APEX-Agents Original Effort: Max 52.8% mercor.com for GLM-5.3-Flash (max) on APEX-Agents Original (opens in a new tab) Archived copy (opens in a new tab) Pass rate Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on APEX-Agents Original AutomationBench 1.0.6 Effort: Max 48.8% autoclaw.z.ai for GLM-5.3-Flash (max) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 24, 2026 Launch post AutoClaw Team (Z.ai) Self-reported Z.ai Record for GLM-5.3-Flash on AutomationBench 1.0.6 Chartography October 2026 leaderboard Effort: Max 16.3% surgehq.ai for GLM-5.3-Flash (Max) on Chartography October 2026 leaderboard (opens in a new tab) Archived copy (opens in a new tab) Chartography Pass@1 Reported October 7, 2026 Benchmark leaderboard Surge AI Independent Record for GLM-5.3-Flash on Chartography October 2026 leaderboard CharXiv Descriptive and reasoning — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 92.5% mercor.com for GLM-5.3-Flash (max) on CharXiv Descriptive and reasoning — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) CharXiv Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on CharXiv Descriptive and reasoning — Mercor single-shot CursorBench 4.0 Effort: Low 26.9% cursor.com for GLM-5.3-Flash (low) on CursorBench 4.0 (opens in a new tab) Archived copy (opens in a new tab) CursorBench Accuracy Reported October 7, 2026 Benchmark leaderboard Cursor Independent Record for GLM-5.3-Flash on CursorBench 4.0 CursorBench 4.0 Effort: High 31.1% cursor.com for GLM-5.3-Flash (high) on CursorBench 4.0 (opens in a new tab) Archived copy (opens in a new tab) CursorBench Accuracy Reported October 7, 2026 Benchmark leaderboard Cursor Independent Record for GLM-5.3-Flash on CursorBench 4.0 CursorBench 4.0 Effort: Max 36.8% cursor.com for GLM-5.3-Flash (max) on CursorBench 4.0 (opens in a new tab) Archived copy (opens in a new tab) CursorBench Accuracy Reported October 7, 2026 Benchmark leaderboard Cursor Independent Record for GLM-5.3-Flash on CursorBench 4.0 DeepSWE 1.1 Effort: Max 63.0% deepswe.datacurve.ai for GLM-5.3-Flash (max) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Benchmark leaderboard Datacurve Independent Record for GLM-5.3-Flash on DeepSWE 1.1 DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: Max Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 42.5% mercor.com for GLM-5.3-Flash (max) on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps (opens in a new tab) Archived copy (opens in a new tab) DeepSWE Pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation Effort: Max 57.9% vals.ai for GLM-5.3-Flash (max) on Finance Agent Benchmark 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) Finance Agent Accuracy Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5.3-Flash on Finance Agent Benchmark 2 — October 2026 evaluation FrontierSWE 2 — October 2026 evaluation Configuration: Proximus harness, 5 trials, 20-hour budget 18.1% frontierswe.com for GLM-5.3-Flash on FrontierSWE 2 — October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) FrontierSWE Score Reported October 7, 2026 Benchmark leaderboard Proximal Independent Record for GLM-5.3-Flash on FrontierSWE 2 — October 2026 evaluation GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 90.2% epoch.ai for GLM-5.3-Flash (max) 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 August 26, 2026 at 10:26 PM UTC Benchmark leaderboard Epoch AI Independent Record for GLM-5.3-Flash on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Vals AI harness Effort: Max Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 86.4% vals.ai for GLM-5.3-Flash (max) 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 GLM-5.3-Flash on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation Effort: Max 6.7% vals.ai for GLM-5.3-Flash (max) on Harvey's Legal Agent Benchmark October 2026 evaluation (opens in a new tab) Archived copy (opens in a new tab) HLAB Task Pass Rate Reported October 6, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5.3-Flash on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Full set — With tools Effort: Max Configuration: With tools 55.3% autoclaw.z.ai for GLM-5.3-Flash (max) on Humanity's Last Exam Full set — With tools (opens in a new tab) Humanity's Last Exam Accuracy Reported September 24, 2026 Launch post AutoClaw Team (Z.ai) Self-reported Z.ai Record for GLM-5.3-Flash on Humanity's Last Exam Full set — With tools Humanity's Last Exam Text only — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 33.6% mercor.com for GLM-5.3-Flash (max) on Humanity's Last Exam Text only — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Humanity's Last Exam Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on Humanity's Last Exam Text only — Mercor single-shot MedXpertQA MM — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 73.7% mercor.com for GLM-5.3-Flash (max) on MedXpertQA MM — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on MedXpertQA MM — Mercor single-shot MMLU-Pro Original — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 87.3% mercor.com for GLM-5.3-Flash (max) on MMLU-Pro Original — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on MMLU-Pro Original — Mercor single-shot MMLU-Pro Original — Vals AI harness Effort: Max Configuration: Vals AI harness 86.1% vals.ai for GLM-5.3-Flash (max) 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 GLM-5.3-Flash on MMLU-Pro Original — Vals AI harness MMMU-Pro 1,730 questions — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 78.4% mercor.com for GLM-5.3-Flash (max) on MMMU-Pro 1,730 questions — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) MMMU-Pro accuracy Setting: Not stated Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on MMMU-Pro 1,730 questions — Mercor single-shot MMMU-Pro Vals AI harness Effort: Max Configuration: Vals AI harness 86.0% vals.ai for GLM-5.3-Flash (max) 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 GLM-5.3-Flash on MMMU-Pro Vals AI harness NL2Repo Bench Original Effort: Max 56.3% autoclaw.z.ai for GLM-5.3-Flash (max) on NL2Repo Bench Original (opens in a new tab) Average test pass rate Reported September 24, 2026 Launch post AutoClaw Team (Z.ai) Self-reported Z.ai Record for GLM-5.3-Flash on NL2Repo Bench Original PostTrainBench 1.2 — Claude Code Effort: Max Configuration: Claude Code harness 36.8% posttrainbench.com for GLM-5.3-Flash (Max) on PostTrainBench 1.2 — Claude Code (opens in a new tab) Archived copy (opens in a new tab) PostTrainBench Weighted Aggregate Reported October 6, 2026 Benchmark leaderboard PostTrainBench Independent PostTrainBench Team Record for GLM-5.3-Flash on PostTrainBench 1.2 — Claude Code Riemann-bench October 2026 leaderboard Effort: Max 8.8% surgehq.ai for GLM-5.3-Flash (Max) 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 GLM-5.3-Flash on Riemann-bench October 2026 leaderboard SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 88.9% mercor.com for GLM-5.3-Flash (max) on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps (opens in a new tab) Archived copy (opens in a new tab) Resolved Tasks Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Vals AI mini-swe-agent Effort: Max Configuration: mini-swe-agent harness 92.0% vals.ai for GLM-5.3-Flash (max) 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 GLM-5.3-Flash on SWE-bench Verified — Vals AI mini-swe-agent Terminal-Bench 2.1 — Claude Code Effort: Max Configuration: Claude Code harness 84.3% autoclaw.z.ai for GLM-5.3-Flash (max) on Terminal-Bench 2.1 — Claude Code (opens in a new tab) Terminal-Bench Accuracy Reported September 24, 2026 Launch post AutoClaw Team (Z.ai) Self-reported Z.ai Record for GLM-5.3-Flash on Terminal-Bench 2.1 — Claude Code Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: Max Configuration: Terminus-2 harness 62.9% vals.ai for GLM-5.3-Flash (max) on Terminal-Bench 2.1 — Vals AI Terminus 2 (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported September 28, 2026 Benchmark leaderboard Vals AI Independent Record for GLM-5.3-Flash on Terminal-Bench 2.1 — Vals AI Terminus 2 Terminal-Bench 4.0 — Claude Code Effort: None Configuration: Claude Code harness 35.8% tbench.ai for GLM-5.3-Flash (none) on Terminal-Bench 4.0 — Claude Code (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported August 26, 2026 Benchmark leaderboard Terminal-Bench Independent Terminal-Bench Team Record for GLM-5.3-Flash on Terminal-Bench 4.0 — Claude Code Terminal-Bench 4.0 — Mercor mini-swe-agent Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 8 hours 29.8% mercor.com for GLM-5.3-Flash (max) on Terminal-Bench 4.0 — Mercor mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Terminal-Bench Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.3-Flash on Terminal-Bench 4.0 — Mercor mini-swe-agent Toolathlon Verified Effort: Max 78.4% autoclaw.z.ai for GLM-5.3-Flash (max) on Toolathlon Verified (opens in a new tab) Tasks completed Reported September 24, 2026 Launch post AutoClaw Team (Z.ai) Self-reported Z.ai Record for GLM-5.3-Flash on Toolathlon Verified Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: Max Configuration: OpenHands harness 30.8% vals.ai for GLM-5.3-Flash (max) 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 GLM-5.3-Flash on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation