Add deploy script, eval refresh script and Go-priced eval data
Deploy to Cloudflare Pages / deploy (push) Failing after 25s
Deploy to Cloudflare Pages / deploy (push) Failing after 25s
- scripts/deploy.sh: manual Cloudflare Pages deploy (same steps as CI) - scripts/refresh-evals.mjs: re-scrape Artificial Analysis + OpenCode Data into evals.js - evals.js now carries OpenCode Go list prices; Hy4 and LongCat 2.5 left empty rather than borrowing a neighbouring model's numbers - workflow creates the Pages project idempotently
This commit is contained in:
+24
-24
@@ -1,27 +1,27 @@
|
||||
// Evaluation data scraped from Artificial Analysis model pages (single consistent harness).
|
||||
// Values are already scaled to 0-100. Retrieved 2026-10-21.
|
||||
// Values are already scaled to 0-100. Regenerate with: node scripts/refresh-evals.mjs
|
||||
export const RAW = [
|
||||
{id:"minimax-m3.1-flash-free",n:"MiniMax M3.1 Flash Free",lab:"MiniMax",free:true,pi:0,po:0,ii:42.7,fc:38.6,scicode:53.4,tb21:null,tb40:25.8,tbh:null,tau2:null,taub:null,apex:null,analyst:null,auto:72.5,gpqa:null,critpt:22.3,hle:48.0,lcr:79.7,ifbench:null,mmmu:79.1,gdpv:47.9,gdppdf:20.8,ctx:1048576},
|
||||
{id:"gemini-4-argon-contributor",n:"Gemini 4 Argon Contributor",lab:"Google",pi:4,po:20,ii:52.6,fc:43.5,scicode:61.8,tb21:null,tb40:57.1,tbh:null,tau2:null,taub:null,apex:null,analyst:48.7,auto:77.5,gpqa:null,critpt:27.1,hle:57.1,lcr:79.7,ifbench:null,mmmu:null,gdpv:56.2,gdppdf:21.8,ctx:1048576},
|
||||
{id:"claude-haiku-5-5",n:"Claude Haiku 5.5",lab:"Anthropic",pi:0.1,po:0.5,ii:43.4,fc:41.8,scicode:55.0,tb21:null,tb40:32.8,tbh:null,tau2:null,taub:null,apex:null,analyst:53.8,auto:35.4,gpqa:null,critpt:18.9,hle:44.4,lcr:82.7,ifbench:null,mmmu:null,gdpv:55.9,gdppdf:20.8,ctx:1000000},
|
||||
{id:"beam-free",n:"Beam Free",lab:"Reflection",free:true,pi:0,po:0,ii:30.3,fc:null,scicode:48.5,tb21:null,tb40:3.0,tbh:null,tau2:null,taub:null,apex:null,analyst:null,auto:48.5,gpqa:null,critpt:13.1,hle:34.7,lcr:78.0,ifbench:null,mmmu:null,gdpv:33.9,gdppdf:11.6,ctx:1048576},
|
||||
{id:"longcat-2.5-preview-free",n:"LongCat 2.5 Preview Free",lab:"Meituan",free:true,pi:0,po:0,ii:null,ctx:1000000},
|
||||
{id:"mimo-v2.6-pro",n:"MiMo-V2.6-Pro",lab:"Xiaomi",pi:0.435,po:0.87,ii:46.3,fc:45.4,scicode:60.9,tb21:null,tb40:34.8,tbh:null,tau2:null,taub:null,apex:null,analyst:37.5,auto:58.6,gpqa:null,critpt:26.6,hle:49.4,lcr:86.3,ifbench:null,mmmu:null,gdpv:59.2,gdppdf:19.2,ctx:1048576},
|
||||
{id:"gpt-6-luna",n:"GPT-6 Luna",lab:"OpenAI",pi:0.1,po:0.5,ii:38.1,fc:41.9,scicode:54.6,tb21:null,tb40:12.6,tbh:null,tau2:null,taub:null,apex:null,analyst:43.8,auto:53.2,gpqa:null,critpt:19.4,hle:38.5,lcr:83.3,ifbench:null,mmmu:79.7,gdpv:46.6,gdppdf:22.8,ctx:1050000},
|
||||
{id:"grok-4.7",n:"Grok 4.7",lab:"xAI",pi:2,po:6,ii:46.4,fc:33.8,scicode:57.4,tb21:null,tb40:25.8,tbh:null,tau2:null,taub:null,apex:null,analyst:52.5,auto:65.6,gpqa:null,critpt:17.7,hle:43.1,lcr:76.7,ifbench:null,mmmu:null,gdpv:60.6,gdppdf:20.0,ctx:500000},
|
||||
{id:"step-5-preview",n:"Step 5 Preview",lab:"StepFun",pi:1,po:2.7,ii:43.7,fc:38.4,scicode:58.9,tb21:null,tb40:33.3,tbh:null,tau2:null,taub:null,apex:38.0,analyst:35.0,auto:51.0,gpqa:null,critpt:20.9,hle:46.5,lcr:88.3,ifbench:null,mmmu:76.4,gdpv:54.3,gdppdf:14.8,ctx:1000000},
|
||||
{id:"deepseek-v4.1-flash",n:"DeepSeek V4.1 Flash",lab:"DeepSeek",pi:0.15,po:0.6,ii:39.5,fc:44.0,scicode:51.9,tb21:null,tb40:26.8,tbh:null,tau2:null,taub:null,apex:null,analyst:35.0,auto:68.9,gpqa:null,critpt:14.3,hle:39.2,lcr:84.0,ifbench:null,mmmu:77.0,gdpv:55.0,gdppdf:12.8,ctx:1000000},
|
||||
{id:"muse-spark-1.3-contributor",n:"Muse Spark 1.3 Contributor",lab:"Meta",pi:0.1,po:0.2,ii:48.1,fc:40.6,scicode:58.8,tb21:84.3,tb40:33.3,tbh:null,tau2:null,taub:50.5,apex:null,analyst:37.5,auto:57.9,gpqa:93.5,critpt:24.9,hle:48.7,lcr:83.0,ifbench:null,mmmu:null,gdpv:59.0,gdppdf:26.6,ctx:1048576},
|
||||
{id:"hy4-preview",n:"Hy4 preview",lab:"Tencent",pi:0.834,po:2.501,ii:null,ctx:1024000},
|
||||
{id:"qwen3.8-flash",n:"Qwen3.8 Flash",lab:"Alibaba",pi:0.15,po:0.47,ii:39.8,fc:null,scicode:50.6,tb21:86.1,tb40:25.3,tbh:null,tau2:null,taub:45.4,apex:null,analyst:null,auto:55.9,gpqa:92.3,critpt:11.1,hle:38.0,lcr:79.7,ifbench:null,mmmu:79.8,gdpv:56.4,gdppdf:15.6,ctx:1000000,note:"AA entry: Qwen3.8-Flash-Next"},
|
||||
{id:"glm-5.3-flash",n:"GLM-5.3-Flash",lab:"Zhipu",pi:0.15,po:0.5,ii:41.8,fc:41.0,scicode:51.6,tb21:84.3,tb40:32.8,tbh:null,tau2:null,taub:47.2,apex:null,analyst:25.0,auto:60.4,gpqa:91.2,critpt:15.4,hle:39.9,lcr:80.0,ifbench:null,mmmu:null,gdpv:57.1,gdppdf:15.4,ctx:1000000},
|
||||
{id:"glm-5.3",n:"GLM-5.3",lab:"Zhipu",pi:1.4,po:4.4,ii:44.8,fc:40.1,scicode:59.0,tb21:83.9,tb40:41.9,tbh:null,tau2:null,taub:50.3,apex:null,analyst:38.8,auto:62.2,gpqa:91.7,critpt:19.1,hle:42.3,lcr:79.7,ifbench:null,mmmu:null,gdpv:57.5,gdppdf:11.2,ctx:1000000},
|
||||
{id:"qwen3.8-max",n:"Qwen3.8 Max",lab:"Alibaba",pi:2,po:6,ii:45.4,fc:43.2,scicode:52.1,tb21:88.8,tb40:38.9,tbh:null,tau2:null,taub:47.8,apex:42.4,analyst:45.0,auto:56.2,gpqa:92.8,critpt:17.7,hle:43.1,lcr:80.3,ifbench:null,mmmu:82.8,gdpv:58.2,gdppdf:22.8,ctx:1000000},
|
||||
{id:"kimi-k3",n:"Kimi K3",lab:"Moonshot",pi:3,po:15,ii:43.6,fc:43.6,scicode:59.5,tb21:85.0,tb40:12.6,tbh:null,tau2:null,taub:46.0,apex:41.3,analyst:38.8,auto:58.3,gpqa:93.5,critpt:23.4,hle:46.9,lcr:88.7,ifbench:null,mmmu:80.5,gdpv:51.6,gdppdf:22.0,ctx:1048576},
|
||||
{id:"kimi-k2.7-code",n:"Kimi K2.7 Code",lab:"Moonshot",pi:0.95,po:4,ii:25.8,fc:null,scicode:47.8,tb21:67.4,tb40:1.0,tbh:44.7,tau2:90.1,taub:20.2,apex:null,analyst:null,auto:24.5,gpqa:89.6,critpt:10.0,hle:35.0,lcr:79.3,ifbench:63.1,mmmu:null,gdpv:26.9,gdppdf:11.2,ctx:262144},
|
||||
{id:"qwen3.7-plus",n:"Qwen3.7 Plus",lab:"Alibaba",pi:0.4,po:1.6,ii:25.2,fc:null,scicode:46.1,tb21:61.0,tb40:1.0,tbh:47.0,tau2:93.0,taub:17.5,apex:22.4,analyst:null,auto:17.4,gpqa:90.0,critpt:9.1,hle:35.6,lcr:73.0,ifbench:78.0,mmmu:80.5,gdpv:13.4,gdppdf:12.2,ctx:1000000},
|
||||
{id:"minimax-m3",n:"MiniMax M3",lab:"MiniMax",pi:0.3,po:1.2,ii:29.2,fc:23.0,scicode:47.1,tb21:65.2,tb40:2.0,tbh:42.4,tau2:88.9,taub:15.3,apex:null,analyst:10.0,auto:21.3,gpqa:92.9,critpt:3.7,hle:39.0,lcr:83.0,ifbench:82.9,mmmu:78.6,gdpv:37.1,gdppdf:9.8,ctx:1048576},
|
||||
{id:"deepseek-v4-pro",n:"DeepSeek V4 Pro",lab:"DeepSeek",pi:0.66,po:1.98,ii:36.0,fc:38.8,scicode:51.0,tb21:78.7,tb40:14.1,tbh:null,tau2:null,taub:39.6,apex:null,analyst:null,auto:56.7,gpqa:92.8,critpt:18.0,hle:41.0,lcr:80.3,ifbench:null,mmmu:null,gdpv:47.4,gdppdf:11.4,ctx:1000000},
|
||||
{id:"mimo-v2.5-pro",n:"MiMo-V2.5-Pro",lab:"Xiaomi",pi:0.435,po:0.87,ii:26.0,fc:null,scicode:50.6,tb21:65.2,tb40:0.0,tbh:43.2,tau2:94.2,taub:9.9,apex:2.4,analyst:20.0,auto:13.7,gpqa:86.6,critpt:4.0,hle:35.7,lcr:79.7,ifbench:79.9,mmmu:null,gdpv:31.0,gdppdf:4.0,ctx:1048576},
|
||||
{id:"mimo-v2.5",n:"MiMo-V2.5",lab:"Xiaomi",pi:0.14,po:0.28,ii:21.8,fc:null,scicode:43.9,tb21:63.7,tb40:0.0,tbh:41.7,tau2:90.6,taub:8.7,apex:null,analyst:null,auto:18.4,gpqa:84.9,critpt:3.7,hle:27.2,lcr:73.0,ifbench:67.1,mmmu:75.4,gdpv:24.9,gdppdf:4.0,ctx:1048576}
|
||||
{"id":"minimax-m3.1-flash-free","n":"MiniMax M3.1 Flash Free","lab":"MiniMax","free":true,"pi":0,"po":0,"ii":42.7,"fc":38.6,"scicode":53.4,"tb21":null,"tb40":25.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":null,"auto":72.5,"gpqa":null,"critpt":22.3,"hle":48,"lcr":79.7,"ifbench":null,"mmmu":79.1,"gdpv":47.9,"gdppdf":20.8,"ctx":1000000},
|
||||
{"id":"gemini-4-argon-contributor","n":"Gemini 4 Argon Contributor","lab":"Google","free":false,"pi":4,"po":20,"ii":52.6,"fc":43.5,"scicode":61.8,"tb21":null,"tb40":57.1,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":48.8,"auto":77.5,"gpqa":null,"critpt":27.1,"hle":57.1,"lcr":79.7,"ifbench":null,"mmmu":null,"gdpv":56.2,"gdppdf":21.8,"ctx":1048576},
|
||||
{"id":"claude-haiku-5-5","n":"Claude Haiku 5.5","lab":"Anthropic","free":false,"pi":0.1,"po":0.5,"ii":43.4,"fc":41.8,"scicode":55,"tb21":null,"tb40":32.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":53.8,"auto":35.4,"gpqa":null,"critpt":18.9,"hle":44.4,"lcr":82.7,"ifbench":null,"mmmu":null,"gdpv":55.9,"gdppdf":20.8,"ctx":1000000},
|
||||
{"id":"beam-free","n":"Beam Free","lab":"Reflection AI","free":true,"pi":0,"po":0,"ii":30.3,"fc":null,"scicode":48.5,"tb21":null,"tb40":3,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":null,"auto":48.5,"gpqa":null,"critpt":13.1,"hle":34.7,"lcr":78,"ifbench":null,"mmmu":null,"gdpv":33.9,"gdppdf":11.6,"ctx":1048576},
|
||||
{"id":"longcat-2.5-preview-free","n":"LongCat 2.5 Preview Free","lab":"Meituan","free":true,"pi":0,"po":0,"ii":null,"fc":null,"scicode":null,"tb21":null,"tb40":null,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":null,"auto":null,"gpqa":null,"critpt":null,"hle":null,"lcr":null,"ifbench":null,"mmmu":null,"gdpv":null,"gdppdf":null,"ctx":1000000},
|
||||
{"id":"mimo-v2.6-pro","n":"MiMo-V2.6-Pro","lab":"Xiaomi","free":false,"pi":0.435,"po":0.87,"ii":46.3,"fc":45.4,"scicode":60.9,"tb21":null,"tb40":34.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":37.5,"auto":58.6,"gpqa":null,"critpt":26.6,"hle":49.4,"lcr":86.3,"ifbench":null,"mmmu":null,"gdpv":59.2,"gdppdf":19.2,"ctx":1048576},
|
||||
{"id":"gpt-6-luna","n":"GPT-6 Luna","lab":"OpenAI","free":false,"pi":0.1,"po":0.5,"ii":38.1,"fc":41.9,"scicode":54.6,"tb21":null,"tb40":12.6,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":43.8,"auto":53.2,"gpqa":null,"critpt":19.4,"hle":38.5,"lcr":83.3,"ifbench":null,"mmmu":79.7,"gdpv":46.6,"gdppdf":22.8,"ctx":1050000},
|
||||
{"id":"grok-4.7","n":"Grok 4.7","lab":"xAI","free":false,"pi":2,"po":6,"ii":46.4,"fc":33.8,"scicode":57.4,"tb21":null,"tb40":25.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":52.5,"auto":65.6,"gpqa":null,"critpt":17.7,"hle":43.1,"lcr":76.7,"ifbench":null,"mmmu":null,"gdpv":60.6,"gdppdf":20,"ctx":500000},
|
||||
{"id":"step-5-preview","n":"Step 5 Preview","lab":"StepFun","free":false,"pi":1,"po":2.7,"ii":43.7,"fc":38.4,"scicode":58.9,"tb21":null,"tb40":33.3,"tbh":null,"tau2":null,"taub":null,"apex":38,"analyst":35,"auto":51,"gpqa":null,"critpt":20.9,"hle":46.5,"lcr":88.3,"ifbench":null,"mmmu":76.4,"gdpv":54.3,"gdppdf":14.8,"ctx":1000000},
|
||||
{"id":"deepseek-v4.1-flash","n":"DeepSeek V4.1 Flash","lab":"DeepSeek","free":false,"pi":0.15,"po":0.6,"ii":39.5,"fc":44,"scicode":51.9,"tb21":null,"tb40":26.8,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":35,"auto":68.9,"gpqa":null,"critpt":14.3,"hle":39.2,"lcr":84,"ifbench":null,"mmmu":77,"gdpv":55,"gdppdf":12.8,"ctx":1000000},
|
||||
{"id":"muse-spark-1.3-contributor","n":"Muse Spark 1.3 Contributor","lab":"Meta","free":false,"pi":0.1,"po":0.2,"ii":48.1,"fc":40.6,"scicode":58.8,"tb21":84.3,"tb40":33.3,"tbh":null,"tau2":null,"taub":50.5,"apex":null,"analyst":37.5,"auto":57.9,"gpqa":93.5,"critpt":24.9,"hle":48.7,"lcr":83,"ifbench":null,"mmmu":null,"gdpv":59,"gdppdf":26.6,"ctx":1048576},
|
||||
{"id":"hy4-preview","n":"Hy4 preview","lab":"Tencent","free":false,"pi":0.834,"po":2.501,"ii":null,"fc":null,"scicode":null,"tb21":null,"tb40":null,"tbh":null,"tau2":null,"taub":null,"apex":null,"analyst":null,"auto":null,"gpqa":null,"critpt":null,"hle":null,"lcr":null,"ifbench":null,"mmmu":null,"gdpv":null,"gdppdf":null,"ctx":1024000},
|
||||
{"id":"qwen3.8-flash","n":"Qwen3.8 Flash","lab":"Alibaba","free":false,"pi":0.15,"po":0.47,"ii":39.8,"fc":null,"scicode":50.6,"tb21":86.1,"tb40":25.3,"tbh":null,"tau2":null,"taub":45.4,"apex":null,"analyst":null,"auto":55.9,"gpqa":92.3,"critpt":11.1,"hle":38,"lcr":79.7,"ifbench":null,"mmmu":79.8,"gdpv":56.4,"gdppdf":15.6,"ctx":1000000},
|
||||
{"id":"glm-5.3-flash","n":"GLM-5.3-Flash","lab":"Zhipu","free":false,"pi":0.15,"po":0.5,"ii":41.8,"fc":41,"scicode":51.6,"tb21":84.3,"tb40":32.8,"tbh":null,"tau2":null,"taub":47.2,"apex":null,"analyst":25,"auto":60.4,"gpqa":91.2,"critpt":15.4,"hle":39.9,"lcr":80,"ifbench":null,"mmmu":null,"gdpv":57.1,"gdppdf":15.4,"ctx":1000000},
|
||||
{"id":"glm-5.3","n":"GLM-5.3","lab":"Zhipu","free":false,"pi":1.4,"po":4.4,"ii":44.8,"fc":40.1,"scicode":59,"tb21":83.9,"tb40":41.9,"tbh":null,"tau2":null,"taub":50.3,"apex":null,"analyst":38.8,"auto":62.2,"gpqa":91.7,"critpt":19.1,"hle":42.3,"lcr":79.7,"ifbench":null,"mmmu":null,"gdpv":57.5,"gdppdf":11.2,"ctx":1000000},
|
||||
{"id":"qwen3.8-max","n":"Qwen3.8 Max","lab":"Alibaba","free":false,"pi":2,"po":6,"ii":45.4,"fc":43.2,"scicode":52.1,"tb21":88.8,"tb40":38.9,"tbh":null,"tau2":null,"taub":47.8,"apex":42.4,"analyst":45,"auto":56.2,"gpqa":92.8,"critpt":17.7,"hle":43.1,"lcr":80.3,"ifbench":null,"mmmu":82.8,"gdpv":58.2,"gdppdf":22.8,"ctx":1000000},
|
||||
{"id":"kimi-k3","n":"Kimi K3","lab":"Moonshot","free":false,"pi":3,"po":15,"ii":43.6,"fc":43.6,"scicode":59.5,"tb21":85,"tb40":12.6,"tbh":null,"tau2":null,"taub":46,"apex":41.3,"analyst":38.8,"auto":58.3,"gpqa":93.5,"critpt":23.4,"hle":46.9,"lcr":88.7,"ifbench":null,"mmmu":80.5,"gdpv":51.6,"gdppdf":22,"ctx":1048576},
|
||||
{"id":"kimi-k2.7-code","n":"Kimi K2.7 Code","lab":"Moonshot","free":false,"pi":0.95,"po":4,"ii":25.8,"fc":null,"scicode":47.8,"tb21":67.4,"tb40":1,"tbh":44.7,"tau2":90.1,"taub":20.2,"apex":null,"analyst":null,"auto":24.5,"gpqa":89.6,"critpt":10,"hle":35,"lcr":79.3,"ifbench":63.1,"mmmu":null,"gdpv":26.9,"gdppdf":11.2,"ctx":262144},
|
||||
{"id":"qwen3.7-plus","n":"Qwen3.7 Plus","lab":"Alibaba","free":false,"pi":0.4,"po":1.6,"ii":25.2,"fc":null,"scicode":46.1,"tb21":61,"tb40":1,"tbh":47,"tau2":93,"taub":17.5,"apex":22.4,"analyst":null,"auto":17.4,"gpqa":90,"critpt":9.1,"hle":35.6,"lcr":73,"ifbench":78,"mmmu":80.5,"gdpv":13.4,"gdppdf":12.2,"ctx":1000000},
|
||||
{"id":"minimax-m3","n":"MiniMax M3","lab":"MiniMax","free":false,"pi":0.3,"po":1.2,"ii":29.2,"fc":23,"scicode":47.1,"tb21":65.2,"tb40":2,"tbh":42.4,"tau2":88.9,"taub":15.3,"apex":null,"analyst":10,"auto":21.3,"gpqa":92.9,"critpt":3.7,"hle":39,"lcr":83,"ifbench":82.9,"mmmu":78.6,"gdpv":37.1,"gdppdf":9.8,"ctx":1048576},
|
||||
{"id":"deepseek-v4-pro","n":"DeepSeek V4 Pro","lab":"DeepSeek","free":false,"pi":0.66,"po":1.98,"ii":36,"fc":38.8,"scicode":51,"tb21":78.7,"tb40":14.1,"tbh":null,"tau2":null,"taub":39.6,"apex":null,"analyst":null,"auto":56.7,"gpqa":92.8,"critpt":18,"hle":41,"lcr":80.3,"ifbench":null,"mmmu":null,"gdpv":47.4,"gdppdf":11.4,"ctx":1000000},
|
||||
{"id":"mimo-v2.5-pro","n":"MiMo-V2.5-Pro","lab":"Xiaomi","free":false,"pi":0.435,"po":0.87,"ii":26,"fc":null,"scicode":50.6,"tb21":65.2,"tb40":0,"tbh":43.2,"tau2":94.2,"taub":9.9,"apex":2.4,"analyst":20,"auto":13.7,"gpqa":86.6,"critpt":4,"hle":35.7,"lcr":79.7,"ifbench":79.9,"mmmu":null,"gdpv":31,"gdppdf":4,"ctx":1048576},
|
||||
{"id":"mimo-v2.5","n":"MiMo-V2.5","lab":"Xiaomi","free":false,"pi":0.14,"po":0.28,"ii":21.8,"fc":null,"scicode":43.9,"tb21":63.7,"tb40":0,"tbh":41.7,"tau2":90.6,"taub":8.7,"apex":null,"analyst":null,"auto":18.4,"gpqa":84.9,"critpt":3.7,"hle":27.2,"lcr":73,"ifbench":67.1,"mmmu":75.4,"gdpv":24.9,"gdppdf":4,"ctx":1048576}
|
||||
];
|
||||
|
||||
Reference in New Issue
Block a user