← comparisons · head to head
Qwen 3.8 Max vs GLM-5.3
Of the 6 public leaderboards that rate both, Qwen 3.8 Max scores higher on 3 and GLM-5.3 on 3. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Qwen 3.8 Max is at 45.7 and GLM-5.3 at 42.4 (out of 100).
Scores as published by each board; table composed September 25, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Qwen 3.8 Max | GLM-5.3 | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,671.2 | 1,621.8 | Qwen 3.8 Max |
| LiveBench global average (0-100) | 78.5 | 76.1 | Qwen 3.8 Max |
| SimpleBench AVG@5 % (private set) | 62.5 | 66.2 | GLM-5.3 |
| LLM Stats LLM Stats Score · composite (0-100), their rendered top 15 | 51.5 | 52.1 | GLM-5.3 |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 51.8 | 57 | GLM-5.3 |
| Artificial Analysis intelligence index · measured runs only | 45.4 | 44.8 | Qwen 3.8 Max |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
Qwen 3.8 Max at a glance
- Developer
- Alibaba
- Status
- Live since August 1, 2026
- API price
- $2 input / $6 output per 1M tokens · Alibaba, qwen3.8-max
- Context window
- 1M tokens
Live - flagship since Aug 1 · 2.4T tier listed Aug 12.
Qwen3.8-Max quietly lost its preview label — Alibaba is now serving it as the flagship
2026-08-03 · Alibaba is serving Qwen3.8-Max on chat.qwen.ai under the plain id `qwen3.8-max`. The preview suffix is gone.
GLM-5.3 at a glance
- Developer
- Zhipu AI
- Status
- Live since August 14, 2026
- API price
- $1.40 input / $4.40 output per 1M tokens · Z.AI, glm-5.3
- Context window
- 1M tokens
Live - same 743B base as 5.2, every gain from post-training · tops CyberGym · open weights on Hugging Face (zai-org/GLM-5.3, 141 safetensors files, public when we read it Sep 25; repo created Aug 25).
GLM-5.3 tops CyberGym and trails the frontier on exploitation — and we missed it because the sweep had no eyes on models.dev
2026-08-14 · Z.ai shipped GLM-5.3 today, and we did not catch it. The entry was armed and the pattern was right — the sweep simply had no source that carried the id. That is now fixed, and the fix is the more useful half of this post.
Qwen 3.8 Max vs GLM-5.3: quick answers
Which is better, Qwen 3.8 Max or GLM-5.3?
It depends on what you measure. Of the 6 public leaderboards that rate both, Qwen 3.8 Max scores higher on 3 and GLM-5.3 on 3. Qwen 3.8 Max's widest lead is on LiveBench; GLM-5.3's widest lead is on Vals AI. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Qwen 3.8 Max is at 45.7 and GLM-5.3 at 42.4 (out of 100).
Which is newer, Qwen 3.8 Max or GLM-5.3?
GLM-5.3. It went live on August 14, 2026, 13 days after Qwen 3.8 Max (August 1, 2026).
Which is cheaper, Qwen 3.8 Max or GLM-5.3?
GLM-5.3 is cheaper on both input and output. On each vendor's own API, Qwen 3.8 Max is $2 input / $6 output per million tokens and GLM-5.3 is $1.40 input / $4.40 output per million tokens. Prices as published in the models.dev catalog, as of 2026-09-25.
Which has the bigger context window, Qwen 3.8 Max or GLM-5.3?
Neither. Both take 1M tokens.
Who makes Qwen 3.8 Max and GLM-5.3?
Qwen 3.8 Max is from Alibaba; GLM-5.3 is from Zhipu AI.
Where do these numbers come from?
Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed September 25, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear the minute the next one drops. Free.
A free Chrome push the moment a new model answers on a public API, an email about 15 minutes later. Texts or a phone call on paid plans.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · the wire