Overall score
64.7
Rank #11 · A confidence
Z.AI · preview
Z.AI's GLM-5.2 model tracked via the BenchLM July 2026 leaderboard for capability comparison.
Overall score
64.7
Rank #11 · A confidence
Capability
60.1
26 eligible benchmark families
Coverage
89%
Confidence A
Benchmarks scored
30
32 raw result rows
Model specification
Identity, configuration and price are preserved as dated source records.
Category profile
A category remains Not evaluated until an eligible source-qualified result is attached.
Benchmark scores
Best published score per benchmark. Open any row for the full per-benchmark leaderboard.
| Benchmark | Category | Score | Date |
|---|---|---|---|
| AIME 2026Ranking weighted | mathematics | 99.2% | 2026-07-15 |
| τ²-Bench TelecomRanking weighted | agents | 99.1228% | 2026-07-15 |
| τ-benchRanking weighted | agents | 99.1% | 2026-07-15 |
| HMMT Feb 2026Ranking weighted | mathematics | 92.5% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 91.2% | 2026-07-15 |
| BenchLM Knowledge priorRanking weighted | research | 84.5% | 2026-07-15 |
| BenchLM Math priorRanking weighted | mathematics | 81.2% | 2026-07-15 |
| Terminal-BenchRanking weighted | agents | 81% | 2026-07-15 |
| MCP AtlasRanking weighted | agents | 76.8% | 2026-07-15 |
| IFBench | instruction following | 73.3% | 2026-07-15 |
| IFEval | instruction following | 73.3% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 71.3333% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 62.31% | 2026-07-15 |
| SWE-Bench ProRanking weighted | coding | 62.1% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 60.98% | 2026-07-15 |
| CursorBenchRanking weighted | coding | 55% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 54.7% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 50.8% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 50.7576% | 2026-07-15 |
| GDPval-AA v2Ranking weighted | agents | 50.6945% | 2026-07-15 |
| SciCodeRanking weighted | coding | 50.5% | 2026-07-15 |
| ToolathlonRanking weighted | agents | 48.2% | 2026-07-15 |
| EnterpriseOps-Gym-AARanking weighted | agents | 42.7335% | 2026-07-15 |
| ITBench-AARanking weighted | agents | 42.6554% | 2026-07-15 |
| APEX-Agents-AARanking weighted | agents | 33.7021% | 2026-07-15 |
| AA AutomationBenchRanking weighted | agents | 27.8% | 2026-07-15 |
| τ³-BankingRanking weighted | agents | 26.8041% | 2026-07-15 |
| CritPtRanking weighted | reasoning | 20.8571% | 2026-07-15 |
| Harvey LAB-AARanking weighted | agents | 7.5% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | 3.9667 index | 2026-07-15 |
Showing the best of 32 raw result rows across 30 benchmark families.
Price and efficiency
Operational values are shown only when the source publishes a comparable measurement or a valid derivation.
Verification summary
News and X posts are structurally excluded from this model's evidence graph.
Missing publication dimensions: efficiency, value. The last source check for this exact model was 2026-07-16.
Related models
Exact variants remain separate even when they share a provider or family.