Cheaper overall
GLM 5.3 Flash
14% lower blended rate
Higher benchmark scores
GLM 5.3 Flash
leads on 13 of 13 figures
Bigger context window
Nemotron-3.5 Super-120b-a12b
1,048,576 vs 1,000,000 tokens
Cheaper cached input
GLM 5.3 Flash
$0.03 vs $0.04, 25% less
Where each one wins
Nemotron-3.5 Super-120b-a12b
- Larger context window 1,048,576 tokens
- Longer maximum output 262,144 tokens
GLM 5.3 Flash
- Cheaper input tokens $0.15 vs $0.20, 25% less
- Cheaper cached input $0.03 vs $0.04, 25% less
- Cheaper on all four workloads
- Higher overall intelligence (Intelligence Index) 41.8 vs 26.5
- Higher expert-exam performance (Humanity's Last Exam) 39.9 vs 30.7
- Higher long-context reasoning (AA-LCR) 80 vs 69
- Ahead on 10 more benchmark figures
What four workloads cost
One run, and the same run a thousand times.
GLM 5.3 Flash is cheaper on all four workloads, by much the same margin each time — about 1.2 times, from $0.0004 against $0.0005 on a chat turn to $0.0615 against $0.0815 on a long document.
| Workload | Nemotron-3.5 Super-120b-a12b | GLM 5.3 Flash | ×1,000 | Difference |
|---|---|---|---|---|
| Chat turn 1,000 in / 500 out | $0.0005 | $0.0004 | $0.4500 / $0.4000 | GLM 5.3 Flash is 11% cheaper |
| RAG answer 10,000 in / 800 out | $0.0024 | $0.0019 | $2.40 / $1.90 | GLM 5.3 Flash is 21% cheaper |
| Agent loop 32,000 in / 700 out × 20 calls | $0.0390 | $0.0310 | $39.00 / $31.00 | GLM 5.3 Flash is 21% cheaper |
| Long document 400,000 in / 3,000 out | $0.0815 | $0.0615 | $81.50 / $61.50 | GLM 5.3 Flash is 25% cheaper |
Price per 1M tokens
Neither model changes its rate with prompt length, so these rates apply to every request.
| Context band | Price | Nemotron-3.5 Super-120b-a12b | GLM 5.3 Flash | Difference |
|---|---|---|---|---|
| Any prompt length | Input | $0.20 | $0.15 | GLM 5.3 Flash is 25% cheaper |
| Any prompt length | Cached input | $0.04 | $0.03 | GLM 5.3 Flash is 25% cheaper |
| Any prompt length | Output | $0.50 | $0.50 | Same |
Blended: Nemotron-3.5 Super-120b-a12b $0.275, GLM 5.3 Flash $0.2375 per 1M — one rate at 3:1 input to output, for comparing two models at a glance.
Nemotron-3.5 Super-120b-a12b priced by Perplexity, GLM 5.3 Flash by Z.ai. Standard tier, pay-as-you-go.
Benchmarks
GLM 5.3 Flash leads on all 13 figures, furthest ahead on 3d Elo, by 196 points.
Overall intelligence
Intelligence Index — Overall intelligence across reasoning, knowledge & math evals
GLM 5.3 Flash ahead by 15.3
Expert-exam performance
Humanity's Last Exam — Expert-level questions across many academic domains
GLM 5.3 Flash ahead by 9.2
Long-context reasoning
AA-LCR — Long-context reasoning across large inputs
GLM 5.3 Flash ahead by 11
Scientific coding
SciCode — Research-level scientific coding tasks
GLM 5.3 Flash ahead by 3.8
Physics research reasoning
CritPt — Unpublished physics research reasoning problems
GLM 5.3 Flash ahead by 4.8
Real-world task performance
GDPval — Economically valuable, real-world knowledge work
GLM 5.3 Flash ahead by 24
Factual accuracy
Omniscience Accuracy — Breadth of factual knowledge across domains
GLM 5.3 Flash ahead by 4.2
Answer reliability
Omniscience Non-Hallucination — How reliably the model avoids fabricated answers
GLM 5.3 Flash ahead by 8.2
3d Elo
Design Arena head-to-head rating in the 3d category
GLM 5.3 Flash ahead by 196
Codecategories Elo
Design Arena head-to-head rating in the codecategories category
GLM 5.3 Flash ahead by 126
Gamedev Elo
Design Arena head-to-head rating in the gamedev category
GLM 5.3 Flash ahead by 163
Uicomponent Elo
Design Arena head-to-head rating in the uicomponent category
GLM 5.3 Flash ahead by 159
Website Elo
Design Arena head-to-head rating in the website category
GLM 5.3 Flash ahead by 101
Each figure is that model's best published run, with the effort level named beside it — where these scores come from.
Specifications
Nemotron-3.5 Super-120b-a12b holds 48,576 more input tokens in one request. Nemotron-3.5 Super-120b-a12b also takes audio. Only GLM 5.3 Flash lists prompt caching and computer use.
| Specification | Nemotron-3.5 Super-120b-a12b | GLM 5.3 Flash |
|---|---|---|
| Context window | 1,048,576 tokens | 1,000,000 tokens |
| Max output | 262,144 tokens | 128,000 tokens |
| Takes in | Text, audio, image, video, file | Text, image, video, file |
| Puts out | Text | Text |
| Released | 15 Oct 2026 | 26 Aug 2026 |
| Status | Active | Active |
| Sold by | Perplexity | Perplexity, Z.ai |
| Tool use | Yes | Yes |
| Structured outputs | Yes | Yes |
| Web search | Not listed | Not listed |
| Prompt caching | Not listed | Yes |
| Code execution | Yes | Yes |
| Computer use | Not listed | Yes |
| Open weights | Yes | Yes |
| Reasoning | Yes | Yes |
FAQs
- Is Nemotron-3.5 Super-120b-a12b cheaper than GLM 5.3 Flash?
- No — the other way round. A 1,000-token prompt with a 500-token reply costs $0.0005 on Nemotron-3.5 Super-120b-a12b and $0.0004 on GLM 5.3 Flash, and the same model is cheaper on every workload on this page.
- How much do Nemotron-3.5 Super-120b-a12b and GLM 5.3 Flash cost per 1M tokens?
- Nemotron-3.5 Super-120b-a12b costs $0.20 for input and $0.50 for output. GLM 5.3 Flash costs $0.15 and $0.50. Standard pay-as-you-go rates, as of 16 Oct 2026.
- Which is better, Nemotron-3.5 Super-120b-a12b or GLM 5.3 Flash?
- On published benchmarks, GLM 5.3 Flash. It leads on 13 of the 13 figures both models report, including overall intelligence (Intelligence Index), where it scores 41.8 against 26.5.
- Does Nemotron-3.5 Super-120b-a12b or GLM 5.3 Flash have a bigger context window?
- Nemotron-3.5 Super-120b-a12b, at 1,048,576 tokens against 1,000,000. That is 48,576 more input tokens in a single request.
Explore these models
Perplexity · 1,048,576-token context