BrowseComp Effort: xHigh Reported as: pro xhigh 77.9% openai.com for GPT-5.2 (pro xhigh) on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on BrowseComp BrowseComp BrowseComp Effort: xHigh 65.8% openai.com for GPT-5.2 (xhigh) on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on BrowseComp BrowseComp CharXiv Reasoning — No tools Effort: xHigh Configuration: No tools 82.1% openai.com for GPT-5.2 (xhigh) on CharXiv Reasoning — No tools (opens in a new tab) CharXiv Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on CharXiv Reasoning — No tools CharXiv Reasoning — Python enabled Effort: xHigh Configuration: With Python 88.7% openai.com for GPT-5.2 (xhigh) on CharXiv Reasoning — Python enabled (opens in a new tab) CharXiv Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on CharXiv Reasoning — Python enabled GDPval Effort: xHigh Reported as: pro xhigh 74.1% openai.com for GPT-5.2 (pro xhigh) on GDPval GDPval (opens in a new tab) Wins or ties Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on GDPval GDPval GDPval Reported as: heavy 70.9% openai.com for GPT-5.2 (heavy) on GDPval GDPval (opens in a new tab) Wins or ties Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on GDPval GDPval GPQA Diamond Effort: xHigh Reported as: pro xhigh 93.2% openai.com for GPT-5.2 (pro xhigh) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond Effort: xHigh 92.4% openai.com for GPT-5.2 (xhigh) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Effort: None Configuration: Epoch AI harness 73.2% epoch.ai for GPT-5.2 (none) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported October 7, 2026 Evaluated July 13, 2026 at 5:28 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Low Configuration: Epoch AI harness 82.7% epoch.ai for GPT-5.2 (low) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported October 7, 2026 Evaluated December 11, 2025 at 8:25 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Medium Configuration: Epoch AI harness 87.9% epoch.ai for GPT-5.2 (medium) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported October 7, 2026 Evaluated December 11, 2025 at 8:49 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: High Configuration: Epoch AI harness 88.2% epoch.ai for GPT-5.2 (high) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported October 7, 2026 Evaluated December 11, 2025 at 8:49 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: xHigh Configuration: Epoch AI harness 91.4% epoch.ai for GPT-5.2 (xhigh) on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported October 7, 2026 Evaluated December 13, 2025 at 9:04 AM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Vals AI harness Effort: xHigh Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 91.7% vals.ai for GPT-5.2 (xhigh) on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.2 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness Humanity's Last Exam Full set — Scale AI evaluation 27.8% labs.scale.com for GPT-5.2 on Humanity's Last Exam Full set — Scale AI evaluation (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 3, 2026 Benchmark leaderboard Scale AI Independent Record for GPT-5.2 on Humanity's Last Exam Full set — Scale AI evaluation Humanity's Last Exam No tools — GPT-5.2 evaluation Effort: xHigh Reported as: pro xhigh Configuration: No tools 36.6% openai.com for GPT-5.2 (pro xhigh) on Humanity's Last Exam No tools — GPT-5.2 evaluation (opens in a new tab) Humanity's Last Exam Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on Humanity's Last Exam No tools — GPT-5.2 evaluation Humanity's Last Exam No tools — GPT-5.2 evaluation Effort: xHigh Configuration: No tools 34.5% openai.com for GPT-5.2 (xhigh) on Humanity's Last Exam No tools — GPT-5.2 evaluation (opens in a new tab) Humanity's Last Exam Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on Humanity's Last Exam No tools — GPT-5.2 evaluation Humanity's Last Exam Search and Python — GPT-5.2 evaluation Effort: xHigh Configuration: Search and Python 45.5% openai.com for GPT-5.2 (xhigh) on Humanity's Last Exam Search and Python — GPT-5.2 evaluation (opens in a new tab) Humanity's Last Exam Accuracy Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on Humanity's Last Exam Search and Python — GPT-5.2 evaluation Humanity's Last Exam Text only — Scale AI evaluation 28.5% labs.scale.com for GPT-5.2 on Humanity's Last Exam Text only — Scale AI evaluation (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for GPT-5.2 on Humanity's Last Exam Text only — Scale AI evaluation MCP Atlas Public, April 2026 update Effort: xHigh 67.6% labs.scale.com for GPT-5.2 (xhigh) on MCP Atlas Public, April 2026 update (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported September 21, 2026 Benchmark leaderboard Scale AI Independent Record for GPT-5.2 on MCP Atlas Public, April 2026 update MMLU-Pro Original — Vals AI harness Effort: xHigh Configuration: Vals AI harness 86.2% vals.ai for GPT-5.2 (xhigh) on MMLU-Pro Original — Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.2 on MMLU-Pro Original — Vals AI harness MMMU-Pro No tools Effort: xHigh Configuration: No tools 79.5% openai.com for GPT-5.2 (xhigh) on MMMU-Pro No tools (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on MMMU-Pro No tools MMMU-Pro Vals AI harness Effort: xHigh Configuration: Vals AI harness 86.7% vals.ai for GPT-5.2 (xhigh) on MMMU-Pro Vals AI harness (opens in a new tab) Archived copy (opens in a new tab) MMMU-Pro accuracy Setting: Standard (4 options) Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.2 on MMMU-Pro Vals AI harness MMMU-Pro With Python Effort: xHigh Configuration: With Python 80.4% openai.com for GPT-5.2 (xhigh) on MMMU-Pro With Python (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on MMMU-Pro With Python MRCR v2 8 needles 128K–256K — GPT-5.2 evaluation Effort: xHigh 77.0% openai.com for GPT-5.2 (xhigh) on MRCR v2 8 needles 128K–256K — GPT-5.2 evaluation (opens in a new tab) Mean sequence-matcher ratio Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on MRCR v2 8 needles 128K–256K — GPT-5.2 evaluation Riemann-bench October 2026 leaderboard Effort: xHigh 37.6% surgehq.ai for GPT-5.2 (xHigh) on Riemann-bench October 2026 leaderboard (opens in a new tab) Archived copy (opens in a new tab) Riemann-bench Pass@1 Reported October 7, 2026 Benchmark leaderboard Surge AI Independent Record for GPT-5.2 on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: Low Configuration: Epoch AI harness 32.8% epoch.ai for GPT-5.2 (low) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Evaluated August 27, 2026 at 7:29 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on SimpleQA Verified Original — Epoch AI harness SimpleQA Verified Original — Epoch AI harness Effort: Medium Configuration: Epoch AI harness 32.7% epoch.ai for GPT-5.2 (medium) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Evaluated August 27, 2026 at 7:29 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on SimpleQA Verified Original — Epoch AI harness SimpleQA Verified Original — Epoch AI harness Effort: High Configuration: Epoch AI harness 34.3% epoch.ai for GPT-5.2 (high) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Evaluated August 27, 2026 at 7:28 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on SimpleQA Verified Original — Epoch AI harness SimpleQA Verified Original — Epoch AI harness Effort: xHigh Configuration: Epoch AI harness 37.1% epoch.ai for GPT-5.2 (xhigh) on SimpleQA Verified Original — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Evaluated August 27, 2026 at 7:27 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on SimpleQA Verified Original — Epoch AI harness SWE-bench Multilingual — mini-swe-agent Effort: High Configuration: mini-swe-agent harness 66.7% github.com for GPT-5.2 (high) on SWE-bench Multilingual — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 13, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5.2 on SWE-bench Multilingual — mini-swe-agent SWE-bench Verified Effort: xHigh 80.0% openai.com for GPT-5.2 (xhigh) on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on SWE-bench Verified SWE-bench Verified — Epoch AI harness Effort: High Configuration: Epoch AI harness 73.8% epoch.ai for GPT-5.2 (high) on SWE-bench Verified — Epoch AI harness (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Evaluated February 12, 2026 at 1:34 PM UTC Benchmark leaderboard Epoch AI Independent Record for GPT-5.2 on SWE-bench Verified — Epoch AI harness SWE-bench Verified — mini-swe-agent Effort: High Configuration: mini-swe-agent harness 72.8% github.com for GPT-5.2 (high) on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported February 17, 2026 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5.2 on SWE-bench Verified — mini-swe-agent SWE-bench Verified — mini-swe-agent Configuration: mini-swe-agent harness 69.0% github.com for GPT-5.2 on SWE-bench Verified — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported December 11, 2025 Benchmark repository SWE-bench Independent SWE-bench Team Record for GPT-5.2 on SWE-bench Verified — mini-swe-agent SWE-bench Verified — Vals AI mini-swe-agent Effort: xHigh Configuration: mini-swe-agent harness 75.8% vals.ai for GPT-5.2 (xhigh) on SWE-bench Verified — Vals AI mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported September 1, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.2 on SWE-bench Verified — Vals AI mini-swe-agent SWE-bench Pro Private — Scale AI SWE-Agent Configuration: SWE-Agent harness, 250 turns, uncapped cost 23.8% labs.scale.com for GPT-5.2 on SWE-bench Pro Private — Scale AI SWE-Agent (opens in a new tab) Archived copy (opens in a new tab) Public tasks resolved Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for GPT-5.2 on SWE-bench Pro Private — Scale AI SWE-Agent SWE-bench Pro Public Effort: xHigh 55.6% openai.com for GPT-5.2 (xhigh) on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on SWE-bench Pro Public SWE-bench Pro Public — Scale AI SWE-Agent Configuration: SWE-Agent harness, 250 turns, uncapped cost 29.9% labs.scale.com for GPT-5.2 on SWE-bench Pro Public — Scale AI SWE-Agent (opens in a new tab) Archived copy (opens in a new tab) Public tasks resolved Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for GPT-5.2 on SWE-bench Pro Public — Scale AI SWE-Agent Terminal-Bench 2.0 — Vals AI Terminus 2 Effort: High Configuration: Terminus-2 harness 51.7% vals.ai for GPT-5.2 (high) on Terminal-Bench 2.0 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported June 4, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.2 on Terminal-Bench 2.0 — Vals AI Terminus 2 Toolathlon Original Effort: High 41.7% toolathlon.xyz for GPT-5.2 (high) on Toolathlon Original (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported December 17, 2025 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for GPT-5.2 on Toolathlon Original Toolathlon Original Effort: xHigh 46.3% openai.com for GPT-5.2 (xhigh) on Toolathlon Original (opens in a new tab) Tasks completed Reported December 11, 2025 Launch post OpenAI Self-reported Record for GPT-5.2 on Toolathlon Original Toolathlon Original Effort: xHigh 43.8% toolathlon.xyz for GPT-5.2 (xhigh) on Toolathlon Original (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported December 18, 2025 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for GPT-5.2 on Toolathlon Original Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: xHigh Configuration: OpenHands harness 53.5% vals.ai for GPT-5.2 (xhigh) on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Vibe Code Bench Score Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GPT-5.2 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation τ³-bench τ³ — Airline Effort: None 52.5% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GPT-5.2 (none) on τ³-bench τ³ — Airline (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 26, 2026 Evaluated May 26, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GPT-5.2 on τ³-bench τ³ — Airline τ³-bench τ³ — Airline Effort: High 83.0% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GPT-5.2 (high) on τ³-bench τ³ — Airline (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 5, 2026 Evaluated May 5, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GPT-5.2 on τ³-bench τ³ — Airline τ³-bench τ³ — Banking, AllTools retrieval, v1.0.1 grading Effort: High Configuration: AllTools retrieval 32.2% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GPT-5.2 (high) on τ³-bench τ³ — Banking, AllTools retrieval, v1.0.1 grading (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 5, 2026 Evaluated May 5, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GPT-5.2 on τ³-bench τ³ — Banking, AllTools retrieval, v1.0.1 grading τ³-bench τ³ — Banking, Qwen embeddings retrieval, v1.0.1 grading Effort: None Configuration: Qwen embeddings retrieval 12.6% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GPT-5.2 (none) on τ³-bench τ³ — Banking, Qwen embeddings retrieval, v1.0.1 grading (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 26, 2026 Evaluated May 26, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GPT-5.2 on τ³-bench τ³ — Banking, Qwen embeddings retrieval, v1.0.1 grading τ³-bench τ³ — Retail Effort: None 75.0% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GPT-5.2 (none) on τ³-bench τ³ — Retail (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 26, 2026 Evaluated May 26, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GPT-5.2 on τ³-bench τ³ — Retail τ³-bench τ³ — Retail Effort: High 81.6% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GPT-5.2 (high) on τ³-bench τ³ — Retail (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported May 5, 2026 Evaluated May 5, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GPT-5.2 on τ³-bench τ³ — Retail