ATProto Browser

{
  "text": "Results? \n\nWe tested\n ✅ GPT-4o (end-to-end audio)\n ✅ GPT pipeline (transcribe + text + TTS)\n ✅ Gemini 2.0 Flash\n ✅ Gemini 2.5 Pro\n\nWe find GPT-4o shines on latency & tone while Gemini 2.5 leads in safety & prompt adherence.\n\nNo model wins everything. (3/5)",
  "$type": "app.bsky.feed.post",
  "embed": {
    "$type": "app.bsky.embed.images",
    "images": [
      {
        "alt": "Bar chart comparing the performance of four models (GPT-4o, GPT Pipeline, Gemini 2.0, and Gemini 2.5) across seven tasks: Jeopardy, Function Calling, Prompt Following, Pronunciation Control, Turn Taking, Deception, and Jailbreaking. GPT-4o generally leads in Jeopardy and Pronunciation Control, while Gemini models perform better in Prompt Following and Jailbreaking (notably, lower is better for Jailbreaking). GPT Pipeline shows moderate performance across tasks. Gemini 2.5 consistently improves on Gemini 2.0, especially in Turn Taking and Prompt Following. The chart uses color-coded bars and icons to categorize tasks (e.g., timing, security, dialogue).",
        "image": {
          "$type": "blob",
          "ref": {
            "$link": "bafkreiawdf5rvsft6odzvvjs7uns72wunphv63yxnyt6sk2ls43gdlyilu"
          },
          "mimeType": "image/jpeg",
          "size": 180102
        },
        "aspectRatio": {
          "width": 960,
          "height": 540
        }
      }
    ]
  },
  "langs": [
    "en"
  ],
  "reply": {
    "root": {
      "cid": "bafyreiclrdnpvgknmlgoppvcdq6p2zsnrwhk5f4zcpzlw2r25gkqmfyu2e",
      "uri": "at://did:plc:exj4ro3xzv7id2hstt5ys5j5/app.bsky.feed.post/3lols6uotzs2x"
    },
    "parent": {
      "cid": "bafyreica427ytr7p7zidfufkj6ylsshjv3ime5ahjhip4xcpt6vprv3sbe",
      "uri": "at://did:plc:exj4ro3xzv7id2hstt5ys5j5/app.bsky.feed.post/3lols6vgdyc2x"
    }
  },
  "createdAt": "2025-05-07T16:15:12.428Z"
}