Model
GLM-5.1
Zhipu AI · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 4.6 | accuracy | N/A | Independent | low | epoch.ai |
| CroissantMiner | 0.6 | accuracy | single-pass | Independent | medium | arxiv.org |
| GPQA Diamond | 89.9 | accuracy | N/A | Independent | high | epoch.ai |
| SimpleQA Verified | 34.0 | accuracy | N/A | Independent | high | epoch.ai |
Math
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| EfficientOpt | 70.0 | solver_time_ratio | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ANCHOR | 7.8 | fccr | cline | Independent | medium | arxiv.org |
| ANCHOR | 6.1 | fccr | opencode | Independent | medium | arxiv.org |
| SciCode | 43.8 | score | N/A | Independent | medium | artificialanalysis.ai |
| SWE-bench Verified | 74.2 | resolved_rate | N/A | Independent | high | epoch.ai |
| WEAVE | 28.7 | resolved_rate | opencode | Independent | medium | arxiv.org |
| WEAVE | 21.0 | resolved_rate | cline | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| ExploitBench | 18.1 | mean_capability | N/A | Independent | low | epoch.ai |
| FinSkillBench | 0.3 | score | N/A | Independent | medium | arxiv.org |
| HelpMeOut | 0.6 | m1 | N/A | Independent | medium | arxiv.org |
| Legal Research Bench | 27.6 | accuracy | N/A | Independent | medium | arxiv.org |
Multimodal
Multimodal| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| FigCodeBench | 44.2 | mmos | N/A | Independent | medium | arxiv.org |
Multilingual
MultilingualReproduced by the community
Loading community runs…