← comparisons · head to head
Step 5 Preview vs GLM-5.3
GLM-5.3 scores higher than Step 5 Preview on all 3 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, Step 5 Preview is at 29.5 and GLM-5.3 at 46.7 (out of 100).
Scores as published by each board; table composed November 13, 2026.
Get the next launch alert, free →
Leaderboard by leaderboard
| Board | Step 5 Preview | GLM-5.3 | Higher |
|---|---|---|---|
| LMArena Elo (community votes) | 1,572.5 | 1,622.5 | GLM-5.3 |
| Vals AI Vals Index accuracy % · weighted finance + coding tasks | 54.8 | 59.8 | GLM-5.3 |
| Artificial Analysis intelligence index · measured runs only | 28.5 | 31.7 | GLM-5.3 |
Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.
For coding
On the ArtificialWatch coding index, Step 5 Preview is at 26 (#40 of 48) and GLM-5.3 at 50.4 (#20). GLM-5.3 scores higher on both coding boards that rate them.
| Coding board | Step 5 Preview | GLM-5.3 |
|---|---|---|
| LMArena · Coding | 1,481.7 | 1,498.5 |
| Vals Vibe Code Bench | 70.4 | 78.1 |
Step 5 Preview at a glance
- Developer
- StepFun
- Status
- Live since September 20, 2026
Live — Sep 20 · 600B total / ~27B active MoE · 1M ctx · $1.00/$2.70 per 1M, $0.05 cached input · open weights landed Oct 15, as scheduled: FP8 and BF16 checkpoints on Hugging Face and ModelScope, plus an NVFP4 build on Hugging Face (604.3B parameters in the safetensors index; about 650 GB in FP8, 1.2 TB in BF16), under the StepFun Model License 1.0, which adds a 'Powered by StepFun AI' credit past 100M monthly users or $20M monthly revenue and a separate commercial license for device makers and for model-as-a-service firms over $20M a year (license read Oct 15) · aimed at long-horizon agentic work.
StepFun opens Step 5 Preview's weights: 600B total, 27B active, 1M context, under its own license
2026-10-15 · StepFun released the weights of Step 5 Preview on October 15, the date it set when the model went on sale through its API on September 20. FP8 and BF16 checkpoints are on Hugging Face and ModelScope, and an NVFP4 build is on Hugging Face too.
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) · Anthropic research (Sep 29): builds end-to-end exploits near Claude Mythos Preview's rate (ExploitBench 50 of 410 vs 56 of 410), and its safeguards fell to simple bypasses 64-100% of the time · Epoch AI report (Oct 29): built one-click file-reading exploits for all six Firefox releases Sep 17-Oct 26 from published-but-unshipped fixes, about $1,000 each, with no refusals at any provider.
Epoch AI: open-weight GLM 5.3 built working Firefox exploits from security fixes that had not shipped yet, for about $1,000 each
2026-10-30 · An open-weight model can now turn browser security fixes that are public but not yet shipped into working exploits on its own, according to a report Epoch AI published October 29.
Anthropic: open-weights GLM-5.3 nearly matches Claude Mythos Preview at building exploits, and its safeguards are easy to strip
2026-09-29 · Anthropic published research on September 29 testing Z.ai's GLM-5.3, an open-weights model anyone can download, on offensive cyber tasks. Its finding: GLM-5.3 can build working end-to-end exploits at close to the rate of Claude Mythos Preview, the model Anthropic released only to vetted defenders.
Step 5 Preview vs GLM-5.3: quick answers
Which is better, Step 5 Preview or GLM-5.3?
It depends on what you measure. GLM-5.3 scores higher than Step 5 Preview on all 3 public leaderboards that rate both. 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, Step 5 Preview is at 29.5 and GLM-5.3 at 46.7 (out of 100).
Which is newer, Step 5 Preview or GLM-5.3?
Step 5 Preview. It went live on September 20, 2026, 37 days after GLM-5.3 (August 14, 2026).
How do Step 5 Preview and GLM-5.3 compare for coding?
On the ArtificialWatch coding index, Step 5 Preview is at 26 (#40 of 48) and GLM-5.3 at 50.4 (#20). GLM-5.3 scores higher on both coding boards that rate them.
Who makes Step 5 Preview and GLM-5.3?
Step 5 Preview is from StepFun; 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 November 13, 2026). Boards measure different things, so raw scores are only comparable within a row.
More comparisons
Hear when the next one drops. Free.
Free: a Chrome push and an email about 15 minutes after a new model answers on a public API. Members get a text or a phone call the moment a launch is confirmed.
- Free forever
- No card
- Unsubscribe in one click
Also: the bench index · API pricing · the wire