GLM-5.1 places in the top three on 4 benchmarks.
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 | |
|---|---|---|---|---|
| LMArena (Elo) | 1,465 | #44 of 333 | Official leaderboard | |
| EQ-Bench 3 | 1,539 | #13 of 78 | Official leaderboard | |
| Humanity's Last Exam | 52.3% | #31 of 147 | Model card | |
| Longform Creative Writing (EQ-Bench) | 73.5 | #31 of 119 | Official leaderboard | |
| Creative Writing v3 | 72.2 | #44 of 120 | Official leaderboard | |
| Extended NYT Connections | 77.7% | #43 of 97 | Official leaderboard | |
| Judgemark v4 | 67.2 | #18 of 40 | Official leaderboard | |
| SEA-HELM | 66.9 | #36 of 62 | Official leaderboard | |
| BullshitBench V2 | 22% | #81 of 122 | Official leaderboard | |
| SimpleQA Verified | 34% | #58 of 84 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 89.9% | #44 of 219 | Epoch AI | |
| FrontierMath | 33.5% | #15 of 70 | Epoch AI | |
| OTIS Mock AIME 2024-2025 | 93.3% | #50 of 202 | Epoch AI | |
| Echo General AI Prediction Leaderboard | 1,006 | #5 of 17 | Official leaderboard | |
| FrontierMath Tier 4 | 12.5% | #19 of 55 | Epoch AI | |
| HMMT Nov 2025 | 94% | #8 of 23 | Model card | |
| MathArena (Apex, IMO, USAMO) | 11.5% | #20 of 47 | Official leaderboard | |
| CritPt | 4.57% | #71 of 160 | Epoch AI | |
| AIME 2026 | 95.8% | #14 of 31 | Official leaderboard | |
| SimpleBench | 55.1% | #46 of 100 | Official leaderboard | |
| ProofBench | 22.2% | #28 of 59 | Official leaderboard | |
| HMMT 2026 | 89.4% | #15 of 31 | Official leaderboard | |
| IMO-AnswerBench | 83.8% | #18 of 37 | Model card | |
| ResearchClawBench | 18.2 | #12 of 23 | Official leaderboard | |
| FrontierMath Tiers 1-3 v2 | 36.8% | #62 of 89 | Epoch AI | |
| NatureBench | 6.67% | #15 of 18 | Official leaderboard | |
| Project Euler (MathArena) | 67.2% | #4 of 4 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveSQLBench | 29% | #11 of 36 | Official leaderboard | |
| EvoCode-Bench | 36.2% | #4 of 13 | Official leaderboard | |
| WeirdML | 57.1% | #37 of 112 | Official leaderboard | |
| OpenHands Index | 58.2% | #12 of 33 | Official leaderboard | |
| SWE-Bench Pro | 58.4% | #31 of 77 | Model card | |
| WebDev Arena | 1,508 | #43 of 105 | Epoch AI | |
| Code Arena | 1,508 | #55 of 124 | Official leaderboard | |
| SWE-bench Verified | 74.2% | #16 of 32 | Epoch AI | |
| ALE-Bench | 887 | #64 of 121 | Epoch AI | |
| Code Migration | 25.8% | #47 of 78 | Official leaderboard | |
| Vibe Code Bench | 31.5% | #73 of 115 | Official leaderboard | |
| NL2Repo-Bench | 42.7% | #18 of 28 | Model card | |
| AndroidBench | 63.2% | #21 of 32 | Official leaderboard | |
| SlopCodeBench | 13.8% | #11 of 14 | Official leaderboard | |
| SWE-Marathon | 1.00% | #10 of 12 | Official leaderboard | |
| EvoCode-Bench v2 | 5.90% | #12 of 13 | Official leaderboard | |
| GBAEval | 0% | #23 of 23 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PinchBench | 80.9% | #2 of 48 | Official leaderboard | |
| LiveClawBench | 74.7% | #2 of 17 | Official leaderboard | |
| Terminal-Bench 2.0 | 69% | #8 of 61 | Model card | |
| SkillsBench | 58.4% | #4 of 21 | Official leaderboard | |
| VitaBench 2.0 | 42% | #5 of 20 | Official leaderboard | |
| Claw-Eval Pass^3 | 62.3% | #6 of 23 | Official leaderboard | |
| GAIA | 68.8% | #19 of 57 | Official leaderboard | |
| SnakeBench | 26 | #62 of 183 | Official leaderboard | |
| PACT | 1,554 | #9 of 26 | Official leaderboard | |
| BrowseComp | 79.3% | #27 of 77 | Model card | |
| Toolathlon | 40.7% | #18 of 50 | Official leaderboard | |
| Claw-Eval | 77.3% | #9 of 23 | Official leaderboard | |
| tau3-bench | 70.6% | #5 of 12 | Model card | |
| ClawBench V2 | 34.6% | #3 of 7 | Official leaderboard | |
| MCP Atlas | 75.6% | #18 of 34 | Official leaderboard | |
| CivBench | 1,482 | #11 of 18 | Official leaderboard | |
| DeepTerminalBench | 30% | #6 of 9 | Official leaderboard | |
| PinchBench 2.0 | 60% | #42 of 57 | Official leaderboard | |
| Chess Puzzles | 20% | #63 of 83 | Epoch AI | |
| EdgeBench | 37.4 | #4 of 5 | Official leaderboard | |
| Long-Horizon-Terminal-Bench (LHTB) | 26.7% | #22 of 25 | Official leaderboard | |
| CEO-Bench | $0 | #18 of 19 | Official leaderboard | |
| Terminal-Bench 2.1 | 58.6% | #13 of 13 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vals Finance Agent | 57.7% | #10 of 49 | Official leaderboard | |
| FORTE | 73.8% | #5 of 21 | Official leaderboard | |
| LegalBench | 84.4% | #33 of 138 | Official leaderboard | |
| CorpFin v2 | 64.5% | #38 of 119 | Official leaderboard | |
| Vending-Bench 2 | $5,634 | #28 of 66 | Official leaderboard | |
| MedCode | 41.6% | #50 of 96 | Official leaderboard | |
| Public Benefits Bench | 61.8% | #29 of 50 | Official leaderboard | |
| TaxEval v2 | 71.2% | #76 of 129 | Official leaderboard | |
| E-Commerce Bench | 2.26 | #12 of 19 | Official leaderboard | |
| Legal Research Bench | 27.9% | #58 of 88 | Official leaderboard | |
| Vals Finance Agent v2 | 44.8% | #57 of 80 | Official leaderboard | |
| APEX-Agents | 40.9% | #43 of 56 | Epoch AI | |
| MedScribe | 72.3% | #81 of 98 | Official leaderboard | |
| ProfBench | 41.6% | #60 of 72 | Official leaderboard | |
| CaseLaw v2 | 51.5% | #48 of 53 | Official leaderboard | |
| Harvey LAB (Legal Agent Benchmark) | 0% | #73 of 80 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| VoxelBench | 1,443 | #41 of 56 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CyberGym | 84% | #8 of 33 | Official leaderboard | |
| CRSBench | 68.6% | #2 of 5 | Official leaderboard | |
| Human Pathogen Capabilities Test v2 (HPCT v2) | 50.3% | #43 of 71 | Official leaderboard | |
| BiomniBench | 60.4 | #5 of 8 | Official leaderboard | |
| ExploitBench | 18% | #6 of 9 | Official leaderboard | |
| ExploitGym | 0.46% | #18 of 18 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CAIS Text Capabilities Index | 27.6 | #37 of 66 | Official leaderboard | |
| CAIS Risk Index | 58.0 | #44 of 65 | 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.