# | Article Title | News Link | Source Image | When Posted | Writer | Article Thumb |
|---|---|---|---|---|---|---|
1 | Researchers build Humanity’s Last Exam AI benchmark | ETIH EdTech News | https://news.google.com/read/CBMiwgFBVV95cUxQUXdjUGZxenBUOEZnUE9UbHl3OHRJbUFKQmJwZWZ2RVF3RmhWSVh1MExLYnhqOHoyVmNqSnVOOWtSQmg5LWdZTGlfdVZwM05hWXNkZWNvRmU4LTMyWkJIS2RwOEpTYzRIX3VVMzZxNkJNSmhheGduOWZINzdVRF93WXVETGZEOXp0STVMaGIyUkt2TU1aQUZ6RXhBQ3pVcndENzc2NnBtWDkxcFdZOEVxYlhTRE9HU3ByQUYxb3E0N0VhZw?hl=en-CA&gl=CA&ceid=CA%3Aen | https://encrypted-tbn3.gstatic.com/faviconV2?url=https://www.edtechinnovationhub.com&client=NEWS_360&size=96&type=FAVICON&fallback_opts=TYPE,SIZE,URL | Mar 9 | By Emma Thompson | https://news.google.com/api/attachments/CC8iL0NnNUJjbWh2TjBNdFpIRnRTSFZ4VFJEU0F4aVRCU2dLTWdrQlFJZ3hLR1NocXdF=-w200-h112-p-df-rw |
2 | OpenAI’s New GPT‑5.4 Surpasses Human Benchmark in Desktop Navigation and Reasoning Tests | https://news.google.com/read/CBMiuAFBVV95cUxOcjhTX2JwbnE5UVJOWWFieTRucjdPbHpVUUhYdmxmVjA5RE4yWUkzTlB5QlIzeTg3TVRGb3hvdGNaMzRqZy1BSzBOUGt0cEV1eUppOTV1TXRnODFMOEtvVHFOeWxHWk1fazdLSGpFMGlMTEFib1Nxazh2WUpRcmlySjlzc2JqdHM4NEl5bVZFMGZOVUQ0R3pPVEx1dF9uVGlQRUtiZzh4QTNyZEl4V0FLSlNXY1NJTG5X?hl=en-CA&gl=CA&ceid=CA%3Aen | https://encrypted-tbn2.gstatic.com/faviconV2?url=https://www.extremetech.com&client=NEWS_360&size=96&type=FAVICON&fallback_opts=TYPE,SIZE,URL | Mar 10 | By Devesh Beri | https://news.google.com/api/attachments/CC8iK0NnNUNXV1JQVHpBeFlXMWlMV1ZYVFJDZkF4ampCU2dLTWdZRlVZenF2UVE=-w200-h112-p-df-rw |
3 | Smart Pension unveils UK-first human capital benchmark for £4.4bn equity fund | https://news.google.com/read/CBMiuAFBVV95cUxQdzBoM3NzV0FQV0NXS1NkM3BGeXRnakZ3UXNKY0xzTmc3enhtakotWEppakY0YkktU3RRMUpYN3JnRlRadGdEeS0yVjJTT09lM21sb2hSUFhxZHFHMUU0alZmcXRTSm8yMDhkQ3ZJa0M4Rm5qMERNZlhwNmt5RWg3bF9jdGJSWklXaE9sSEpjZENqcGg3SWxrVDlUT0NmdkFuUXhPLVhYeFUybW9QUV9DRWJGZUZORmkz?hl=en-CA&gl=CA&ceid=CA%3Aen | https://encrypted-tbn1.gstatic.com/faviconV2?url=https://www.ipe.com&client=NEWS_360&size=96&type=FAVICON&fallback_opts=TYPE,SIZE,URL | Mar 19 | By Krystle Higgins | https://news.google.com/api/attachments/CC8iK0NnNTVNemt0UmxjM1dFaDRXRVp4VFJDM0FSaVRBaWdCTWdZeGNZcVdQQVE=-w200-h112-p-df-rw |
4 | AI benchmarks are broken. Here’s what we need instead. | https://news.google.com/read/CBMipwFBVV95cUxQZGQ3dHlENnVNVmlwbWE3VFplQzJCZ0NhV1NLbUl6RmZzbk1YTF9tbmh1OTJ0V0dnYXdzRmZRaGZQdEdiVVBNbmVMUWV4NEpNMENLMUxsRkxPekl1VVJneEt6c0VVZzA5dHU2a3JJS0wtcHRBcTlQcUxJa0tFVk55OFZkeUJaaEt2QlNHc0Fsel84dGVEWDVFUVVfOFFlZGtack1tenhlWdIBrAFBVV95cUxOUnpwejZHN3NwcVpmRk1iTzk1dkdpNTZKbGY2TEduYXNjdXRxeC1uY3gxVnh6NGlPVGpqY3N6THVmeWkwNGlXYTUtX2YwbTJCVnFkc0I5U09CZEFzRGZnTjA4T0Fma2JwUGxUOF9PUUlWTkE0NjRLbjJNM3RCUUdKaHRpWGlmcV8zT1JrSVBmMmZkd1FOWi12YkR1c0x0YUtmejZCNTRBdE1zQVU5?hl=en-CA&gl=CA&ceid=CA%3Aen | https://encrypted-tbn0.gstatic.com/faviconV2?url=https://www.technologyreview.com&client=NEWS_360&size=96&type=FAVICON&fallback_opts=TYPE,SIZE,URL | Mar 31 | By Angela Aristidou | https://news.google.com/api/attachments/CC8iK0NnNW5hek53VFVVdFNqRjJYM3BEVFJERUF4aW5CU2dLTWdZQlZZck5LUWM=-w200-h112-p-df-rw |
5 | A benchmark of expert-level academic questions to assess AI capabilities | https://news.google.com/read/CBMiX0FVX3lxTE93bU50WWJqVzdWR0RFOEpmYVZ4MXVLaEFGLUtzVGxkZDQzTloyRndvU1F2NzkzQXpxU2Vwbjg4ck9Pb2NPaXgwcElhV0g4X3lfcDlEamh6LVh0eUlmWVZr?hl=en-CA&gl=CA&ceid=CA%3Aen | https://encrypted-tbn1.gstatic.com/faviconV2?url=https://www.nature.com&client=NEWS_360&size=96&type=FAVICON&fallback_opts=TYPE,SIZE,URL | Jan 28 | - | https://news.google.com/api/attachments/CC8iJ0NnNHRNbkIxVms1SlJWSlBhME13VFJESUFoaXRCU2dLTWdNQmNBSQ=-w200-h112-p-df-rw |
Keyword |
|---|
human benchmark |