GLM-5.3
As of 14 Sep 2026, GLM-5.3 is the RightSignal pick for best open-weight LLM.
GLM-5.3 (max) tops Artificial Analysis's open-weights table on Intelligence Index v4.3 with 45, one point clear of Kimi K3 (max) on 44, and the weights have been on Hugging Face since 28 August.
current reign
held off
reigns
Why GLM-5.3 is the pick
- GLM-5.3 (max) tops Artificial Analysis's open-weights table on Intelligence Index v4.3 with 45, one point clear of Kimi K3 (max) on 44, and the weights have been on Hugging Face since 28 August.
- On cost the two are effectively level — about $2.01 per Index task against K3's $2.00 — so the separator is throughput, with GLM-5.3 measured at roughly 66 output tokens per second against K3's 37.
- It ships under Z.ai's own glm-5.3 licence rather than a standard open one, and it takes text-only inputs.
Evidence
The sources behind this title’s record.
- artificialanalysis.ai/leaderboards/models
- artificialanalysis.ai/models/open-source
- huggingface.co/zai-org/GLM-5.3
- huggingface.co/moonshotai/Kimi-K3
- huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
- artificialanalysis.ai/models
- huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
- huggingface.co/orcarouter/Qwen3.8-Flash-Next-Uncensored-GGUF
Vendor numbers are treated as claims until independently reproduced — how we judge. Structured benchmark comparisons are on the roadmap.
Caveats & challengers
- GLM-5.3 ships under Z.ai's own glm-5.3 licence rather than MIT or Apache-2.0, and providers above $10bn in revenue need a Z.ai security review before commercial use, so read the LICENSE file in the repo before deploying.
- The weights landed on Hugging Face on 28 August, about two weeks after the 14 August API launch, and the reign here is dated from 10 September.
- Artificial Analysis moved to Intelligence Index v4.3 on 7 September, so any v4.2 scores or cost-per-task figures are no longer comparable.
At a glance
- Title
- Best open-weight LLM
- Licence
- glm-5.3 licence (Z.ai custom)
- Pick since
- 10 Sep 2026
- Last reviewed
- 13 Sep 2026
- Title holders to date
- 13
- Official page
- huggingface.co/zai-org/GLM-5.3
Title history
Every change, on the record.
GLM-5.3 (max) tops Artificial Analysis's open-weights table on Intelligence Index v4.3 with 45, one point clear of Kimi K3 (max) on 44, and the weights have been on Hugging Face since 28 August.
4 daysas pick
The world's first open 3T-class model (2.8T total, 104B active), trading blows with Claude Fable 5 and GPT-5.6 Sol rather than with other…
45 daysas pick
A 753B MIT-licensed release that retook the lead from DeepSeek-V4-Pro — the model Kimi K3 later had to benchmark itself against.
41 daysas pick
1.6T parameters with 49B active and a 1M context, explicitly claiming the best-open-model title.
55 daysas pick
A 744B/40B-active model claiming best-in-class among all open models on reasoning, coding and agentic work.
70 daysas pick
Set state of the art on Humanity's Last Exam and BrowseComp — the first open model to top a headline frontier benchmark outright.
97 daysas pick
A 1T-parameter MoE with 32B active claiming state of the art on agentic and coding benchmarks against Claude Opus 4 and GPT-4.1 — not mer…
118 daysas pick
Put open weights on the reasoning curve for the first time, under MIT, and held the crown through the whole first half of 2025.
172 daysas pick
A 671B MoE that beat the 405B at a fraction of the serving cost, and flipped local-LLM consensus to the Chinese labs essentially overnight.
25 daysas pick
The first open release that genuinely traded blows with GPT-4-class closed models — the reference open model for the rest of 2024.
156 daysas pick
Jumped clear of Mixtral on every reasoning benchmark and landed high in the overall LMArena table, not just the open slice.
96 daysas pick
The first open MoE to beat Llama 2 70B while activating only ~13B parameters — and it did it under Apache-2.0.
129 daysas pick
as pick