モデル比較
人気のAIモデルを性能・価格・特徴で比較
69.2SWE-Bench Pro58.6
93.6GPQA Diamond93.6
—ARC-AGI-285
57.9HLE52.2
—FrontierMath35.4
88.6SWE-bench Verified—
58.6SWE-Bench Pro64.3
93.6GPQA Diamond—
85ARC-AGI-2—
52.2HLE—
35.4FrontierMath—
64.6SWE-Bench Pro64.3
64.7SWE-Bench Pro58.6
—GPQA Diamond93.6
—ARC-AGI-285
—HLE52.2
—FrontierMath35.4