APEX-Agents Original Effort: Max 45.2% mercor.com for GLM-5.2 (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-5.2 on APEX-Agents Original AutomationBench 1.0.6 Effort: Max 26.2% github.com for GLM-5.2 (max) on AutomationBench 1.0.6 (opens in a new tab) Task pass rate Reported September 24, 2026 Benchmark repository Zapier Independent Zapier AutomationBench Team Record for GLM-5.2 on AutomationBench 1.0.6 BrowseComp 130-question subset — Mercor web research agent Effort: Max Configuration: Mercor web research agent, 100 steps, 3 hours 65.4% mercor.com for GLM-5.2 (max) on BrowseComp 130-question subset — Mercor web research agent (opens in a new tab) Archived copy (opens in a new tab) BrowseComp Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.2 on BrowseComp 130-question subset — Mercor web research agent CyberGym Original 77.2% z.ai for GLM-5.2 on CyberGym Original (opens in a new tab) Vulnerability reproduction success Reported June 16, 2026 Launch post Z.ai Self-reported Record for GLM-5.2 on CyberGym Original DeepSWE 1.1 Effort: Max 44.0% deepswe.datacurve.ai for GLM-5.2 (max) on DeepSWE 1.1 (opens in a new tab) DeepSWE Pass@1 Reported September 22, 2026 Benchmark leaderboard Datacurve Independent Record for GLM-5.2 on DeepSWE 1.1 DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Effort: Max Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 38.9% mercor.com for GLM-5.2 (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-5.2 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Finance Agent Benchmark 2 — October 2026 evaluation 49.7% vals.ai for GLM-5.2 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-5.2 on Finance Agent Benchmark 2 — October 2026 evaluation GPQA Diamond 91.2% z.ai for GLM-5.2 on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported June 16, 2026 Launch post Z.ai Self-reported Record for GLM-5.2 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Effort: None Configuration: Epoch AI harness 71.2% epoch.ai for GLM-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 August 10, 2026 at 5:45 PM UTC Benchmark leaderboard Epoch AI Independent Record for GLM-5.2 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Low Configuration: Epoch AI harness 87.9% epoch.ai for GLM-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 August 10, 2026 at 5:45 PM UTC Benchmark leaderboard Epoch AI Independent Record for GLM-5.2 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Epoch AI harness Effort: Max Configuration: Epoch AI harness 91.9% epoch.ai for GLM-5.2 (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 June 24, 2026 at 8:55 PM UTC Benchmark leaderboard Epoch AI Independent Record for GLM-5.2 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 90.2% mercor.com for GLM-5.2 (max) on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot (opens in a new tab) Archived copy (opens in a new tab) GPQA Diamond Accuracy Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.2 on Graduate-Level Google-Proof Q&A Diamond — Mercor single-shot GPQA Diamond — Vals AI harness Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 85.6% vals.ai for GLM-5.2 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-5.2 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness HLAB October 2026 evaluation Effort: Max 7.1% vals.ai for GLM-5.2 (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-5.2 on Harvey's Legal Agent Benchmark October 2026 evaluation Humanity's Last Exam Text only — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 31.7% mercor.com for GLM-5.2 (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-5.2 on Humanity's Last Exam Text only — Mercor single-shot MCP Atlas Public, April 2026 update 77.8% labs.scale.com for GLM-5.2 on MCP Atlas Public, April 2026 update (opens in a new tab) Pass rate Reported September 24, 2026 Benchmark leaderboard Scale AI Independent Record for GLM-5.2 on MCP Atlas Public, April 2026 update MMLU-Pro Original — Mercor single-shot Effort: Max Configuration: Mercor single-shot agent 85.9% mercor.com for GLM-5.2 (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-5.2 on MMLU-Pro Original — Mercor single-shot MMLU-Pro Original — Vals AI harness Configuration: Vals AI harness 86.7% vals.ai for GLM-5.2 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-5.2 on MMLU-Pro Original — Vals AI harness NL2Repo Bench Original 48.9% z.ai for GLM-5.2 on NL2Repo Bench Original (opens in a new tab) Average test pass rate Reported June 16, 2026 Launch post Z.ai Self-reported Record for GLM-5.2 on NL2Repo Bench Original PostTrainBench 1.1 — Claude Code Effort: Max Configuration: Claude Code harness 31.7% posttrainbench.com for GLM-5.2 (Max) on PostTrainBench 1.1 — 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-5.2 on PostTrainBench 1.1 — Claude Code PostTrainBench 1.2 — Claude Code Effort: Max Configuration: Claude Code harness 30.4% posttrainbench.com for GLM-5.2 (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-5.2 on PostTrainBench 1.2 — Claude Code Riemann-bench October 2026 leaderboard Effort: Max 10.4% surgehq.ai for GLM-5.2 (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-5.2 on Riemann-bench October 2026 leaderboard SimpleQA Verified Original — Epoch AI harness Effort: Max Configuration: Epoch AI harness 34.2% epoch.ai for GLM-5.2 (max) 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 7:36 PM UTC Benchmark leaderboard Epoch AI Independent Record for GLM-5.2 on SimpleQA Verified Original — Epoch AI harness SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps Effort: Max Configuration: Mercor mini-swe-agent, 250 steps, 1 hour 46.0% mercor.com for GLM-5.2 (max) on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Mercor Independent Record for GLM-5.2 on SWE Atlas Codebase QnA — Mercor mini-swe-agent, 250 steps SWE Atlas Codebase QnA — Public; mini-swe-agent Configuration: mini-swe-agent harness 48.1% labs.scale.com for GLM-5.2 on SWE Atlas Codebase QnA — Public; mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for GLM-5.2 on SWE Atlas Codebase QnA — Public; mini-swe-agent SWE Atlas Refactoring — mini-swe-agent Configuration: mini-swe-agent harness 42.4% labs.scale.com for GLM-5.2 on SWE Atlas Refactoring — mini-swe-agent (opens in a new tab) Archived copy (opens in a new tab) Mean pass@1 Reported October 7, 2026 Benchmark leaderboard Scale AI Independent Record for GLM-5.2 on SWE Atlas Refactoring — mini-swe-agent SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 78.6% mercor.com for GLM-5.2 (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-5.2 on SWE-bench Multilingual — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Epoch AI harness Effort: Max Configuration: Epoch AI harness 78.7% epoch.ai for GLM-5.2 (max) 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 June 25, 2026 at 1:13 PM UTC Benchmark leaderboard Epoch AI Independent Record for GLM-5.2 on SWE-bench Verified — Epoch AI harness SWE-bench Verified — Mercor mini-swe-agent, 1000 steps Effort: Max Configuration: Mercor mini-swe-agent, 1000 steps, 3 hours 78.5% mercor.com for GLM-5.2 (max) on SWE-bench Verified — 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-5.2 on SWE-bench Verified — Mercor mini-swe-agent, 1000 steps SWE-bench Verified — Vals AI mini-swe-agent Effort: Max Configuration: mini-swe-agent harness 82.8% vals.ai for GLM-5.2 (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-5.2 on SWE-bench Verified — Vals AI mini-swe-agent SWE-bench Pro Public 62.1% z.ai for GLM-5.2 on SWE-bench Pro Public (opens in a new tab) Public tasks resolved Reported June 16, 2026 Launch post Z.ai Self-reported Record for GLM-5.2 on SWE-bench Pro Public Terminal-Bench 2.1 — Terminus-2 Configuration: Terminus-2 harness 81.0% z.ai for GLM-5.2 on Terminal-Bench 2.1 — Terminus-2 (opens in a new tab) Terminal-Bench Accuracy Reported June 16, 2026 Launch post Z.ai Self-reported Record for GLM-5.2 on Terminal-Bench 2.1 — Terminus-2 Terminal-Bench 2.1 — Vals AI Terminus 2 Effort: Max Configuration: Terminus-2 harness 67.8% vals.ai for GLM-5.2 (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-5.2 on Terminal-Bench 2.1 — Vals AI Terminus 2 Toolathlon Verified Effort: Max 59.9% toolathlon.xyz for GLM-5.2 (max) on Toolathlon Verified (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported June 30, 2026 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for GLM-5.2 on Toolathlon Verified Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Effort: Max Configuration: OpenHands harness 64.0% vals.ai for GLM-5.2 (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-5.2 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation τ³-bench τ³ — Banking, AllTools retrieval, v1.0.1 grading Effort: xHigh Configuration: AllTools retrieval 37.1% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GLM-5.2 (xhigh) 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 August 4, 2026 Evaluated July 24, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GLM-5.2 on τ³-bench τ³ — Banking, AllTools retrieval, v1.0.1 grading