Compare · ModelsLive · 2 picked · head to head
GLM 4.5 vs Step 3.5 Flash
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Step 3.5 Flash wins on 6/7 benchmarks
Step 3.5 Flash wins 6 of 7 shared benchmarks. Leads in math · knowledge · language.
Category leads
arena·GLM 4.5math·Step 3.5 Flashknowledge·Step 3.5 Flashlanguage·Step 3.5 Flashcoding·Step 3.5 Flash
Hype vs Reality
Attention vs performance
GLM 4.5
#18 by perf·no signal
Step 3.5 Flash
#7 by perf·#11 by attention
Best value
Step 3.5 Flash
7.8x better value than GLM 4.5
GLM 4.5
49.4 pts/$
$1.40/M
Step 3.5 Flash
384.5 pts/$
$0.20/M
Vendor risk
Mixed exposure
One or more vendors flagged
z-ai
private · undisclosed
StepFun
$5.0B·Tier 1
Head to head
7 benchmarks · 2 models
GLM 4.5Step 3.5 Flash
Chatbot Arena Elo · Overall
GLM 4.5 leads by +19.5
GLM 4.5
1410.9
Step 3.5 Flash
1391.4
OpenCompass · AIME2025
Step 3.5 Flash leads by +9.9
GLM 4.5
85.8
Step 3.5 Flash
95.7
OpenCompass · GPQA-Diamond
Step 3.5 Flash leads by +4.2
GLM 4.5
79.5
Step 3.5 Flash
83.7
OpenCompass · HLE
Step 3.5 Flash leads by +4.7
GLM 4.5
16.9
Step 3.5 Flash
21.6
OpenCompass · IFEval
Step 3.5 Flash leads by +7.8
GLM 4.5
85.4
Step 3.5 Flash
93.2
OpenCompass · LiveCodeBenchV6
Step 3.5 Flash leads by +18.9
GLM 4.5
65.0
Step 3.5 Flash
83.9
OpenCompass · MMLU-Pro
Step 3.5 Flash leads by +0.8
GLM 4.5
82.7
Step 3.5 Flash
83.5
Full benchmark table
| Benchmark | GLM 4.5 | Step 3.5 Flash |
|---|---|---|
Chatbot Arena Elo · Overall | 1410.9 | 1391.4 |
OpenCompass · AIME2025 | 85.8 | 95.7 |
OpenCompass · GPQA-Diamond | 79.5 | 83.7 |
OpenCompass · HLE | 16.9 | 21.6 |
OpenCompass · IFEval | 85.4 | 93.2 |
OpenCompass · LiveCodeBenchV6 | 65.0 | 83.9 |
OpenCompass · MMLU-Pro | 82.7 | 83.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| GLM 4.5 | $0.60 | $2.20 | 131K tokens (~66 books) | $10.00 |
| Step 3.5 Flash | $0.10 | $0.30 | 262K tokens (~131 books) | $1.50 |