# GPT 5.2: OpenAI Strikes Back Source: https://www.youtube.com/watch?v=4p73Uu_jZ10 Recap page: https://rapidrecap.app/video/4p73Uu_jZ10 Generated: 2025-12-12T17:10:21.586+00:00 --- ## Quick Overview GPT-5.2 Thinking sets a new state-of-the-art across multiple benchmarks, notably outperforming Gemini 1.5 Pro on GPAQ Diamond (92.4% vs 91.9%) and achieving 100% on AIME 2025 (No tools), while showing significant gains in long-context reasoning (near 100% accuracy on 256k tokens in the MRCRv2 test) and coding accuracy on SWE-Bench Pro (55.6% vs 53% for GPT-5.1 Codex-max). **Key Points:** - GPT-5.2 Thinking achieves a 100.0% score on the AIME 2025 (No tools) benchmark, surpassing Gemini 3 Pro's 95.0%. - On GPQA Diamond (No tools), GPT-5.2 Thinking scores 92.4%, slightly ahead of Gemini 3 Pro's 91.9%. - GPT-5.2 Thinking achieves 80.0% on SWE-bench Verified, compared to Gemini 3 Pro's 76.2%. - In long-context reasoning (MRCRv2, 4 needles), GPT-5.2 Thinking achieves near 100% accuracy at 256k tokens, while GPT-5.1 Thinking drops significantly. - On MLE-Bench-30 (no browsing), GPT-5.2 achieves 55% pass@1, beating GPT-5.1 Codex-max's 53%. - OpenAI is pricing GPT-5.2 models competitively, with GPT-5.2 Thinking priced at $1.75/1M input tokens and $14/1M output tokens, which is still cheaper than the Opus tier despite higher quality. - The developers are focusing on building superintelligence within the next ten years, as stated by Sam Altman (15:09). ![Screenshot at 00:04: The introduction slide clearly displays the focus of the announcement: "Introducing GPT-5.2," positioning it as the most advanced frontier model for professional work.](https://ss.rapidrecap.app/screens/4p73Uu_jZ10/00-00-04.png) **Context:** This video discusses the announcement and initial performance metrics of OpenAI's new frontier model, GPT-5.2, contrasting its capabilities against competitors like Gemini 3 Pro, Claude Opus, and previous GPT versions. The analysis covers performance across academic benchmarks (like GPQA, AIME, ARC-AGI-1), real-world software engineering tasks (SWE-Bench), long-context understanding (MRCRv2), and pricing/availability. ## Detailed Analysis The video introduces GPT-5.2 as OpenAI's latest frontier model, highlighting its record-breaking results across numerous benchmarks. On the GPT-4 vs. GPT-5.2 Thinking comparison table (08:08), GPT-5.2 excels in many areas, including scoring 100% on AIME 2025 (No tools) compared to Gemini 3 Pro's 95.0%, and achieving 92.4% on GPQA Diamond (No tools) against Gemini 3 Pro's 91.9%. The model also shows significant improvement in coding tasks, scoring 80.0% on SWE-bench Verified versus 76.2% for Gemini 3 Pro (08:00). A key advancement is in long-context reasoning, where GPT-5.2 Thinking maintains near 100% accuracy even with 256k tokens on the MRCRv2 test, significantly outperforming GPT-5.1 Thinking (13:09). Furthermore, on the MLE-Bench-30 (no browsing) chart (14:01), GPT-5.2 achieves 55% pass@1, beating GPT-5.1 Codex-max's 53%. The speaker notes that while some benchmarks show close competition, GPT-5.2 appears superior in complex reasoning (15:51). Regarding pricing, GPT-5.2 Thinking is priced at $1.75/1M input tokens and $14/1M output tokens, which is noted as being cheaper than Claude Opus 4.5 for similar quality (15:34). The video concludes with a quote from Sam Altman expressing high certainty that superintelligence will be built within ten years (15:09). ### Benchmark Performance Comparison - GPT-5.2 Thinking surpasses Gemini 3 Pro on GPQA Diamond (92.4% vs 91.9%), achieves 100% on AIME 2025 (No tools), and scores 80.0% on SWE-bench Verified (vs 76.2%). - GPT-5.2 Thinking significantly outperforms GPT-5.1 Thinking on ARC-AGI-1 (Verified) (52.9% vs 31.1%). ### Coding Performance (MLE-Bench-30, no browsing) - GPT-5.2 achieves 55% pass@1, beating GPT-5.1 Codex-Max's 53% and GPT-5's 45%. ### Long Context Reasoning (MRCRv2, 4 needles) - GPT-5.2 Thinking maintains nearly 100% accuracy across the entire context window up to 256k tokens, where GPT-5.1 Thinking performance degrades. ### Economic Comparison - GPT-5.2 Thinking is priced at $1.75/1M input tokens and $14/1M output tokens, noted as cheaper than Opus 4.5 for comparable quality due to efficiency gains (15:34). ### Human vs. AI Benchmarks (GPQd) - GPT-5.2 Thinking beats or ties top industry professionals on 70.9% of comparisons, setting a new state-of-the-art score (01:15). ### Future Outlook - Sam Altman is quoted expressing certainty that superintelligence will be built within ten more years (15:09). ![Screenshot at 00:04: The introduction slide clearly displays the focus of the announcement: "Introducing GPT-5.2," positioning it as the most advanced frontier model for professional work.](https://ss.rapidrecap.app/screens/4p73Uu_jZ10/00-00-04.png) ![Screenshot at 00:18: A comparison table showing GPT-5.2 Thinking outperforming Gemini 3 Pro across several key benchmarks like GPQA Diamond and AIME 2025.](https://ss.rapidrecap.app/screens/4p73Uu_jZ10/00-00-18.png) ![Screenshot at 00:55: A bar chart illustrating GPT-5.2 Thinking's success on economically valuable tasks, beating or tying industry professionals on 70.9% of comparisons.](https://ss.rapidrecap.app/screens/4p73Uu_jZ10/00-00-55.png) ![Screenshot at 04:41: The ARC-AGI-1 Leaderboard chart visually comparing model performance \(Score vs. Cost per Task\), where GPT-5.2 models show significant efficiency improvements over previous iterations.](https://ss.rapidrecap.app/screens/4p73Uu_jZ10/00-04-41.png) ![Screenshot at 13:03: A graph comparing GPT-5.2 Thinking against GPT-5.1 Thinking on the MRCRv2 long-context task, showing GPT-5.2 maintaining high accuracy across 256k tokens.](https://ss.rapidrecap.app/screens/4p73Uu_jZ10/00-13-03.png)