{
  "type": "tweet",
  "id": "2071356504805142532",
  "url": "https://x.com/github/status/2071356504805142532",
  "twitterUrl": "https://twitter.com/github/status/2071356504805142532",
  "text": "We benchmarked the GitHub Copilot agentic harness against the harnesses that ship leading models natively.\n\nHolding the model and task fixed across SWE-bench Verified, SWE-bench Pro, SkillsBench, TerminalBench, and Win-Hill, the results were clear:\n✅ Task resolution on par with model-vendor harnesses\n✅ Fewer tokens across most configurations\n\n💡 A key learning: With GitHub Copilot supporting more than 20 models, you're free to pick efficiency or peak quality per task.",
  "source": "Twitter for iPhone",
  "retweetCount": 42,
  "replyCount": 43,
  "likeCount": 366,
  "quoteCount": 7,
  "viewCount": 56357,
  "createdAt": "Sun Jun 28 22:14:09 +0000 2026",
  "lang": "en",
  "bookmarkCount": 112,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2071356504805142532",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "github",
    "url": "https://x.com/github",
    "twitterUrl": "https://twitter.com/github",
    "id": "13334762",
    "name": "GitHub",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": "Business",
    "profilePicture": "https://pbs.twimg.com/profile_images/2051404708766507008/ATxxTJXO_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/13334762/1780668208",
    "description": "",
    "location": "San Francisco, CA",
    "followers": 2675803,
    "following": 333,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Mon Feb 11 04:41:50 +0000 2008",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 8743,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 3022,
    "statusesCount": 10643,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2061868355934654624"
    ],
    "profile_bio": {
      "description": "The AI-powered developer platform to build, scale, and deliver secure software.",
      "entities": {
        "description": {},
        "url": {
          "urls": [
            {
              "display_url": "github.com",
              "expanded_url": "http://github.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/bbJgfyzKzp"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/Pfu2nN3Son",
        "expanded_url": "https://twitter.com/github/status/2071356504805142532/photo/1",
        "ext_alt_text": "Scatter plot titled \"Resolution rate vs. cost per task,\" plotting resolution rate (pass@1, y-axis, 62–78%) against mean cost per task in USD (x-axis, $0.40–$1.40). Each marker is one agent × model configuration (mean of 5 runs on Terminal-Bench 2), surrounded by a shaded ±1σ ellipse. A legend identifies three agents by color: Copilot CLI (purple), Codex CLI (gray), and Claude Code (teal). The subtitle notes that up and to the left is better: higher resolution at lower cost. A dashed vertical line splits the points into two clusters: lower-cost GPT-family models (GPT-5.4 and GPT-5.5) on the left, and higher-cost Claude-family models (Sonnet 4.6 and Opus 4.7) on the right.",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2071355444950667264",
        "indices": [
          279,
          302
        ],
        "media_key": "3_2071355444950667264",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy+7s172xAACgACHL7vxEAa8AQAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHL7uzXvbEAAKAAIcvu/EQBrwBAAA",
            "media_key": "3_2071355444950667264"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HL7uzXvbEAAJpng.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 860,
              "w": 1535,
              "x": 0,
              "y": 0
            },
            {
              "h": 1013,
              "w": 1013,
              "x": 453,
              "y": 0
            },
            {
              "h": 1013,
              "w": 889,
              "x": 515,
              "y": 0
            },
            {
              "h": 1013,
              "w": 507,
              "x": 706,
              "y": 0
            },
            {
              "h": 1013,
              "w": 1535,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1013,
          "width": 1535
        },
        "sizes": {
          "large": {
            "h": 1013,
            "w": 1535
          }
        },
        "type": "photo",
        "url": "https://t.co/Pfu2nN3Son"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}