GLM-4.6 vs GPT-6 Astra
GLM-4.6 (Z.ai (Zhipu AI),Tsinghua University) and GPT-6 Astra (OpenAI) compared on benchmarks, pricing, context window, and use-case rankings.
- GPT-6 Astra leads on overall intelligence (ECI 169 vs 141).
- GLM-4.6 is cheaper on input tokens — $0.60 vs $10.00 per 1M.
- GPT-6 Astra has a larger context window (1.1M vs 205K tokens).
- GPT-6 Astra ranks higher for coding (95th vs 18th percentile).
| Attribute | GLM-4.6 | GPT-6 Astra |
|---|---|---|
| Scores | ||
| Intelligence (ECI) | 141 | 169 |
| Coding | 18 | 95 |
| Math | 20 | 96 |
| Reasoning & Knowledge | 25 | 99 |
| Agentic & Tools | 12 | 96 |
| Specifications | ||
| Developer | Z.ai (Zhipu AI),Tsinghua University | OpenAI |
| Family | — | GPT |
| Released | Sep 30, 2025 | Sep 3, 2026 |
| Parameters | 357B | — |
| Availability | Open weights (unrestricted) | API access |
| Context window | 205K | 1.1M |
| Price — $/M input | $0.60 | $10.00 |
| Price — $/M output | $2.20 | $50.00 |
| Inputs | text | file, image, text |
| Outputs | text | text |
| Benchmarks | ||
| AIME 2024/2025 | 86% | 100% |
| APEX | 4% | 47% |
| FrontierMath | 4% | — |
| FrontierMath Tier 4 | 2% | — |
| GPQA Diamond | 78% | 96% |
| Humanity's Last Exam | 14% | 55% |
| LiveCodeBench | 70% | — |
| MMLU-Pro | 83% | — |
| SciCode | 38% | 56% |
| Terminal-Bench | 25% | — |
| WebDev Arena | 1340 | 1797 |
| τ²-bench | 70% | — |
| ARC-AGI | — | 99% |
| ARC-AGI-2 | — | 95% |
| SimpleQA Verified | — | 76% |
| WeirdML | — | 93% |
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-4.6 better than GPT-6 Astra?
On Epoch AI's Capabilities Index, GPT-6 Astra scores higher (169) than GLM-4.6 (141). The right pick depends on your task — compare their coding, math, and reasoning scores in the table above.
Which is cheaper, GLM-4.6 or GPT-6 Astra?
GLM-4.6 is cheaper on input tokens at $0.60 per million, versus $10.00 (representative OpenRouter pricing).
Which has a larger context window, GLM-4.6 or GPT-6 Astra?
GPT-6 Astra supports up to 1.1M tokens, compared with 205K for the other.
Which is better for coding, GLM-4.6 or GPT-6 Astra?
Across coding benchmarks like SWE-bench Verified and Terminal-Bench, GPT-6 Astra ranks higher — 95th vs 18th 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.