GLM-5.3 vs Qwen3.8 Max
Published test results, prices, limits and features, side by side. Share the link to show someone exactly this comparison.
- GLM-5.3Z.ai
- Qwen3.8 MaxAlibaba
At a glance
Capability index
GLM-5.3155.6
Qwen3.8 Max156.4
Qwen3.8 Max is 0.8 points higher.
Price per 1M tokens
GLM-5.3$2.15
Qwen3.8 Max$3.00
GLM-5.3 is 28% cheaper.
Context window
GLM-5.31M tokens
Qwen3.8 Max1M tokens
They take in about the same.
Released
GLM-5.3Aug 14, 2026
Qwen3.8 MaxAug 3, 2026
GLM-5.3 is 11 days newer.
Where each scores higher
On the 22 tests both have taken, each on its own scale. A gap of a point or two can sit within a test’s margin of error.
GLM-5.3
- LiveBench coding+6.1 points
- DeepSWE+11.5 points
- LiveBench language+0.2 points
- Arena instruction following+2 points
Qwen3.8 Max
- LiveBench overall+2.3 points
- Arena text+3 points
- Arena WebDev+48 points
- Arena coding+3 points
- LiveBench mathematics+3.4 points
- Mock AIME 2024–2025+8.3 points
- FrontierMath Tiers 1–3+6.0 points
- FrontierMath Tier 4+17.1 points
- Arena math+4 points
- SimpleQA Verified+4.8 points
- LiveBench agentic coding+3.7 points
- LiveBench instructions+4.8 points
- Arena creative writing+14 points
- LiveBench data analysis+8.2 points
- LiveBench reasoning+2.4 points
- GPQA Diamond+1.8 points
- Chess puzzles+8.0 points
Level on Arena hard prompts.
1 more test has results for only one of them; the table below lists every result.
Everything side by side
| Measure | ||
|---|---|---|
| Model | ||
| Maker | Z.ai | Alibaba |
| Sold here by | Z.AI | Alibaba |
| API model ID | glm-5.3 | qwen3.8-max |
| Released | Aug 14, 2026 | Aug 3, 2026 |
| Knowledge cutoff | Not reported | Not reported |
| Weights | Open: downloadable | Closed: hosted access only |
| Developer’s country | China | China |
| Hosts selling it | 75including Z.ai directly | 36including Alibaba directly |
| Test results | ||
| Capability index | 155.6#27 of 274 | 156.4 (best of these models)#22 of 274 |
| LiveBench overall | 76.1%#32 of 66 | 78.5% (best of these models)#17 of 66 |
| Arena text | 1479#27 of 413 | 1482 (best of these models)#23 of 413 |
| LiveBench coding | 79.0% (best of these models)#26 of 66 | 72.9%#52 of 66 |
| Arena WebDev | 1623#20 of 138 | 1671 (best of these models)#10 of 138 |
| Arena coding | 1521#34 of 408 | 1524 (best of these models)#28 of 408 |
| LiveBench mathematics | 87.9%#43 of 66 | 91.3% (best of these models)#27 of 66 |
| Mock AIME 2024–2025 | 91.1%#65 of 297 | 99.4% (best of these models)#14 of 297 |
| FrontierMath Tiers 1–3 | 68.8%#25 of 114 | 74.7% (best of these models)#18 of 114 |
| FrontierMath Tier 4 | 29.3%#36 of 70 | 46.3% (best of these models)#25 of 70 |
| Arena math | 1494#20 of 396 | 1498 (best of these models)#18 of 396 |
| SimpleQA Verified | 41.0%#44 of 86 | 45.8% (best of these models)#37 of 86 |
| LiveBench agentic coding | 60.9%#15 of 66 | 64.7% (best of these models)#7 of 66 |
| DeepSWE | 69.0% (best of these models)#16 of 69 | 57.5%#36 of 69 |
| CursorBench | 42.6%#20 of 62 | Not tested |
| LiveBench language | 79.9% (best of these models)#31 of 66 | 79.7%#34 of 66 |
| LiveBench instructions | 69.3%#33 of 66 | 74.1% (best of these models)#13 of 66 |
| Arena creative writing | 1454#34 of 411 | 1468 (best of these models)#20 of 411 |
| Arena instruction following | 1476 (best of these models)#25 of 413 | 1474#31 of 413 |
| LiveBench data analysis | 70.2%#51 of 66 | 78.4% (best of these models)#24 of 66 |
| LiveBench reasoning | 85.8%#35 of 66 | 88.2% (best of these models)#23 of 66 |
| GPQA Diamond | 90.9%#34 of 319 | 92.7% (best of these models)#24 of 319 |
| Chess puzzles | 21.0%#80 of 227 | 29.0% (best of these models)#54 of 227 |
| Arena hard prompts | 1503#25 of 413 | 1503#27 of 413 |
| Price per million tokens | ||
| Input | $1.40 (best of these models) | $2.00 |
| Output | $4.40 (best of these models) | $6.00 |
| Blended, 3 input to 1 output | $2.15 (best of these models) | $3.00 |
| Cached input | $0.26 | $0.25 (best of these models) |
| Writing to the cache | Free (best of these models) | $2.50 |
| The maker’s own price | This listing | This listing |
| Limits | ||
| Context window | 1M tokens | 1M tokens |
| Max input | 1M tokens (best of these models) | 991K tokens |
| Max output | 131.1K tokens | 131.1K tokens |
| Features | ||
| Reads | text | images, PDFs, text and video |
| Produces | text | text |
| Reasoning | Yeseffort low, high, max; can be switched off; thinking budget can be set | Yeseffort low, medium, xhigh; can be switched off; thinking budget can be set |
| Tool calling | Yes | Yes |
| Structured output | Yes, such as JSON | Yes, such as JSON |
| File attachments | No | Yes |
| Temperature setting | Supported | Supported |
Bold marks the better value in each row. Prices are each model’s own list price, or the middle price across hosts when the maker does not sell it, blended as three input tokens for every output token. Test results as published by LiveBench (Apache-2.0), Epoch AI (CC BY 4.0), Datacurve DeepSWE, compiled by Epoch AI (CC BY 4.0), Cursor CursorBench, compiled by Epoch AI (CC BY 4.0), Arena (CC BY 4.0); model details and prices from models.dev (MIT). Confirm pricing with the provider before use.