Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | zai-orgGLM-5.2Remove × | stepfun-aiStep-5-PreviewRemove × |
|---|---|---|
| What’s different | GLM-5.2 is Z-AI's latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on… | 600B total and 27B active parameters; accepts images and video, with FP8 and BF16 weights for deployment. |
| Date | Jun 16, 2026Listed | Sep 18, 2026Released |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.0341 in / $7.00 out/ 1M tokensWafer · via OpenRouter · all routes ↗wafer/us · quantization=fp4 | $1.00 in / $2.70 out/ 1M tokensDeepInfra · all routes ↗ |
| Provider endpoints | 44 endpoints → | 6 endpoints → |
Benchmarks Each result retains its evaluation configuration | ||
| AA Intelligence ↗4.3.2 | Not reported | 43.73 ↗Effort not specifiedIndependent result |
| AA-Briefcase ↗1.1 | Not reported | 1,424.32 ↗Effort not specifiedIndependent result |
| GDPval-AA ↗2.1 | Not reported | 1,586.63 ↗Effort not specifiedIndependent result |
| AutomationBench-AA ↗AA Index 4.3.2 collection | Not reported | 50.96% ↗Effort not specifiedIndependent result |
| Terminal-Bench 4.0 · AA ↗ | Not reported | 33.33% ↗Effort not specifiedHarness unreportedIndependent result |
| SciCode ↗AA Index 4.3.2 collection | Not reported | 58.91% ↗AA · Under reviewEffort not specifiedIndependent result |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | Not reported | 46.48% ↗Effort not specifiedIndependent result |
| GDP.pdf ↗AA Index 4.3.2 collection | Not reported | 14.8% ↗Effort not specifiedIndependent result |
| CritPt ↗AA Index 4.3.2 collection | Not reported | 20.86% ↗AA · Under reviewEffort not specifiedIndependent result |
| AA-Omniscience ↗AA Index 4.3.2 collection | Not reported | 16.38 ↗Effort not specifiedIndependent result |
| AA-LCR ↗1.1 | Not reported | 88.33% ↗Effort not specifiedIndependent result |
| LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 62.01% ↗Effort: max · single run · equal mean of 7 suitesIndependent result |
| LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 76.9% ↗Effort: max · single runIndependent result |
| LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 72.8% ↗Effort: max · single runIndependent result |
| LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 24% ↗Effort: max · single runIndependent result |
| LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 85.6% ↗Effort: max · single runIndependent result |
| LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 27.5% ↗Effort: max · single runIndependent result |
| LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 63.5% ↗Effort: max · single runIndependent result |
| LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02) | Not reported | 83.8% ↗Effort: max · single runIndependent result |
Specifications | ||
| Context window | 1M | 1M |
| Max output | 943.7K | 64K |
| Parameters | — | — |
| Tool calling | Supported | Supported |
| Structured output | Supported | Supported |
| Image input | Not reported | Supported |
| Video input | Not reported | Supported |
| Reasoning | Supported | Supported |
| Prompt caching | Supported | Supported |
| Open weights | Supported | Supported |