Gemini 3.1 Pro vs GLM-5.2
Gemini 3.1 Pro (Google DeepMind) and GLM-5.2 (Z.ai (Zhipu AI)) compared on benchmarks, pricing, context window, and use-case rankings.
- Gemini 3.1 Pro leads on overall intelligence (ECI 155 vs 152).
- GLM-5.2 ranks higher for coding (83th vs 59th percentile).
| Attribute | Gemini 3.1 Pro | GLM-5.2 |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 155 | 152 |
| Coding | 59 | 83 |
| Math | 71 | 33 |
| Reasoning & Knowledge | 93 | 59 |
| Agentic & Tools | 79 | 89 |
| Specifications | ||
| Developer | Google DeepMind | Z.ai (Zhipu AI) |
| Family | Gemini | — |
| Released | Feb 19, 2026 | Jun 16, 2026 |
| Parameters | — | — |
| Availability | API access | Open weights (unrestricted) |
| Context window | — | 1M |
| Price — $/M input | — | $0.50 |
| Price — $/M output | — | $3.04 |
| Inputs | — | text |
| Outputs | — | text |
| Benchmarks | ||
| AIME 2024/2025 | 96% | 86% |
| APEX | 34% | 36% |
| ARC-AGI | 98% | 77% |
| ARC-AGI-2 | 77% | 23% |
| FrontierMath | 37% | — |
| FrontierMath Tier 4 | 17% | — |
| GPQA Diamond | 94% | 92% |
| GSO (code optimization) | 23% | — |
| Humanity's Last Exam | 46% | 41% |
| METR task horizon | 6.4 h | — |
| SimpleBench | 80% | — |
| SimpleQA Verified | 77% | 38% |
| SWE-bench Verified | 76% | 79% |
| Terminal-Bench | 80% | — |
| WebDev Arena | 1461 | 1593 |
| WeirdML | 72% | 70% |
| SciCode | — | 51% |
| τ²-bench | — | 99% |
Use-case scores are 0–100 percentile composites across each area’s benchmarks, ranked against every model from the past year. Highlighted cells lead each row. Open a model for the full picture.
Frequently asked questions
Is Gemini 3.1 Pro better than GLM-5.2?
On Epoch AI's Capabilities Index, Gemini 3.1 Pro scores higher (155) than GLM-5.2 (152). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is better for coding, Gemini 3.1 Pro or GLM-5.2?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, GLM-5.2 ranks higher — 83th vs 59th percentile among the models tracked on Model Beat.
Want a different match-up? Open the compare tool to add or swap models.
More comparisons
Benchmarks & model data from Epoch AI (CC BY); pricing & specs from OpenRouter. ECI = Epoch Capabilities Index.