Model
GLM-5.3
Zhipu AI · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| CritPt | 19.1 | accuracy | N/A | Independent | low | epoch.ai |
| GPQA Diamond | 90.9 | accuracy | N/A | Independent | high | epoch.ai |
| SimpleQA Verified | 41.0 | accuracy | N/A | Independent | high | epoch.ai |
| TasteVal | 0.6 | compute_multiplier | N/A | Independent | medium | arxiv.org |
Math
Math| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| OpenProblemBench | 1.2 | mean_judged_solve_rate | N/A | Independent | medium | arxiv.org |
Coding
Coding| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| A2Z GameSpec-Bench | 55.6 | gdd_fidelity | N/A | Independent | medium | arxiv.org |
| AAArena | 2359.2 | elo | codex | Independent | medium | arxiv.org |
| CRUXEval-style | 55.3 | accuracy | N/A | Independent | medium | arxiv.org |
| D2K-Bench | 1.3 | s_perf | N/A | Independent | medium | arxiv.org |
| DeepSWE | 69.0 | pass@1 | mini-swe-agent | Independent | medium | deepswe.datacurve.ai |
| MetaKernelBench | 51.4 | paired_lift | cute dsl | Independent | medium | arxiv.org |
| SciCode | 59.0 | score | N/A | Independent | medium | artificialanalysis.ai |
| WorldSolver | 23.6 | score | N/A | Independent | medium | arxiv.org |
Agentic / Tool Use
Agentic / Tool Use| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| AgenticBBO-Bench | 0.5 | hpo | N/A | Independent | medium | arxiv.org |
| AgentMonBench | 1.0 | silentswap | N/A | Independent | medium | arxiv.org |
| BioStudyBench | 81.3 | pass_rate | N/A | Independent | medium | arxiv.org |
| BOTTLED | 0.3 | f1 | N/A | Independent | medium | arxiv.org |
| IGMBench | 48.2 | success_rate | N/A | Independent | medium | arxiv.org |
| Incident-Arena | 0.3 | pass@1 | claude code | Independent | medium | arxiv.org |
| ServeLearnBench | 39.5 | accuracy | skillopt | Independent | medium | arxiv.org |
Long Context
Long Context| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| LongHarness Bench | 9.5 | accuracy | direct | Independent | medium | arxiv.org |
Instruction Following
Instruction Following| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| Design Creativity Bench | 41.9 | overall | N/A | Independent | medium | arxiv.org |
Safety & Alignment
Safety & Alignment| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| FIGS | 50.0 | automated_judge_applying_a_10-rule_taxonomy_separating_sycophancy_from_calibrated_validation | N/A | Independent | medium | arxiv.org |
| Nonpublic Vulnerabilities Benchmark | 0.6 | attack_score | opencode | Independent | medium | arxiv.org |
| ObligationBench | 30.4 | recall | N/A | Independent | medium | arxiv.org |
Multilingual
Multilingual| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| HakemBench | 0.8 | composite | N/A | Independent | medium | arxiv.org |
Reproduced by the community
Loading community runs…