Overall score
55.6
Rank #39 · B confidence
Z.AI · stable
Z.AI's GLM-5 model tracked via the BenchLM July 2026 leaderboard for capability comparison.
Overall score
55.6
Rank #39 · B confidence
Capability
58.7
25 eligible benchmark families
Coverage
73%
Confidence B
Benchmarks scored
31
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 |
|---|---|---|---|
| τ²-Bench TelecomRanking weighted | agents | 98.2456% | 2026-07-15 |
| τ-benchRanking weighted | agents | 98.2% | 2026-07-15 |
| AIME 2026Ranking weighted | mathematics | 95.8% | 2026-07-15 |
| IFEval | instruction following | 92.6% | 2026-07-15 |
| HMMT Feb 2026Ranking weighted | mathematics | 86.4% | 2026-07-15 |
| GPQA DiamondRanking weighted | reasoning | 86% | 2026-07-15 |
| MMLU-ProRanking weighted | research | 85.7% | 2026-07-15 |
| BenchLM Knowledge priorRanking weighted | research | 82.7% | 2026-07-15 |
| SWE-bench VerifiedRanking weighted | coding | 77.8% | 2026-07-15 |
| IFBench | instruction following | 72.3% | 2026-07-15 |
| SuperGPQARanking weighted | reasoning | 66.8% | 2026-07-15 |
| AA Long Context ReasoningRanking weighted | research | 63.3333% | 2026-07-15 |
| SWE-RebenchRanking weighted | coding | 62.8% | 2026-07-15 |
| LongBench v2 | long context | 60.8% | 2026-07-15 |
| BenchLM Coding priorRanking weighted | coding | 60.28% | 2026-07-15 |
| BenchLM Multimodal priorRanking weighted | multimodal | 56.6% | 2026-07-15 |
| BenchLM Reasoning priorRanking weighted | reasoning | 56.2% | 2026-07-15 |
| SWE-Bench ProRanking weighted | coding | 55.1% | 2026-07-15 |
| BenchLM Agentic priorRanking weighted | agents | 54.85% | 2026-07-15 |
| BenchLM Math priorRanking weighted | mathematics | 51.5% | 2026-07-15 |
| Humanity's Last ExamRanking weighted | reasoning | 50.4% | 2026-07-15 |
| SciCodeRanking weighted | coding | 46.2% | 2026-07-15 |
| Long-Horizon-Terminal-BenchRanking weighted | agents | 43.2% | 2026-07-15 |
| Terminal-Bench HardRanking weighted | agents | 43.1818% | 2026-07-15 |
| ToolathlonRanking weighted | agents | 38% | 2026-07-15 |
| GAIARanking weighted | agents | 31.5% | 2026-07-15 |
| MCP AtlasRanking weighted | agents | 31.1% | 2026-07-15 |
| FrontierMathRanking weighted | mathematics | 16.434% | 2026-07-15 |
| APEX-Agents-AARanking weighted | agents | 14.4543% | 2026-07-15 |
| AA-OmniscienceRanking weighted | research | 2 index | 2026-07-15 |
| CritPtRanking weighted | reasoning | 2% | 2026-07-15 |
Showing the best of 32 raw result rows across 31 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.