GPQA Diamond 87.4% alibabacloud.com for Qwen3-Max-Thinking on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported January 25, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3-Max-Thinking on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Vals AI harness Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 84.8% vals.ai for Qwen3-Max-Thinking 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 Qwen3-Max-Thinking on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness Humanity's Last Exam Full set — No tools Configuration: No tools 30.2% alibabacloud.com for Qwen3-Max-Thinking on Humanity's Last Exam Full set — No tools (opens in a new tab) Humanity's Last Exam Accuracy Reported January 25, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3-Max-Thinking on Humanity's Last Exam Full set — No tools Humanity's Last Exam Full set — With tools Configuration: With tools 49.8% alibabacloud.com for Qwen3-Max-Thinking on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported January 25, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3-Max-Thinking on Humanity's Last Exam Full set — With tools IFBench Original 70.9% alibabacloud.com for Qwen3-Max-Thinking on IFBench Original (opens in a new tab) Accuracy Reported January 25, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3-Max-Thinking on IFBench Original MMLU-Pro Original 85.7% alibabacloud.com for Qwen3-Max-Thinking on MMLU-Pro Original (opens in a new tab) Accuracy Reported January 25, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3-Max-Thinking on MMLU-Pro Original MMLU-Pro Original — Vals AI harness Configuration: Vals AI harness 85.0% vals.ai for Qwen3-Max-Thinking 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 Qwen3-Max-Thinking on MMLU-Pro Original — Vals AI harness SWE-bench Verified 75.3% alibabacloud.com for Qwen3-Max-Thinking on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported January 25, 2026 Launch post Alibaba Cloud Community Self-reported Qwen Team Record for Qwen3-Max-Thinking on SWE-bench Verified Terminal-Bench 2.0 — Vals AI Terminus 2 Configuration: Terminus-2 harness 20.2% vals.ai for Qwen3-Max-Thinking 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 Qwen3-Max-Thinking on Terminal-Bench 2.0 — Vals AI Terminus 2