{
  "generated": "2026-09-08",
  "benchmark": "mmmu",
  "results": [
    {
      "system": "GPT-4V(ision) (Playground)",
      "developer": "OpenAI",
      "value": 56.8,
      "date": "2023-11-27",
      "source": {
        "url": "https://arxiv.org/abs/2311.16502",
        "kind": "paper",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "split": "validation",
        "shots": 0,
        "notes": "MMMU paper Table; test-set score 56.1. Best human expert 88.6."
      }
    },
    {
      "system": "GPT-4o (0513)",
      "developer": "OpenAI",
      "value": 69.1,
      "date": "2024-05-13",
      "source": {
        "url": "https://mmmu-benchmark.github.io/",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "split": "validation",
        "notes": "Self-reported entry on the official MMMU leaderboard (source: author)."
      }
    },
    {
      "system": "o3",
      "developer": "OpenAI",
      "value": 82.9,
      "date": "2025-04-16",
      "source": {
        "url": "https://mmmu-benchmark.github.io/",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "split": "validation",
        "notes": "Self-reported entry on the official MMMU leaderboard (source: author). Also reported by OpenAI in the GPT-5 launch chart (82.9)."
      }
    },
    {
      "system": "GPT-5 w/ thinking",
      "developer": "OpenAI",
      "value": 84.2,
      "date": "2025-08-07",
      "source": {
        "url": "https://mmmu-benchmark.github.io/",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "split": "validation",
        "notes": "Self-reported entry on the official MMMU leaderboard (source: author). Matches OpenAI's GPT-5 launch post (84.2)."
      }
    },
    {
      "system": "GPT-5.1",
      "developer": "OpenAI",
      "value": 85.4,
      "date": "2025-11-13",
      "source": {
        "url": "https://mmmu-benchmark.github.io/",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "split": "validation",
        "notes": "Self-reported entry on the official MMMU leaderboard (source: author). Top of the official leaderboard (last updated 2025-09-05 header, entry dated 2025-11-13); within 3 points of the best-expert 88.6."
      }
    }
  ]
}