GLM 5.3 vs Qwen3.8 Max (0902)
GLM 5.3 is from Z.ai. Qwen3.8 Max (0902) is from Qwen. GLM 5.3 costs $1.40 per million output tokens. Qwen3.8 Max (0902) costs $6.00. Qwen3.8 Max (0902) leads on the Epoch Capabilities Index: GLM 5.3 scores 156.2 and Qwen3.8 Max (0902) scores 156.2. A typical request, about 1,000 words in and 400 words out, costs $0.0008 on GLM 5.3 and $0.0056 on Qwen3.8 Max (0902).
Prices updated . Benchmarks updated .
| GLM 5.3 | Qwen3.8 Max (0902) | |
|---|---|---|
| Lab | Z.ai | Qwen |
| You send / 1M | $0.070 | $2.00 |
| It replies / 1M | $1.40 | $6.00 |
| Context | 1M | 984K |
| Launched | 2026-08-14 | 2026-09-02 |
| Weights | Open weights, restricted | Closed |
| Typical request | $0.0008 | $0.0056 |
| ECI | 156.2 | 156.2 |
| GPQA | 90.9% | 92.3% |
| ARC-AGI-2 | n/a | n/a |
| HLE | n/a | n/a |
| AIME | 91.1% | 100.0% |
| SimpleQA | 41.0% | 47.3% |
| CritPt | 19.1% | 17.7% |
| Arena | 1,474 | n/a |
| Arena web | 1,623 | 1,676 |
Which is cheaper?
GLM 5.3 costs less to run: $1.40 per million output tokens, against $6.00 for Qwen3.8 Max (0902). Input tokens are $0.070 per million for GLM 5.3 and $2.00 per million for Qwen3.8 Max (0902). A typical request, about 1,000 words in and 400 words out, costs $0.0008 on GLM 5.3 and $0.0056 on Qwen3.8 Max (0902).
Which scores higher?
Qwen3.8 Max (0902) scores higher on Epoch Capabilities Index: 156.2 against 156.2 for GLM 5.3. That index is an independent composite from Epoch AI. Lab-reported scores are kept off this comparison. Context windows are 1M and 984K. Prices are US dollars per million tokens at current public rates.
Verdict
Qwen3.8 Max (0902) scores higher on Epoch Capabilities Index (156.2 vs 156.2). GLM 5.3 costs less at $1.40 per million output tokens. Context is 1M for GLM 5.3 and 984K for Qwen3.8 Max (0902). Use the model pages for every score on file, including lab-reported numbers.
FAQ
Which is cheaper, GLM 5.3 vs Qwen3.8 Max (0902)?
GLM 5.3 costs less to run: $1.40 per million output tokens, against $6.00 for Qwen3.8 Max (0902). Input tokens are $0.070 per million for GLM 5.3 and $2.00 per million for Qwen3.8 Max (0902). A typical request, about 1,000 words in and 400 words out, costs $0.0008 on GLM 5.3 and $0.0056 on Qwen3.8 Max (0902).
Which scores higher, GLM 5.3 vs Qwen3.8 Max (0902)?
Qwen3.8 Max (0902) scores higher on Epoch Capabilities Index: 156.2 against 156.2 for GLM 5.3. That index is an independent composite from Epoch AI. Lab-reported scores are kept off this comparison. Context windows are 1M and 984K. Prices are US dollars per million tokens at current public rates.
What is the verdict for GLM 5.3 vs Qwen3.8 Max (0902)?
Qwen3.8 Max (0902) scores higher on Epoch Capabilities Index (156.2 vs 156.2). GLM 5.3 costs less at $1.40 per million output tokens. Context is 1M for GLM 5.3 and 984K for Qwen3.8 Max (0902). Use the model pages for every score on file, including lab-reported numbers.
Open this pair in the comparison view
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.