GLM-5 vs GLM-5.3-Flash
GLM-5 (Z.ai (Zhipu AI)) and GLM-5.3-Flash (Z.ai (Zhipu AI)) compared on benchmarks, pricing, context window, and use-case rankings.
- GLM-5.3-Flash leads on overall intelligence (ECI 153 vs 146).
- GLM-5.3-Flash is cheaper on input tokens: $0.13 vs $0.70 per 1M.
- GLM-5.3-Flash has a larger context window (1M vs 205K tokens).
- GLM-5.3-Flash ranks higher for coding (75th vs 35th percentile).
| Attribute | GLM-5 | GLM-5.3-Flash |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 146 | 153 |
| Coding | 35 | 75 |
| Math | 14 | 52 |
| Reasoning & Knowledge | 25 | 52 |
| Agentic & Tools | 50 | 69 |
| Specifications | ||
| Developer | Z.ai (Zhipu AI) | Z.ai (Zhipu AI) |
| Family | — | — |
| Released | Feb 12, 2026 | Aug 20, 2026 |
| Parameters | 744B | 320B |
| Availability | Open weights (unrestricted) | Open weights (unrestricted) |
| Context window | 205K | 1M |
| Price — $/M input | $0.70 | $0.13 |
| Price — $/M output | $2.24 | $0.44 |
| Inputs | text | text, image, video |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 80% | 94% |
| APEX | 17% | 53% |
| ARC-AGI | 45% | 91% |
| ARC-AGI-2 | 5% | 66% |
| FrontierMath | 16% | — |
| FrontierMath Tier 4 | 2% | — |
| GPQA Diamond | 88% | 90% |
| Humanity's Last Exam | 29% | 40% |
| SciCode | 46% | 52% |
| SimpleBench | 53% | — |
| SWE-bench Verified | 72% | — |
| Terminal-Bench | 52% | — |
| WebDev Arena | 1436 | 1607 |
| WeirdML | 48% | — |
| τ²-bench | 98% | — |
| SimpleQA Verified | — | 32% |
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 GLM-5 better than GLM-5.3-Flash?
On Epoch AI's Capabilities Index, GLM-5.3-Flash scores higher (153) than GLM-5 (146). The right pick depends on your task, so compare their coding, math, and reasoning scores in the table above.
Which is cheaper, GLM-5 or GLM-5.3-Flash?
GLM-5.3-Flash is cheaper on input tokens at $0.13 per million, versus $0.70 (representative OpenRouter pricing).
Which has a larger context window, GLM-5 or GLM-5.3-Flash?
GLM-5.3-Flash supports up to 1M tokens, compared with 205K for the other.
Which is better for coding, GLM-5 or GLM-5.3-Flash?
GLM-5.3-Flash ranks higher across coding benchmarks like WebDev Arena and SciCode: 75th vs 35th 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.