OpenAI 的 GPT-5.6 Sol 基准测试声明因自定义测试环境而受到质疑

报道来源 [4]

1. The Decoder TIER_1 English(EN) · Matthias Bastian · 2026-07-30 09:03

   OpenAI 声称 GPT-5.6 Sol 在 ARC-AGI-3 上击败 Opus 5，凭借其最新 API 和两个额外设置

   <p><img alt="" class="attachment-full size-full wp-post-image" height="768" src="https://the-decoder.com/wp-content/uploads/2026/06/openai_gpt56_sol.png" style="height: auto; margin-bottom: 10px;" width="1376" /></p> <p> OpenAI counters Anthropic's ARC-AGI-3 record: GPT-5.6 Sol s…

2. The Decoder TIER_1 English(EN) · Matthias Bastian · 2026-07-30 07:40

   OpenAI声称GPT-5.6 Sol在ARC-AGI-3上击败Opus 5，但仅在其自有的定制测试框架下

   <p><img alt="" class="attachment-full size-full wp-post-image" height="768" src="https://the-decoder.com/wp-content/uploads/2026/06/openai_gpt56_sol.png" style="height: auto; margin-bottom: 10px;" width="1376" /></p> <p> OpenAI counters Anthropic's ARC-AGI-3 record: GPT-5.6 Sol s…

3. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-07-30 10:50

   OpenAI 表示 GPT-5.6 Sol 在 ARC-AGI-3 上击败 Opus 5，但仅限于使用其自有 API 功能。若无这些功能，得分降至 7.8%。公平基准测试仍是一项挑战

   OpenAI says GPT-5.6 Sol beats Opus 5 on ARC-AGI-3, but only with its own API features. Without them, the score drops to 7.8%. Fair benchmarking remains a challenge. Source: The Decoder AI https:// the-decoder.com/openai-claims- gpt-5-6-sol-beats-opus-5-on-arc-agi-3-with-its-lates…

   链接 the-decoder.com/openai-claims-gpt-5-6-sol…
4. Mastodon — mastodon.social TIER_1 English(EN) · sipirtu · 2026-07-30 08:50

   OpenAI 表示 GPT-5.6 Sol 在 ARC-AGI-3 上通过自定义工具超越 Opus 5，但在官方测试中得分 7.8%。Opus 5 在没有特殊优化的情况下达到了 30.2%。

   OpenAI says GPT-5.6 Sol tops Opus 5 on ARC-AGI-3 with a custom harness but scores 7.8 percent in the official test. Opus 5 reached 30.2 percent without special setups. Source: The Decoder AI https:// the-decoder.com/openai-claims- gpt-5-6-sol-beats-opus-5-on-arc-agi-3-but-only-wi…

   链接 the-decoder.com/openai-claims-gpt-5-6-sol…