LabsZ.ai
Z.ai
Track Z.ai model scores across public AI benchmarks including GPQA Diamond, AAII, ECI, GDPval-AA, and SciCode. Each result is shown one benchmark at a time, with source links and evaluation dates — no blended score or composite ranking. 5 models tracked, spanning GLM and GLM-4 (GLM-4.7 series).
Models 5
GLM-5.2
GLM · glm-5.2
2026-06-16
13 results
GLM-5.1
GLM · glm-5.1
2026-04-07
27 results
GLM-5
GLM · glm-5
2026-02-11
25 results
GLM-4.7
GLM-4 (GLM-4.7 series) · glm-4.7
2025-12-22
16 results
GLM-4.6
GLM · glm-4.6
2025-09-30
18 results
Progress by benchmark
Show progress on
Single benchmark only
This view shows GPQA Diamond (accuracy) only. Other benchmarks use different metrics and are not directly comparable.
Progress matrix
| Model | SWE-bench Verified % resolved | Terminal-Bench 2.1 task success | DeepSWE % resolved | GPQA Diamond accuracy | LiveCodeBench Pro Codeforces Elo | Humanity's Last Exam accuracy | LiveBench score | SWE-bench Pro % resolved | Berkeley Function Calling Leaderboard accuracy | MMMU-Pro accuracy | LMArena source-defined rating | ARC-AGI-1 accuracy | ARC-AGI-2 accuracy | ARC-AGI-3 accuracy | FrontierMath accuracy | AIME (OTIS Mock) accuracy | SimpleQA Verified accuracy | GBA Eval overall score | WeirdML average accuracy | MCP Atlas pass rate | Remote Labor Index automation rate | Artificial Analysis Intelligence Index Index | Epoch Capabilities Index Index | Aider Polyglot % correct | SWE-rebench Resolved rate (pass@1) | MMLU-Pro accuracy | OSWorld task success rate | GAIA: A Benchmark for General AI Assistants accuracy | BrowseComp accuracy | τ²-bench (Telecom) pass^1 | AIME 2026 accuracy | MathVista accuracy | Video-MME accuracy | GDPval Elo | LiveCodeBench Pass@1 | METR Task-Completion Time Horizons 50% time horizon | SciCode accuracy | MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark) accuracy | AA-Omniscience: Knowledge and Hallucination Benchmark AA-Omniscience Index | IFBench accuracy | MultiChallenge accuracy | OpenAI-MRCR v2 (Multi-Round Coreference Resolution) accuracy (mean SequenceMatcher similarity) | LongBench v2 accuracy | Global-MMLU accuracy | Video-MMMU accuracy | WebDev Arena Elo | Search Arena Elo | Arena-Hard-Auto v2.0 % win rate | EQ-Bench Creative Writing v3 Elo | Design Arena Elo | AILuminate AI Safety Benchmark Safety grade | MASK (Model Alignment between Statements and Knowledge) Honesty score | MCP-Universe Overall Success Rate | CharXiv accuracy | OCRBench v2 accuracy | ScreenSpot-Pro accuracy | FACTS Grounding Grounding accuracy | BigCodeBench calibrated Pass@1 | SWE-bench Multilingual % resolved | SWE-bench Multimodal % resolved | SuperGPQA accuracy | EnigmaEval accuracy | ZeroBench accuracy | IMO-Bench accuracy | PutnamBench Problems solved | MathArena HMMT February 2026 accuracy | FrontierMath Tier 4 accuracy | Vectara Hallucination Leaderboard Hallucination Rate | Gray Swan Arena (Agent Red-Teaming / Indirect Prompt Injection) Attack Success Rate (ASR) | PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts Difficulty-Weighted Accuracy (DW-ACC) | Vibe Code Bench Overall accuracy | Online-Mind2Web Task success rate | WebArena Task success rate | GSO: Software Optimization Benchmark for SWE-Agents Opt@1 | MultiNRC accuracy | Terminal-Bench 2.0 task success | SWE-Marathon resolution rate (pass@1) | FrontierCode weighted score (Diamond) | FrontierSWE dominance score | ProgramBench almost-resolved rate | CursorBench score | PostTrainBench weighted average score |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GLM-4.6 GLM | — | — | — | — | — | — | — | 9.67% | 72.38% | — | 1440 | — | — | — | 3.82% | — | — | — | — | — | — | 30.2 | 141.4 | — | — | 82.9% | — | — | — | — | — | — | — | 1029 | 56.1% | — | 38.4% | — | — | — | — | — | — | 85.6% | — | 1355 | — | — | 1393 | 1220 | — | — | 25.97% | — | — | — | — | — | — | — | — | — | — | — | — | — | 2.1% | 9.5% | — | — | 3.09% | — | — | — | — | — | — | — | — | — | — | — |
| GLM-4.7 GLM-4 (GLM-4.7 series) | 73.8% | — | — | 85.7% | — | 24.8% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 42.1 | 144.6 | — | 58.7% | 85.6% | — | — | — | — | — | — | — | 1185 | — | — | 45.1% | — | — | — | — | — | — | 79.9% | — | 1440 | — | — | 1403 | 1273 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 11.7% | — | — | — | — | — | — | — | 41.0% | — | — | — | — | — | 7.48% |
| GLM-5 GLM | 72.1% | — | — | 87.8% | — | — | — | — | — | — | 1445 | 44.67% | 4.86% | — | 16.43% | 80.0% | — | — | 48.2% | — | — | 49.8 | 146.6 | — | 62.8% | — | — | 33.8% | — | — | 95.83% | — | — | 1395 | — | — | 46.2% | — | — | — | — | — | — | 81.9% | — | 1436 | — | — | 1658 | 1300 | — | — | — | — | — | — | — | — | 69.7% | — | — | — | — | — | — | 86.36% | 2.1% | 10.1% | — | — | 23.36% | — | — | — | — | — | — | — | — | — | — | 13.88% |
| GLM-5.1 GLM | 74.2% | — | 17.48% | 85.5% | — | 25.63% | 70.18% | — | — | — | 1469 | — | — | — | 33.45% | 92.2% | 37.3% | — | 57.1% | — | — | 51.4 | 149.9 | — | 62.7% | — | — | — | — | 97.7% | 95.83% | — | — | 1535 | — | — | 43.8% | — | 2 | 76.3% | — | — | — | — | — | 1533 | — | — | 1645 | 1335 | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 89.39% | 12.5% | — | — | — | 31.46% | — | — | — | — | 63.5% | — | — | 31% | — | — | — |
| GLM-5.2 GLM | — | 81.0% | 46.2% | 91.2% | — | 40.5% | — | 62.1% | — | — | — | 77% | 22.78% | — | — | — | — | — | — | 76.8% | — | — | — | — | — | — | — | — | — | — | 99.2% | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | — | 92.5% | — | — | — | — | — | — | — | — | — | — | 13.0% | — | 74% | — | — | 34.3% |
Scores are not normalised across benchmarks. Each column uses its own metric. Compare columns independently.