BrowseComp Reported as: thinking 62.0% z.ai for GLM-5 (thinking) on BrowseComp BrowseComp (opens in a new tab) BrowseComp Accuracy Reported February 12, 2026 Launch post Z.ai Self-reported Record for GLM-5 on BrowseComp BrowseComp CyberGym Original Reported as: thinking 43.2% z.ai for GLM-5 (thinking) on CyberGym Original (opens in a new tab) Vulnerability reproduction success Reported February 12, 2026 Launch post Z.ai Self-reported Record for GLM-5 on CyberGym Original DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps Configuration: Mercor mini-swe-agent, 500 steps, 2 hours 2.1% mercor.com for GLM-5 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 on DeepSWE 1.1 — Mercor mini-swe-agent, 500 steps GPQA Diamond Reported as: thinking 86.0% z.ai for GLM-5 (thinking) on Graduate-Level Google-Proof Q&A Diamond (opens in a new tab) GPQA Diamond Accuracy Reported February 12, 2026 Launch post Z.ai Self-reported Record for GLM-5 on Graduate-Level Google-Proof Q&A Diamond GPQA Diamond — Epoch AI harness Configuration: Epoch AI harness 87.8% epoch.ai for GLM-5 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 February 12, 2026 at 5:19 PM UTC Benchmark leaderboard Epoch AI Independent Record for GLM-5 on Graduate-Level Google-Proof Q&A Diamond — Epoch AI harness GPQA Diamond — Vals AI harness Reported as: thinking Configuration: Vals AI harness: mean of zero-shot and few-shot CoT 83.3% vals.ai for GLM-5 (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 GLM-5 on Graduate-Level Google-Proof Q&A Diamond — Vals AI harness MMLU-Pro Original — Vals AI harness Reported as: thinking Configuration: Vals AI harness 86.0% vals.ai for GLM-5 (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 GLM-5 on MMLU-Pro Original — Vals AI harness SWE Atlas Codebase QnA — Public; mini-swe-agent Configuration: mini-swe-agent harness 20.5% labs.scale.com for GLM-5 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 on SWE Atlas Codebase QnA — Public; mini-swe-agent SWE Atlas Refactoring — mini-swe-agent Configuration: mini-swe-agent harness 24.2% labs.scale.com for GLM-5 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 on SWE Atlas Refactoring — mini-swe-agent SWE-bench Multilingual Reported as: thinking 73.3% z.ai for GLM-5 (thinking) on SWE-bench Multilingual (opens in a new tab) Resolved Tasks Reported February 12, 2026 Launch post Z.ai Self-reported Record for GLM-5 on SWE-bench Multilingual SWE-bench Multilingual — mini-swe-agent Configuration: mini-swe-agent harness 69.7% github.com for GLM-5 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 GLM-5 on SWE-bench Multilingual — mini-swe-agent SWE-bench Verified Reported as: thinking 77.8% z.ai for GLM-5 (thinking) on SWE-bench Verified (opens in a new tab) Resolved Tasks Reported February 12, 2026 Launch post Z.ai Self-reported Record for GLM-5 on SWE-bench Verified SWE-bench Verified — Epoch AI harness Configuration: Epoch AI harness 72.1% epoch.ai for GLM-5 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 15, 2026 at 3:40 PM UTC Benchmark leaderboard Epoch AI Independent Record for GLM-5 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 GLM-5 (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 GLM-5 on SWE-bench Verified — mini-swe-agent SWE-bench Verified — Vals AI mini-swe-agent Reported as: thinking Configuration: mini-swe-agent harness 71.4% vals.ai for GLM-5 (thinking) 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 on SWE-bench Verified — Vals AI mini-swe-agent Terminal-Bench 2.0 — Vals AI Terminus 2 Reported as: thinking Configuration: Terminus-2 harness 49.4% vals.ai for GLM-5 (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 GLM-5 on Terminal-Bench 2.0 — Vals AI Terminus 2 Toolathlon Original 39.2% toolathlon.xyz for GLM-5 on Toolathlon Original (opens in a new tab) Archived copy (opens in a new tab) Tasks completed Reported February 13, 2026 Benchmark leaderboard Toolathlon Independent Toolathlon Authors Record for GLM-5 on Toolathlon Original Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation Reported as: thinking Configuration: OpenHands harness 23.4% vals.ai for GLM-5 (thinking) 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 on Vibe Code Bench 1.1 — OpenHands, October 2026 evaluation τ³-bench τ³ — Airline Reported as: enabled 82.5% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GLM-5 (enabled) on τ³-bench τ³ — Airline (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported March 2, 2026 Evaluated February 27, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GLM-5 on τ³-bench τ³ — Airline τ³-bench τ³ — Banking, text-embedding-3-large retrieval, v1.0.1 grading Reported as: enabled Configuration: text-embedding-3-large retrieval 9.8% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GLM-5 (enabled) on τ³-bench τ³ — Banking, text-embedding-3-large retrieval, v1.0.1 grading (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported March 2, 2026 Evaluated February 27, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GLM-5 on τ³-bench τ³ — Banking, text-embedding-3-large retrieval, v1.0.1 grading τ³-bench τ³ — Retail Reported as: enabled 73.7% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GLM-5 (enabled) on τ³-bench τ³ — Retail (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported March 2, 2026 Evaluated February 27, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GLM-5 on τ³-bench τ³ — Retail τ³-bench τ³ — Telecom Reported as: enabled 86.8% sierra-tau-bench-public.s3.us-west-2.amazonaws.com for GLM-5 (enabled) on τ³-bench τ³ — Telecom (opens in a new tab) Archived copy (opens in a new tab) Task success rate Reported March 2, 2026 Evaluated February 27, 2026 Benchmark leaderboard Sierra Independent Sierra Research Record for GLM-5 on τ³-bench τ³ — Telecom