data/capability_scores.json

{
  "_metric": "Artificial Analysis Intelligence Index",
  "_snapshot": "2026-06-18",
  "_source": "https://artificialanalysis.ai/evaluations/artificial-analysis-intelligence-index (snapshot via benchlm.ai aggregation)",
  "_note": "Single-number capability aggregate (a normalized mean of capability benchmarks — built the same way as Raidex's RAI Score). Keyed by Raidex model_name (the leaderboard 'Model' column). Models without a published score on this snapshot's index version are omitted rather than mixed across versions: mistral-large-latest. Meta-Llama-3.3-70B-Instruct (AA ~14), claude-haiku-4-5-20251001 (AA 24) and Qwen3-235B-A22B-Instruct-2507 (AA 25) added from the artificialanalysis.ai model pages — all NON-reasoning index variants, matching the config Raidex evaluates (temperature 0, no extended-thinking budget; the reasoning variants score higher), consistent with this snapshot's gpt-4o~11 scale. Roster-widening open-weight batch (MiniMax-M2.7, gemma-4-31B-it, DeepSeek-V3.1, phi-4) read off the same benchlm snapshot to enrich the capability-vs-RAI scatter.",
  "scores": {
    "claude-opus-4-8": 55.7,
    "gpt-5.5": 54.8,
    "gpt-5.2": 42.2,
    "grok-4.3": 37.6,
    "claude-sonnet-4-6": 35.9,
    "Qwen3-235B-A22B-Instruct-2507": 25.0,
    "DeepSeek-V3.2": 24.7,
    "claude-haiku-4-5-20251001": 24.0,
    "gpt-oss-120b": 23.8,
    "gemini-2.5-flash": 14.1,
    "Meta-Llama-3.3-70B-Instruct": 14.0,
    "gpt-4o": 11.2,
    "gpt-4o-mini": 6.9,
    "gemma-3-27b-it": 4.8,
    "MiniMax-M2.7": 38.1,
    "gemma-4-31B-it": 29.4,
    "DeepSeek-V3.1": 21.1,
    "phi-4": 4.9
  }
}