Top-performing Chinese open model, strong coding + reasoning
SI v3 uses weighted percentages from one Artificial Analysis configuration. Ranking requires all five benchmarks. Partial scores average only available weights. Scores are not comparable to SI v2 or a probability of reaching singularity.
Compared with models released within six months of it.
| Benchmark | Score | Rank |
|---|---|---|
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 43.2% | #27 / 58 |
MMLU-Provals.ai Harder 10-option successor to MMLU; more reasoning-focused | 86.9% | #34 / 61 |
LiveCodeBenchvals.ai Contamination-free competitive programming (filtered by cutoff date) | 81.4% | #41 / 62 |
GPQAArtificial Analysis PhD-level science questions even experts struggle with | 86.8% | #59 / 96 |
HLEArtificial Analysis Challenging multidisciplinary questions evaluated by Artificial Analysis | 30.1% | #66 / 100 |
| Benchmark / source | Score |
|---|---|
HLE Artificial AnalysisGLM-5.1 (Reasoning) | 30.1% |
Terminal-Bench 2.1 Artificial AnalysisGLM-5.1 (Reasoning) | 61.8% |
Terminal-Bench 4.0 Artificial AnalysisGLM-5.1 (Reasoning) | 2% |
SciCode Artificial AnalysisGLM-5.1 (Reasoning) | 44.8% |
AA-LCR Artificial AnalysisGLM-5.1 (Reasoning) | 73.7% |
CritPt Artificial AnalysisGLM-5.1 (Reasoning) | 4.6% |
ITBench SRE Artificial AnalysisGLM-5.1 (Reasoning) | 40.3% |
IFBench Artificial AnalysisGLM-5.1 (Reasoning) | 76.3% |