GLM-4.7 places in the top three on Terminal-Bench Hard.
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) | 1,441 | #75 of 333 | Official leaderboard | |
| MMLU-Pro | 84.3% | #38 of 151 | Model card | |
| EQ-Bench 3 | 1,463 | #26 of 78 | Official leaderboard | |
| Humanity's Last Exam | 42.8% | #54 of 147 | Model card | |
| Judgemark v2.1 | 77.5 | #17 of 42 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 66.0 | #52 of 119 | Official leaderboard | |
| Creative Writing v3 | 70.2 | #54 of 120 | Official leaderboard | |
| SEA-HELM | 71.5 | #29 of 62 | Official leaderboard | |
| LOCA-Bench | 5.30% | #6 of 9 | Official leaderboard | |
| CL-bench | 15.9% | #17 of 24 | Official leaderboard | |
| Vectara Hallucination Leaderboard (2025 dataset) | 11.7% | #75 of 104 | Official leaderboard | |
| SimpleQA Verified | 32.2% | #62 of 84 | Epoch AI | |
| CL-bench Life | 10.9% | #12 of 16 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AIME 2025 | 95.7% | #22 of 143 | Model card | |
| HMMT 2025 | 97.1% | #9 of 49 | Model card | |
| General365 | 57.4% | #8 of 23 | Official leaderboard | |
| GPQA Diamond | 83.3% | #78 of 219 | Epoch AI | |
| HMMT Nov 2025 | 93.5% | #9 of 23 | Model card | |
| OTIS Mock AIME 2024-2025 | 83.3% | #83 of 202 | Epoch AI | |
| CritPt | 1.71% | #86 of 160 | Epoch AI | |
| IMO-AnswerBench | 82% | #20 of 37 | Model card | |
| SimpleBench | 47.7% | #56 of 100 | Official leaderboard | |
| FrontierMath | 2.44% | #53 of 70 | Epoch AI | |
| ProofBench | 6.00% | #49 of 59 | Official leaderboard | |
| FrontierMath Tier 4 | 0% | #53 of 55 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v6 | 84.9% | #21 of 76 | Model card | |
| SWE-bench Verified | 73.8% | #53 of 150 | Model card | |
| Bird-SQL | 62.9% | #6 of 13 | Official leaderboard | |
| WebDev Arena | 1,435 | #60 of 105 | Epoch AI | |
| OTelBench | 13% | #8 of 14 | Official leaderboard | |
| Code Arena | 1,435 | #72 of 124 | Official leaderboard | |
| IOI (Vals) | 7.58% | #35 of 55 | Official leaderboard | |
| LiveSQLBench | 20.3% | #25 of 36 | Official leaderboard | |
| SWE-bench Multilingual | 66.7% | #49 of 70 | Model card | |
| OpenHands Index | 42.3% | #26 of 33 | Official leaderboard | |
| ALE-Bench | 399 | #104 of 121 | Epoch AI | |
| OJBench | 50.8% | #7 of 8 | Official leaderboard | |
| PostTrainBench | 7.48% | #21 of 23 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Terminal-Bench Hard | 33.3% | #2 of 11 | Model card | |
| tau2-bench | 87.4% | #19 of 69 | Model card | |
| SnakeBench | 26 | #65 of 183 | Official leaderboard | |
| BrowseComp-ZH | 66.6% | #8 of 17 | Model card | |
| BrowseComp | 67.5% | #48 of 77 | Model card | |
| VITA-Bench | 18.3% | #12 of 18 | Official leaderboard | |
| LisanBench | 197.0 | #90 of 133 | Official leaderboard | |
| Terminal-Bench 2.0 | 33.4% | #30 of 43 | Official leaderboard | |
| Chess Puzzles | 21% | #58 of 83 | Epoch AI | |
| Toolathlon | 23.8% | #37 of 50 | Official leaderboard | |
| Pencil Puzzle Bench | 0% | #44 of 53 | Official leaderboard | |
| MCP Atlas | 58.1% | #29 of 34 | Official leaderboard | |
| RWSearch | 69% | #6 of 7 | Official leaderboard | |
| BalatroBench | 3.07 | #15 of 16 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vals Finance Agent v1 | 41.9% | #17 of 47 | Official leaderboard | |
| LegalBench | 83.4% | #55 of 138 | Official leaderboard | |
| ProfBench | 46.6% | #39 of 72 | Official leaderboard | |
| CaseLaw v2 | 54.9% | #37 of 53 | Official leaderboard | |
| TaxEval v2 | 68.8% | #91 of 129 | Official leaderboard | |
| Vending-Bench 2 | $2,377 | #48 of 66 | Official leaderboard | |
| Vals Finance Agent | 46% | #36 of 49 | Official leaderboard | |
| MedCode | 32.8% | #80 of 96 | Official leaderboard | |
| CorpFin v2 | 46.4% | #101 of 119 | Official leaderboard | |
| MedScribe | 68.6% | #88 of 98 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BinaryAudit | 24.6% | #9 of 20 | Official leaderboard | |
| KORA | 25.2% | #30 of 42 | Official leaderboard | |
| CyberGym | 23.5% | #24 of 33 | 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.