ARC Prize 公布 Gemini 4 Argon 在 ARC-AGI 的测试结果
In addition to its strong performance on ARC-AGI-3 using the provider adapter harness (which preserves opaque reasoning and enables automatic compaction), Argon
ARC Prize 公布 Google Gemini 4 Argon 在 ARC-AGI 上的测试结果：ARC-AGI-3 在 provider adapter harness 下得分 97.5%、成本 4.8K 美元，标准 harness 下低推理档 49.8%、中推理档 46.3%，高推理档仅完成 55 个游戏中的 19 个因此未公布分数。ARC-AGI-2 为 91.3%、每任务 0.32 美元，ARC-AGI-1 为 98.5%、每任务 0.16 美元。ARC Prize 称 Argon 是第二个在 ARC-AGI-3 上超过 95% 的前沿实验室模型，其 97.5% 仅次于 GPT-6 Astra 的 99.9%，并在 25 个公开游戏中比人类基线少用 62% 的动作。成本按当前每百万 token 输入 2 美元、输出 10 美元的入门价格计算。
推荐理由
AI 评分 77
ARC Prize 公布 Gemini 4 Argon 在 ARC-AGI 三个版本上的成绩与成本，并说明标准测试框架下因 API 问题未能跑完全部游戏。
主题
正文
当前显示原文，中文全文译文尚未就绪。
In addition to its strong performance on ARC-AGI-3 using the provider adapter harness (which preserves opaque reasoning and enables automatic compaction), Argon is also notable for its high scores using the standard harness (which enables the model to carry forward notes between turns).
However, we encountered API issues that prevented us from completing testing with the standard harness:
- Low reasoning: 49.8%, with runs completed on 42 of 55 games - Medium reasoning: 46.3%, with runs completed on 46 of 55 games - High reasoning: Runs completed on only 19 of 55 games, so we did not publish a score
Reported scores include all 55 games, retaining partial credit earned on incomplete runs.
We used the current introductory pricing of $2 input / $10 output per million tokens to calculate the costs.