Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
GLM-5.3-Flash
GLM-5.3-Flash is an open-weight model from Z.ai, released Aug 26, 2026. It ranks #29 of 351 on the LMArena text leaderboard with a rating of 1472, and #22 of 27 on the Vals Index with 50.86%. It costs $0.15 per million input tokens and $0.50 per million output tokens, with a 1M-token context window.
- Developer
- Z.ai (Zhipu AI)
- Released
- Aug 26, 2026
- Context window
- 1M
- Price in / out, per 1M tokens
- $0.15 / $0.50
- Weights
- Open · MIT
- Inputs
- Text, Images, Video
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 6.4M
- Hugging Face likes
- 2.9K
The rating LMArena published at each update since Aug 27, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| Vals IndexVals AI | 50.86% | 22 / 27 | $1.13 | |
| Terminal-Bench 4.0Coding | 37.37% | 16 / 55 | $1.22 | |
| SWE-benchCoding | 92.00% | 10 / 85 | $0.02 | |
| Vibe Code BenchCoding | 30.76% | 74 / 115 | $2.35 | |
| Code MigrationCoding | 51.65% | 15 / 28 | $4.48 | |
| LiveCodeBenchCoding | 80.51% | 69 / 143 | $0.075 / $0.25 | |
| Finance AgentFinance | 60.59% | 18 / 31 | $0.07 | |
| Finance IndexFinance | 55.83% | 20 / 31 | $0.31 | |
| Tax Agent BenchFinance | 31.55% | 24 / 76 | $0.14 | |
| Legal IndexLaw | 71.05% | 12 / 28 | $0.19 | |
| Legal Research BenchLaw | 45.19% | 19 / 85 | $0.12 | |
| GPQA DiamondReasoning | 86.36% | 43 / 138 | $0.075 / $0.25 | |
| MMLU-ProReasoning | 86.06% | 49 / 138 | $0.075 / $0.25 | |
| MMMUReasoning | 86.01% | 23 / 93 | $0.075 / $0.25 | |
| Terminal-Bench ScienceReasoning | 2.86% | 34 / 42 | $0.52 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1472 | 29 / 351 | 38.4K |
| CodingLMArena | 1508 | 15 / 346 | 9.7K |
| MathLMArena | 1502 | 14 / 339 | 1.9K |
| Creative writingLMArena | 1441 | 44 / 349 | 8.2K |
| Instruction followingLMArena | 1479 | 20 / 351 | 13.3K |
| Hard promptsLMArena | 1491 | 19 / 351 | 24.4K |
| Multi-turnLMArena | 1471 | 35 / 349 | 5.9K |
| Long queriesLMArena | 1482 | 25 / 330 | 16.9K |
| ExpertLMArena | 1512 | 20 / 305 | 3.9K |
| Legal and governmentIndustries | 1475 | 37 / 325 | 3.1K |
| Medicine and healthcareIndustries | 1476 | 31 / 325 | 2.6K |
| Business and financeIndustries | 1461 | 32 / 344 | 7K |
| ChineseLanguages | 1531 | 17 / 328 | 3K |
| SpanishLanguages | 1472 | 26 / 249 | 1.5K |
| GermanLanguages | 1457 | 43 / 261 | 654 |
| FrenchLanguages | 1489 | 25 / 252 | 1.4K |
| JapaneseLanguages | 1442 | 39 / 236 | 729 |
| WebDevLMArena | 1608 | 30 / 124 | 19.7K |
| VisionLMArena | 1294 | 24 / 146 | 16.3K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare GLM-5.3-Flash
Z.ai (Zhipu AI)
A Tsinghua spin-out that builds the GLM family of open bilingual models. Founded 2019, based in Beijing. z.ai
Questions
Who makes GLM-5.3-Flash?
GLM-5.3-Flash is made by Z.ai (Zhipu AI), founded 2019 and based in Beijing.
How much does GLM-5.3-Flash cost?
$0.15 per million input tokens and $0.50 per million output tokens, at its provider’s list price.
What is GLM-5.3-Flash’s context window?
1M tokens (1,048,576).
How does GLM-5.3-Flash rank?
#29 of 351 on LMArena’s text leaderboard, rated 1472 (95% interval 1468–1477) from 38,359 votes, as of Oct 22, 2026.
Is GLM-5.3-Flash open source?
GLM-5.3-Flash has open weights under the MIT license, downloadable from Hugging Face (zai-org/GLM-5.3-Flash).