceIndex: 14
|
|
824
|
+
intelligenceIndex: 14,
|
|
825
825
|
normalizedScore: 20,
|
|
826
826
|
|
|
827
827
|
// AA specific benchmarks
|
|
@@ -909,7 +909,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
909
909
|
},
|
|
910
910
|
"mistral-small-feb-24": {
|
|
911
911
|
// AA Intelligence Index (composite score)
|
|
912
|
-
intelligenceIndex: 9
|
|
912
|
+
intelligenceIndex: 9,
|
|
913
913
|
normalizedScore: 13,
|
|
914
914
|
|
|
915
915
|
// AA specific benchmarks
|
|
@@ -1068,7 +1068,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1068
1068
|
|
|
1069
1069
|
// AA specific benchmarks
|
|
1070
1070
|
codingIndex: 13.3,
|
|
1071
|
-
mathIndex: 27
|
|
1071
|
+
mathIndex: 27,
|
|
1072
1072
|
|
|
1073
1073
|
// Academic benchmarks
|
|
1074
1074
|
mmluPro: 0.681,
|
|
@@ -1089,7 +1089,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1089
1089
|
normalizedScore: 27,
|
|
1090
1090
|
|
|
1091
1091
|
// AA specific benchmarks
|
|
1092
|
-
codingIndex: 16
|
|
1092
|
+
codingIndex: 16,
|
|
1093
1093
|
mathIndex: 40.3,
|
|
1094
1094
|
|
|
1095
1095
|
// Academic benchmarks
|
|
@@ -1151,7 +1151,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1151
1151
|
},
|
|
1152
1152
|
"mistral-medium": {
|
|
1153
1153
|
// AA Intelligence Index (composite score)
|
|
1154
|
-
intelligenceIndex: 9
|
|
1154
|
+
intelligenceIndex: 9,
|
|
1155
1155
|
normalizedScore: 13,
|
|
1156
1156
|
|
|
1157
1157
|
// AA specific benchmarks
|
|
@@ -1195,7 +1195,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1195
1195
|
},
|
|
1196
1196
|
"devstral-small-may-25": {
|
|
1197
1197
|
// AA Intelligence Index (composite score)
|
|
1198
|
-
intelligenceIndex: 18
|
|
1198
|
+
intelligenceIndex: 18,
|
|
1199
1199
|
normalizedScore: 26,
|
|
1200
1200
|
|
|
1201
1201
|
// AA specific benchmarks
|
|
@@ -1222,7 +1222,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1222
1222
|
|
|
1223
1223
|
// AA specific benchmarks
|
|
1224
1224
|
codingIndex: undefined,
|
|
1225
|
-
mathIndex: 63
|
|
1225
|
+
mathIndex: 63,
|
|
1226
1226
|
|
|
1227
1227
|
// Academic benchmarks
|
|
1228
1228
|
mmluPro: 0.739,
|
|
@@ -1244,7 +1244,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1244
1244
|
|
|
1245
1245
|
// AA specific benchmarks
|
|
1246
1246
|
codingIndex: 16.4,
|
|
1247
|
-
mathIndex: 26
|
|
1247
|
+
mathIndex: 26,
|
|
1248
1248
|
|
|
1249
1249
|
// Academic benchmarks
|
|
1250
1250
|
mmluPro: 0.752,
|
|
@@ -1376,7 +1376,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1376
1376
|
|
|
1377
1377
|
// AA specific benchmarks
|
|
1378
1378
|
codingIndex: undefined,
|
|
1379
|
-
mathIndex: 22
|
|
1379
|
+
mathIndex: 22,
|
|
1380
1380
|
|
|
1381
1381
|
// Academic benchmarks
|
|
1382
1382
|
mmluPro: 0.269,
|
|
@@ -1463,7 +1463,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1463
1463
|
normalizedScore: 41,
|
|
1464
1464
|
|
|
1465
1465
|
// AA specific benchmarks
|
|
1466
|
-
codingIndex: 30
|
|
1466
|
+
codingIndex: 30,
|
|
1467
1467
|
mathIndex: 57.7,
|
|
1468
1468
|
|
|
1469
1469
|
// Academic benchmarks
|
|
@@ -1507,8 +1507,8 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1507
1507
|
normalizedScore: 32,
|
|
1508
1508
|
|
|
1509
1509
|
// AA specific benchmarks
|
|
1510
|
-
codingIndex: 22
|
|
1511
|
-
mathIndex: 41
|
|
1510
|
+
codingIndex: 22,
|
|
1511
|
+
mathIndex: 41,
|
|
1512
1512
|
|
|
1513
1513
|
// Academic benchmarks
|
|
1514
1514
|
mmluPro: 0.819,
|
|
@@ -1530,7 +1530,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1530
1530
|
|
|
1531
1531
|
// AA specific benchmarks
|
|
1532
1532
|
codingIndex: 15.9,
|
|
1533
|
-
mathIndex: 68
|
|
1533
|
+
mathIndex: 68,
|
|
1534
1534
|
|
|
1535
1535
|
// Academic benchmarks
|
|
1536
1536
|
mmluPro: 0.844,
|
|
@@ -1794,7 +1794,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1794
1794
|
|
|
1795
1795
|
// AA specific benchmarks
|
|
1796
1796
|
codingIndex: 19.8,
|
|
1797
|
-
mathIndex: 58
|
|
1797
|
+
mathIndex: 58,
|
|
1798
1798
|
|
|
1799
1799
|
// Academic benchmarks
|
|
1800
1800
|
mmluPro: 0.799,
|
|
@@ -1903,7 +1903,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1903
1903
|
normalizedScore: 33,
|
|
1904
1904
|
|
|
1905
1905
|
// AA specific benchmarks
|
|
1906
|
-
codingIndex: 19
|
|
1906
|
+
codingIndex: 19,
|
|
1907
1907
|
mathIndex: 41.3,
|
|
1908
1908
|
|
|
1909
1909
|
// Academic benchmarks
|
|
@@ -1947,8 +1947,8 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1947
1947
|
normalizedScore: 19,
|
|
1948
1948
|
|
|
1949
1949
|
// AA specific benchmarks
|
|
1950
|
-
codingIndex: 11
|
|
1951
|
-
mathIndex: 7
|
|
1950
|
+
codingIndex: 11,
|
|
1951
|
+
mathIndex: 7,
|
|
1952
1952
|
|
|
1953
1953
|
// Academic benchmarks
|
|
1954
1954
|
mmluPro: 0.691,
|
|
@@ -1970,7 +1970,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1970
1970
|
|
|
1971
1971
|
// AA specific benchmarks
|
|
1972
1972
|
codingIndex: 5.1,
|
|
1973
|
-
mathIndex: 7
|
|
1973
|
+
mathIndex: 7,
|
|
1974
1974
|
|
|
1975
1975
|
// Academic benchmarks
|
|
1976
1976
|
mmluPro: 0.59,
|
|
@@ -1991,7 +1991,7 @@ export const BENCHMARKS_CHUNK_3: Record<string, HardcodedBenchmark> = {
|
|
|
1991
1991
|
normalizedScore: 14,
|
|
1992
1992
|
|
|
1993
1993
|
// AA specific benchmarks
|
|
1994
|
-
codingIndex: 3
|
|
1994
|
+
codingIndex: 3,
|
|
1995
1995
|
mathIndex: 0.3,
|
|
1996
1996
|
|
|
1997
1997
|
// Academic benchmarks
|
|
@@ -73,7 +73,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
73
73
|
},
|
|
74
74
|
"solar-pro-2-preview-non-reasoning": {
|
|
75
75
|
// AA Intelligence Index (composite score)
|
|
76
|
-
intelligenceIndex: 16
|
|
76
|
+
intelligenceIndex: 16,
|
|
77
77
|
normalizedScore: 23,
|
|
78
78
|
|
|
79
79
|
// AA specific benchmarks
|
|
@@ -188,7 +188,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
188
188
|
|
|
189
189
|
// AA specific benchmarks
|
|
190
190
|
codingIndex: 14.5,
|
|
191
|
-
mathIndex: 61
|
|
191
|
+
mathIndex: 61,
|
|
192
192
|
|
|
193
193
|
// Academic benchmarks
|
|
194
194
|
mmluPro: 0.816,
|
|
@@ -298,7 +298,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
298
298
|
|
|
299
299
|
// AA specific benchmarks
|
|
300
300
|
codingIndex: 22.1,
|
|
301
|
-
mathIndex: 57
|
|
301
|
+
mathIndex: 57,
|
|
302
302
|
|
|
303
303
|
// Academic benchmarks
|
|
304
304
|
mmluPro: 0.824,
|
|
@@ -403,7 +403,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
403
403
|
},
|
|
404
404
|
"granite-3.3-8b-non-reasoning": {
|
|
405
405
|
// AA Intelligence Index (composite score)
|
|
406
|
-
intelligenceIndex: 7
|
|
406
|
+
intelligenceIndex: 7,
|
|
407
407
|
normalizedScore: 10,
|
|
408
408
|
|
|
409
409
|
// AA specific benchmarks
|
|
@@ -425,7 +425,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
425
425
|
},
|
|
426
426
|
"reka-flash-sep-24": {
|
|
427
427
|
// AA Intelligence Index (composite score)
|
|
428
|
-
intelligenceIndex: 12
|
|
428
|
+
intelligenceIndex: 12,
|
|
429
429
|
normalizedScore: 17,
|
|
430
430
|
|
|
431
431
|
// AA specific benchmarks
|
|
@@ -540,7 +540,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
540
540
|
|
|
541
541
|
// AA specific benchmarks
|
|
542
542
|
codingIndex: 36.3,
|
|
543
|
-
mathIndex: 95
|
|
543
|
+
mathIndex: 95,
|
|
544
544
|
|
|
545
545
|
// Academic benchmarks
|
|
546
546
|
mmluPro: 0.856,
|
|
@@ -561,7 +561,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
561
561
|
normalizedScore: 32,
|
|
562
562
|
|
|
563
563
|
// AA specific benchmarks
|
|
564
|
-
codingIndex: 11
|
|
564
|
+
codingIndex: 11,
|
|
565
565
|
mathIndex: undefined,
|
|
566
566
|
|
|
567
567
|
// Academic benchmarks
|
|
@@ -583,8 +583,8 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
583
583
|
normalizedScore: 49,
|
|
584
584
|
|
|
585
585
|
// AA specific benchmarks
|
|
586
|
-
codingIndex: 32
|
|
587
|
-
mathIndex: 48
|
|
586
|
+
codingIndex: 32,
|
|
587
|
+
mathIndex: 48,
|
|
588
588
|
|
|
589
589
|
// Academic benchmarks
|
|
590
590
|
mmluPro: 0.794,
|
|
@@ -650,7 +650,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
650
650
|
|
|
651
651
|
// AA specific benchmarks
|
|
652
652
|
codingIndex: 29.5,
|
|
653
|
-
mathIndex: 86
|
|
653
|
+
mathIndex: 86,
|
|
654
654
|
|
|
655
655
|
// Academic benchmarks
|
|
656
656
|
mmluPro: 0.829,
|
|
@@ -694,7 +694,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
694
694
|
|
|
695
695
|
// AA specific benchmarks
|
|
696
696
|
codingIndex: 10.9,
|
|
697
|
-
mathIndex: 73
|
|
697
|
+
mathIndex: 73,
|
|
698
698
|
|
|
699
699
|
// Academic benchmarks
|
|
700
700
|
mmluPro: 0.788,
|
|
@@ -843,7 +843,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
843
843
|
},
|
|
844
844
|
"jamba-1.5-mini": {
|
|
845
845
|
// AA Intelligence Index (composite score)
|
|
846
|
-
intelligenceIndex: 8
|
|
846
|
+
intelligenceIndex: 8,
|
|
847
847
|
normalizedScore: 11,
|
|
848
848
|
|
|
849
849
|
// AA specific benchmarks
|
|
@@ -936,7 +936,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
936
936
|
|
|
937
937
|
// AA specific benchmarks
|
|
938
938
|
codingIndex: 11.9,
|
|
939
|
-
mathIndex: 14
|
|
939
|
+
mathIndex: 14,
|
|
940
940
|
|
|
941
941
|
// Academic benchmarks
|
|
942
942
|
mmluPro: 0.72,
|
|
@@ -975,7 +975,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
975
975
|
},
|
|
976
976
|
"qwen2.5-turbo": {
|
|
977
977
|
// AA Intelligence Index (composite score)
|
|
978
|
-
intelligenceIndex: 12
|
|
978
|
+
intelligenceIndex: 12,
|
|
979
979
|
normalizedScore: 17,
|
|
980
980
|
|
|
981
981
|
// AA specific benchmarks
|
|
@@ -1041,7 +1041,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1041
1041
|
},
|
|
1042
1042
|
"qwen3-235b-a22b-2507-instruct": {
|
|
1043
1043
|
// AA Intelligence Index (composite score)
|
|
1044
|
-
intelligenceIndex: 25
|
|
1044
|
+
intelligenceIndex: 25,
|
|
1045
1045
|
normalizedScore: 36,
|
|
1046
1046
|
|
|
1047
1047
|
// AA specific benchmarks
|
|
@@ -1090,7 +1090,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1090
1090
|
|
|
1091
1091
|
// AA specific benchmarks
|
|
1092
1092
|
codingIndex: 17.4,
|
|
1093
|
-
mathIndex: 82
|
|
1093
|
+
mathIndex: 82,
|
|
1094
1094
|
|
|
1095
1095
|
// Academic benchmarks
|
|
1096
1096
|
mmluPro: 0.828,
|
|
@@ -1107,11 +1107,11 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1107
1107
|
},
|
|
1108
1108
|
"qwen3-235b-a22b-non-reasoning": {
|
|
1109
1109
|
// AA Intelligence Index (composite score)
|
|
1110
|
-
intelligenceIndex: 17
|
|
1110
|
+
intelligenceIndex: 17,
|
|
1111
1111
|
normalizedScore: 24,
|
|
1112
1112
|
|
|
1113
1113
|
// AA specific benchmarks
|
|
1114
|
-
codingIndex: 14
|
|
1114
|
+
codingIndex: 14,
|
|
1115
1115
|
mathIndex: 23.7,
|
|
1116
1116
|
|
|
1117
1117
|
// Academic benchmarks
|
|
@@ -1178,7 +1178,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1178
1178
|
|
|
1179
1179
|
// AA specific benchmarks
|
|
1180
1180
|
codingIndex: 0.9,
|
|
1181
|
-
mathIndex: 18
|
|
1181
|
+
mathIndex: 18,
|
|
1182
1182
|
|
|
1183
1183
|
// Academic benchmarks
|
|
1184
1184
|
mmluPro: 0.347,
|
|
@@ -1200,7 +1200,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1200
1200
|
|
|
1201
1201
|
// AA specific benchmarks
|
|
1202
1202
|
codingIndex: 23.2,
|
|
1203
|
-
mathIndex: 91
|
|
1203
|
+
mathIndex: 91,
|
|
1204
1204
|
|
|
1205
1205
|
// Academic benchmarks
|
|
1206
1206
|
mmluPro: 0.843,
|
|
@@ -1266,7 +1266,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1266
1266
|
|
|
1267
1267
|
// AA specific benchmarks
|
|
1268
1268
|
codingIndex: undefined,
|
|
1269
|
-
mathIndex: 29
|
|
1269
|
+
mathIndex: 29,
|
|
1270
1270
|
|
|
1271
1271
|
// Academic benchmarks
|
|
1272
1272
|
mmluPro: 0.764,
|
|
@@ -1288,7 +1288,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1288
1288
|
|
|
1289
1289
|
// AA specific benchmarks
|
|
1290
1290
|
codingIndex: 13.8,
|
|
1291
|
-
mathIndex: 73
|
|
1291
|
+
mathIndex: 73,
|
|
1292
1292
|
|
|
1293
1293
|
// Academic benchmarks
|
|
1294
1294
|
mmluPro: 0.798,
|
|
@@ -1327,7 +1327,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1327
1327
|
},
|
|
1328
1328
|
"qwen3-30b-a3b-2507-instruct": {
|
|
1329
1329
|
// AA Intelligence Index (composite score)
|
|
1330
|
-
intelligenceIndex: 15
|
|
1330
|
+
intelligenceIndex: 15,
|
|
1331
1331
|
normalizedScore: 21,
|
|
1332
1332
|
|
|
1333
1333
|
// AA specific benchmarks
|
|
@@ -1354,7 +1354,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1354
1354
|
|
|
1355
1355
|
// AA specific benchmarks
|
|
1356
1356
|
codingIndex: 12.4,
|
|
1357
|
-
mathIndex: 58
|
|
1357
|
+
mathIndex: 58,
|
|
1358
1358
|
|
|
1359
1359
|
// Academic benchmarks
|
|
1360
1360
|
mmluPro: 0.675,
|
|
@@ -1376,7 +1376,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1376
1376
|
|
|
1377
1377
|
// AA specific benchmarks
|
|
1378
1378
|
codingIndex: 4.5,
|
|
1379
|
-
mathIndex: 37
|
|
1379
|
+
mathIndex: 37,
|
|
1380
1380
|
|
|
1381
1381
|
// Academic benchmarks
|
|
1382
1382
|
mmluPro: 0.634,
|
|
@@ -1393,7 +1393,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1393
1393
|
},
|
|
1394
1394
|
"qwen2.5-coder-instruct-7b": {
|
|
1395
1395
|
// AA Intelligence Index (composite score)
|
|
1396
|
-
intelligenceIndex: 10
|
|
1396
|
+
intelligenceIndex: 10,
|
|
1397
1397
|
normalizedScore: 14,
|
|
1398
1398
|
|
|
1399
1399
|
// AA specific benchmarks
|
|
@@ -1419,7 +1419,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1419
1419
|
normalizedScore: 22,
|
|
1420
1420
|
|
|
1421
1421
|
// AA specific benchmarks
|
|
1422
|
-
codingIndex: 11
|
|
1422
|
+
codingIndex: 11,
|
|
1423
1423
|
mathIndex: 72.3,
|
|
1424
1424
|
|
|
1425
1425
|
// Academic benchmarks
|
|
@@ -1595,8 +1595,8 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1595
1595
|
normalizedScore: 19,
|
|
1596
1596
|
|
|
1597
1597
|
// AA specific benchmarks
|
|
1598
|
-
codingIndex: 9
|
|
1599
|
-
mathIndex: 19
|
|
1598
|
+
codingIndex: 9,
|
|
1599
|
+
mathIndex: 19,
|
|
1600
1600
|
|
|
1601
1601
|
// Academic benchmarks
|
|
1602
1602
|
mmluPro: 0.743,
|
|
@@ -1723,7 +1723,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1723
1723
|
},
|
|
1724
1724
|
"qwen3-1.7b-reasoning": {
|
|
1725
1725
|
// AA Intelligence Index (composite score)
|
|
1726
|
-
intelligenceIndex: 8
|
|
1726
|
+
intelligenceIndex: 8,
|
|
1727
1727
|
normalizedScore: 11,
|
|
1728
1728
|
|
|
1729
1729
|
// AA specific benchmarks
|
|
@@ -1767,12 +1767,12 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1767
1767
|
},
|
|
1768
1768
|
"qwen3-coder-30b-a3b-instruct": {
|
|
1769
1769
|
// AA Intelligence Index (composite score)
|
|
1770
|
-
intelligenceIndex: 20
|
|
1770
|
+
intelligenceIndex: 20,
|
|
1771
1771
|
normalizedScore: 29,
|
|
1772
1772
|
|
|
1773
1773
|
// AA specific benchmarks
|
|
1774
1774
|
codingIndex: 19.4,
|
|
1775
|
-
mathIndex: 29
|
|
1775
|
+
mathIndex: 29,
|
|
1776
1776
|
|
|
1777
1777
|
// Academic benchmarks
|
|
1778
1778
|
mmluPro: 0.706,
|
|
@@ -1838,7 +1838,7 @@ export const BENCHMARKS_CHUNK_4: Record<string, HardcodedBenchmark> = {
|
|
|
1838
1838
|
|
|
1839
1839
|
// AA specific benchmarks
|
|
1840
1840
|
codingIndex: 25.5,
|
|
1841
|
-
mathIndex: 75
|
|
1841
|
+
mathIndex: 75,
|
|
1842
1842
|
|
|
1843
1843
|
// Academic benchmarks
|
|
1844
1844
|
mmluPro: 0.838,
|