GLM-5.3 ranks first on 2 of the 144 benchmarks it has scores on.
Open weights Flagship
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Creative Writing v3 | 82.2 | #2 of 120 | Official leaderboard | |
| Humanity's Last Exam | 62.5% | #9 of 147 | Model card | |
| LMArena (Elo) | 1,481 | #25 of 333 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 81.8 | #10 of 119 | Official leaderboard | |
| BullshitBench V2 | 72% | #19 of 122 | Official leaderboard | |
| BullshitBench | 50.9% | #28 of 107 | Official leaderboard | |
| Judgemark v4 | 72.6 | #12 of 40 | Official leaderboard | |
| AgentIF (2026-10 setting) | 64.2% | #9 of 24 | Official leaderboard | |
| Extended NYT Connections | 74.2% | #49 of 97 | Official leaderboard | |
| SimpleQA Verified | 41% | #49 of 84 | Epoch AI | |
| HLE-Diamond | 25.1% | #16 of 18 | Official leaderboard | |
| Continual Learning Exam | 24% | #10 of 10 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 90.9% | #36 of 219 | Epoch AI | |
| CritPt | 19.1% | #33 of 160 | Epoch AI | |
| SimpleBench | 66.2% | #24 of 100 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 91.1% | #59 of 202 | Epoch AI | |
| FrontierMath Tiers 1-3 v2 | 68.8% | #30 of 89 | Epoch AI | |
| DTBench | 79.5% | #61 of 178 | Official leaderboard | |
| Prophet Arena | 85.5 | #7 of 18 | Official leaderboard | |
| ProofBench | 49% | #34 of 83 | Epoch AI | |
| FrontierMath Tier 4 v2 | 29.3% | #37 of 71 | Epoch AI | |
| ProofBench v1.1 | 49% | #31 of 51 | Official leaderboard | |
| NatureBench | 10% | #11 of 18 | Official leaderboard | |
| MysteryMechanism | 23% | #19 of 29 | Official leaderboard | |
| PaperBenchX | 7.53% | #7 of 10 | Official leaderboard | |
| Terminal-Bench-Science | 8.10% | #12 of 17 | Official leaderboard | |
| FrontierPhysics | 1.20% | #14 of 19 | Official leaderboard | |
| LatchBio Capabilities v1.0 | 33.6% | #23 of 27 | Official leaderboard | |
| xbench-ScienceQA | 65.8% | #26 of 29 | Official leaderboard | |
| BTF-3 | 0.15 | #9 of 10 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WeirdML | 75.4% | #16 of 112 | Official leaderboard | |
| WebDev Arena | 1,614 | #17 of 105 | Epoch AI | |
| Code Arena | 1,623 | #24 of 124 | Official leaderboard | |
| NL2Repo-Bench | 58% | #6 of 28 | Model card | |
| DeepSWE | 69% | #7 of 28 | Official leaderboard | |
| ALE-Bench | 1,317 | #31 of 121 | Epoch AI | |
| Vibe Code Bench | 78.1% | #33 of 115 | Official leaderboard | |
| TasteVal | 59.2× | #6 of 20 | Official leaderboard | |
| Tencent WorkBuddy Bench | 77.4% | #3 of 10 | Official leaderboard | |
| Code Migration | 44.2% | #24 of 78 | Official leaderboard | |
| IOI v2 (Vals) | 68.4% | #14 of 45 | Official leaderboard | |
| Code Migration v1.1 | 55.1% | #11 of 29 | Official leaderboard | |
| RSI-Exam | 40.3% | #7 of 18 | Official leaderboard | |
| PostTrainBench | 39.8% | #3 of 7 | Model card | |
| PostTrainBench 1.2 | 34.5% | #8 of 17 | Official leaderboard | |
| FrontierSWE | 30.2% | #10 of 21 | Epoch AI | |
| Vibe Code Bench 1-100 | 20% | #13 of 26 | Official leaderboard | |
| FrontierCS 2 | 25% | #8 of 16 | Official leaderboard | |
| Vals RSI Index | 0.23 | #13 of 25 | Official leaderboard | |
| CursorBench | 42.6% | #10 of 19 | Epoch AI | |
| SWE-Marathon | 42.5% | #6 of 11 | Model card | |
| SWE-Bench Pro V2 | 95.6% | #9 of 16 | Official leaderboard | |
| SWE-Bench Pro V2 Hard | 84.3% | #9 of 16 | Official leaderboard | |
| FrontierCode | 40.1% | #26 of 46 | Epoch AI | |
| SWE-Marathon v1.1 | 42.5% | #11 of 17 | Official leaderboard | |
| FrontierCode 2.0 | 17.8% | #19 of 26 | Official leaderboard | |
| ViBench 2.0 | 0% | #7 of 9 | Official leaderboard | |
| RSI Bench | 32.3 | #7 of 8 | Official leaderboard | |
| Brokk Power Ranking | 2.80 | #17 of 19 | Official leaderboard | |
| ProgramBench | 19% | #19 of 20 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CivBench | 1,634 | #1 of 18 | Official leaderboard | |
| MCP Atlas | 84.2% | #5 of 34 | Official leaderboard | |
| Terminal-Bench 2.1 | 88.2% | #8 of 53 | Model card | |
| Toolathlon | 73% | #7 of 37 | Model card | |
| Long-Horizon-Terminal-Bench 2.0 | 54.2% | #4 of 15 | Official leaderboard | |
| AutomationBench | 48.2% | #12 of 41 | Model card | |
| LLM Chess | 605 | #37 of 124 | Official leaderboard | |
| Mystery Game Puzzles | 33% | #27 of 80 | Epoch AI | |
| Terminal-Bench 3.0 | 32.4% | #4 of 11 | Official leaderboard | |
| Terminal-Bench 4.0 | 41.8% | #9 of 23 | Official leaderboard | |
| Hermes Bench | 71.8% | #7 of 17 | Official leaderboard | |
| WitnessBench | 16.6% | #5 of 12 | Official leaderboard | |
| Chess Puzzles | 37% | #39 of 83 | Epoch AI | |
| Agent Arena | 0.01 | #28 of 53 | Official leaderboard | |
| RecreationBench | 24.4% | #8 of 10 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| JobBench | 61.4% | #1 of 16 | Official leaderboard | |
| MedScribe | 88.8% | #11 of 98 | Official leaderboard | |
| Legal Research Bench | 49% | #10 of 88 | Official leaderboard | |
| Tax Agent Bench | 39.7% | #11 of 79 | Official leaderboard | |
| Vals Legal Index | 74.6% | #5 of 33 | Official leaderboard | |
| GDPval-AA v2 | 1,769 | #4 of 26 | Model card | |
| Public Benefits Bench | 68.5% | #10 of 50 | Official leaderboard | |
| LegalBench | 84.8% | #29 of 138 | Official leaderboard | |
| Vending-Bench 2 | $8,164 | #16 of 66 | Official leaderboard | |
| Vals Finance Index | 60.5% | #9 of 35 | Official leaderboard | |
| Vals Finance Agent v2 | 55.8% | #22 of 80 | Official leaderboard | |
| Vending-Bench Arena | $7,841 | #9 of 32 | Official leaderboard | |
| Vals Finance Agent v2.1 | 65% | #10 of 35 | Official leaderboard | |
| Harvey LAB v1.1 (HLAB-Vals-1.1) | 14.6% | #10 of 33 | Official leaderboard | |
| E-Commerce Bench | 3.91 | #6 of 19 | Official leaderboard | |
| APEX-Agents | 56.6% | #18 of 56 | Epoch AI | |
| Harvey LAB (Legal Agent Benchmark) | 8.33% | #27 of 80 | Official leaderboard | |
| Vals Index v2.2 | 59.7% | #12 of 32 | Official leaderboard | |
| Legora BAR | 102.0 | #7 of 17 | Official leaderboard | |
| $OneMillion-Bench | 31% | #6 of 13 | Official leaderboard | |
| Holdings-IndividualTaxBench | 72.8% | #6 of 13 | Official leaderboard | |
| Clipping Bench | $644 | #9 of 19 | Official leaderboard | |
| TaxEval v2 | 72.4% | #62 of 129 | Official leaderboard | |
| MedCode | 42.9% | #47 of 96 | Official leaderboard | |
| Excel Modeling Benchmark v1.1 | 69.1% | #19 of 37 | Official leaderboard | |
| Thrive Holdings helpdesk ticket resolution benchmark | 48.1% | #8 of 15 | Official leaderboard | |
| Immigration Bench | 66.7% | #13 of 24 | Official leaderboard | |
| RCM-Bench-1 | 88.3% | #11 of 20 | Official leaderboard | |
| Ivo-micro1 ContractBench | 55% | #4 of 7 | Official leaderboard | |
| Excel Modeling Benchmark | 56.3% | #46 of 76 | Official leaderboard | |
| PolicyBench | 81.1% | #31 of 50 | Official leaderboard | |
| RWE-bench | 0% | #8 of 11 | Official leaderboard | |
| Quant-Arena | 38.9 | #7 of 9 | Official leaderboard | |
| Agents' Last Exam | 26.2% | #11 of 12 | Official leaderboard | |
| TaxCalcBench v2 | 0% | #26 of 26 | Official leaderboard | |
| Build-A-Chip-Bench | 0% | #5 of 5 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| VoxelBench | 1,782 | #25 of 56 | Official leaderboard | |
| Code2Video Benchmark | 1,496 | #10 of 19 | Official leaderboard | |
| ArtifactArena | 978 | #16 of 21 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CyberGym | 97.2% | #2 of 33 | Official leaderboard | |
| DeepsecBench | 21.8 | #11 of 28 | Official leaderboard | |
| SRE-Bench | 9.16% | #13 of 33 | Official leaderboard | |
| CyberBench v1.1 (Vals) | 72.1% | #17 of 43 | Official leaderboard | |
| DistressBench | 72.5% | #19 of 42 | Official leaderboard | |
| OncologyBench | 17.3% | #15 of 30 | Official leaderboard | |
| ExploitGym | 18.3% | #9 of 18 | Official leaderboard | |
| Human Pathogen Capabilities Test v2 (HPCT v2) | 53.2% | #37 of 71 | Official leaderboard | |
| FORTRESS | 28.2% | #38 of 66 | Official leaderboard | |
| ExploitBench | 54.4% | #11 of 19 | Model card | |
| PCT (Polarized Contrastive Pairs) | 46.8% | #27 of 46 | Official leaderboard | |
| Last Secure Code Benchmark | 21.3% | #4 of 6 | Official leaderboard | |
| BioSecBench-Refusal | 10.9% | #15 of 22 | Official leaderboard | |
| BioSecBench-Function | 31.8% | #19 of 27 | Official leaderboard | |
| TxBench-Oligo-Discovery | 31.9% | #20 of 28 | Official leaderboard | |
| MetagenomicsBench | 27.3% | #21 of 26 | Official leaderboard | |
| BioSecBench-Surveillance | 36.6% | #23 of 27 | Official leaderboard | |
| scBench-Long | 10.2% | #24 of 27 | Official leaderboard | |
| TxBench-Antibody-Discovery | 26.3% | #25 of 28 | Official leaderboard | |
| TxBench-Preclinical-Pharmacology | 35% | #25 of 28 | Official leaderboard | |
| EpiBench | 12.9% | #25 of 27 | Official leaderboard | |
| SpatialBench-Long | 18.4% | #25 of 27 | Official leaderboard | |
| VariantBench | 26.3% | #25 of 27 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMCA | 55.5% | #14 of 139 | Epoch AI | |
| Conceptual Reasoning Index | 63.4 | #26 of 149 | Official leaderboard | |
| SuperCLUE | 71.3 | #4 of 18 | Official leaderboard | |
| ACCoRD | 70.9 | #46 of 150 | Official leaderboard | |
| Hermes Index | 39.2 | #7 of 17 | Official leaderboard | |
| CAIS Risk Index | 48.8 | #27 of 65 | Official leaderboard | |
| CAIS Text Capabilities Index | 35.6 | #29 of 66 | Official leaderboard |
Z.ai's models in color, against every other model on the Epoch Capabilities Index, by release date.
The benchmarks the lab chose to headline, with the scores it gave.