Skip to content

Commit 61782cb

Browse files
ericyangpanericyangpan
authored
Merge pull request #170 from aicodingstack/codex/ranking-intelligence-index
feat(rankings): expand model intelligence rankings
2 parents a9b1406 + 86b454b commit 61782cb

132 files changed

Lines changed: 5401 additions & 727 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

‎AGENTS.md‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -98,4 +98,7 @@ const tComponent = useTranslations('components.navigation.breadcrumb')
9898
## Development Workflow
9999

100100
- **Development server:** Do not start `npm run dev` automatically. User will start it manually when needed.
101+
- **Standalone preview assets:** Before starting `.next/standalone/server.js`, sync `public/` into `.next/standalone/public/` and `.next/static/` into `.next/standalone/.next/static/`. Repeat this after every production build because Next.js regenerates `.next/standalone/`. Never start the standalone server without these assets.
102+
- **Standalone preview host:** The standalone server `HOSTNAME` must match the hostname used in the preview URL. For a `http://localhost:<port>` preview, start with `HOSTNAME=localhost`; do not substitute `127.0.0.1`, because locale middleware rewrites can otherwise become self-redirects.
103+
- **Standalone preview verification:** After starting or restarting a standalone preview, verify that one default-locale URL without a locale prefix returns `200`, one locale-prefixed URL returns `200`, and a stylesheet referenced by the page returns `200` with a CSS content type. When using tmux, include the asset sync and matching `HOSTNAME` in the pane start command.
101104
- **Git commits:** Do not create commits autonomously. Always ask the user before committing changes.

‎data/$schemas/model-intelligence-index.schema.json‎

Lines changed: 21 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
{
2+
"$schema": "https://json-schema.org/draft/2020-12/schema",
3+
"title": "Model Intelligence Index Configuration",
4+
"description": "Editorial display configuration for the model intelligence ranking.",
5+
"type": "object",
6+
"properties": {
7+
"$schema": {
8+
"type": "string"
9+
},
10+
"hiddenVendorIds": {
11+
"type": "array",
12+
"items": {
13+
"type": "string",
14+
"pattern": "^[a-z0-9-]+$"
15+
},
16+
"uniqueItems": true
17+
}
18+
},
19+
"required": ["$schema", "hiddenVendorIds"],
20+
"additionalProperties": false
21+
}

‎data/$schemas/model-price-intelligence-index.schema.json‎

Lines changed: 89 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,89 @@
1+
{
2+
"$schema": "https://json-schema.org/draft/2020-12/schema",
3+
"title": "Model Price Intelligence Index Configuration",
4+
"description": "Curated model selection, price weighting, and chart-label placement for the model price-intelligence ranking.",
5+
"type": "object",
6+
"properties": {
7+
"$schema": {
8+
"type": "string"
9+
},
10+
"inputShare": {
11+
"type": "number",
12+
"minimum": 0,
13+
"maximum": 1
14+
},
15+
"outputShare": {
16+
"type": "number",
17+
"minimum": 0,
18+
"maximum": 1
19+
},
20+
"models": {
21+
"type": "array",
22+
"items": {
23+
"$ref": "#/$defs/selectedModel"
24+
},
25+
"minItems": 1,
26+
"uniqueItems": true
27+
}
28+
},
29+
"required": ["$schema", "inputShare", "outputShare", "models"],
30+
"additionalProperties": false,
31+
"$defs": {
32+
"labelAnchor": {
33+
"type": "string",
34+
"enum": ["start", "middle", "end"]
35+
},
36+
"selectedModel": {
37+
"type": "object",
38+
"properties": {
39+
"modelId": {
40+
"type": "string",
41+
"pattern": "^[a-z0-9-]+$"
42+
},
43+
"labelDx": {
44+
"type": "number"
45+
},
46+
"labelDy": {
47+
"type": "number"
48+
},
49+
"labelAnchor": {
50+
"$ref": "#/$defs/labelAnchor"
51+
},
52+
"linearLabelDx": {
53+
"type": "number"
54+
},
55+
"linearLabelDy": {
56+
"type": "number"
57+
},
58+
"linearLabelAnchor": {
59+
"$ref": "#/$defs/labelAnchor"
60+
},
61+
"usdPriceOverride": {
62+
"$ref": "#/$defs/usdPriceOverride"
63+
}
64+
},
65+
"required": ["modelId", "labelDx", "labelDy", "labelAnchor"],
66+
"additionalProperties": false
67+
},
68+
"usdPriceOverride": {
69+
"type": "object",
70+
"properties": {
71+
"input": {
72+
"type": "number",
73+
"exclusiveMinimum": 0
74+
},
75+
"output": {
76+
"type": "number",
77+
"exclusiveMinimum": 0
78+
},
79+
"sourceUrl": {
80+
"type": "string",
81+
"format": "uri",
82+
"pattern": "^https://"
83+
}
84+
},
85+
"required": ["input", "output", "sourceUrl"],
86+
"additionalProperties": false
87+
}
88+
}
89+
}

‎data/artificial-analysis-index.json‎

Lines changed: 61 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@
33
"sourceUrl": "https://artificialanalysis.ai/leaderboards/models",
44
"methodologyUrl": "https://artificialanalysis.ai/methodology/intelligence-benchmarking",
55
"indexVersion": "4.1",
6-
"observedAt": "2026-07-26",
6+
"observedAt": "2026-07-27",
77
"legacyMissingModelIds": ["composer", "cursor-composer-2", "cursor-composer-2-5"],
88
"entries": [
99
{
@@ -72,6 +72,12 @@
7272
"estimated": false,
7373
"configuration": "Claude Opus 4.8 (max)"
7474
},
75+
{
76+
"modelId": "claude-opus-5",
77+
"score": 61,
78+
"estimated": false,
79+
"configuration": "Claude Opus 5 (max)"
80+
},
7581
{
7682
"modelId": "claude-sonnet-3",
7783
"score": 5,
@@ -246,6 +252,18 @@
246252
"estimated": true,
247253
"configuration": "Gemini 3 Pro Preview (high)"
248254
},
255+
{
256+
"modelId": "gemma-4-26b-a4b",
257+
"score": 26,
258+
"estimated": false,
259+
"configuration": "Gemma 4 26B A4B (Reasoning)"
260+
},
261+
{
262+
"modelId": "gemma-4-31b",
263+
"score": 29,
264+
"estimated": false,
265+
"configuration": "Gemma 4 31B (Reasoning)"
266+
},
249267
{
250268
"modelId": "glm-4-5",
251269
"score": 19,
@@ -492,6 +510,12 @@
492510
"estimated": true,
493511
"configuration": "Grok Code Fast 1"
494512
},
513+
{
514+
"modelId": "hy3",
515+
"score": 41,
516+
"estimated": false,
517+
"configuration": "Hy3"
518+
},
495519
{
496520
"modelId": "kimi-k2-instruct",
497521
"score": 19,
@@ -576,6 +600,24 @@
576600
"estimated": false,
577601
"configuration": "MiniMax-M3"
578602
},
603+
{
604+
"modelId": "mimo-v2-5",
605+
"score": 37,
606+
"estimated": false,
607+
"configuration": "MiMo-V2.5"
608+
},
609+
{
610+
"modelId": "mimo-v2-5-pro",
611+
"score": 42,
612+
"estimated": false,
613+
"configuration": "MiMo-V2.5-Pro"
614+
},
615+
{
616+
"modelId": "mimo-v2-flash",
617+
"score": 25,
618+
"estimated": false,
619+
"configuration": "MiMo-V2-Flash (Non-reasoning)"
620+
},
579621
{
580622
"modelId": "mistral-medium-3-5",
581623
"score": 30,
@@ -612,6 +654,24 @@
612654
"estimated": true,
613655
"configuration": "o4-mini (high)"
614656
},
657+
{
658+
"modelId": "qwen3-5-122b-a10b",
659+
"score": 32,
660+
"estimated": false,
661+
"configuration": "Qwen3.5 122B A10B (Reasoning)"
662+
},
663+
{
664+
"modelId": "qwen3-5-35b-a3b",
665+
"score": 24,
666+
"estimated": false,
667+
"configuration": "Qwen3.5 35B A3B (Non-reasoning)"
668+
},
669+
{
670+
"modelId": "qwen3-5-397b-a17b",
671+
"score": 34,
672+
"estimated": false,
673+
"configuration": "Qwen3.5 397B A17B (Reasoning)"
674+
},
615675
{
616676
"modelId": "qwen3-coder-30b-a3b",
617677
"score": 14,

0 commit comments

Comments
 (0)