Model
GLM-5
Zhipu AI · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CL-bench | 18.7 | overall | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 87.8 | accuracy | N/A | Independent | high | epoch.ai |
| GPQA Diamond | 86.0 | accuracy | N/A | Self-reported | low | artificialanalysis.ai |
| HLE | 50.4 | accuracy | N/A | Self-reported | low | lastexam.ai |
| LMArena | 1454.0 | elo | N/A | Self-reported | low | lmarena.ai |
| MMLU-Pro | 70.4 | accuracy | N/A | Self-reported | low | artificialanalysis.ai |
Math
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| AIME 2025 | 84.0 | accuracy | N/A | Self-reported | low | kaggle.com |
| MATH-500 | 88.0 | accuracy | N/A | Self-reported | low | kaggle.com |
| SELF-POT | 0.7 | success_rate | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| LiveCodeBench | 52.0 | pass@1 | N/A | Self-reported | low | livecodebench.github.io |
| SWE-bench Verified | 77.8 | resolved_rate | N/A | Self-reported | low | swebench.com |
| SWE-bench Verified | 72.1 | resolved_rate | N/A | Independent | high | epoch.ai |
| Terminal-Bench 2.0 | 56.2 | accuracy | N/A | Self-reported | low | tbench.ai |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| 2D-FET-Bench V2 | 28.8 | pass@1 | react-3/c0 | Independent | medium | arxiv.org |
| BrowseComp | 75.9 | accuracy | N/A | Self-reported | low | openai.com |
| GeoNatureAgent (GNA) | 50.2 | accuracy | N/A | Independent | medium | arxiv.org |
| OpenGameEval | 42.9 | pass_rate | N/A | Independent | medium | arxiv.org |
| Synthetic Trading Benchmark | 9.2 | e0_sharpe | N/A | Independent | medium | arxiv.org |
| τ²-bench | 89.7 | pass^1 | N/A | Self-reported | low | github.com |
| Terminal-Bench | 52.4 | accuracy | Terminus 2 | Independent | medium | tbench.ai |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| IFEval | 88.0 | prompt_strict_accuracy | N/A | Self-reported | low | artificialanalysis.ai |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| DistressBench | 0.7 | score | N/A | Independent | medium | arxiv.org |
Abstract Reasoning
Abstract ReasoningReproduced by the community
Loading community runs…