Cheaper overall
Nemotron-3.5 Super-120b-a12b
82% lower blended rate
Higher benchmark scores
GLM 5
leads on 9 of 11 figures
Bigger context window
Nemotron-3.5 Super-120b-a12b
1,048,576 vs 204,800 tokens
Cheaper cached input
Nemotron-3.5 Super-120b-a12b
$0.04 vs $0.20, 80% less
Where each one wins
Nemotron-3.5 Super-120b-a12b
- Cheaper input tokens $0.20 vs $1.00, 80% less
- Cheaper output tokens $0.50 vs $3.20, 84% less
- Cheaper cached input $0.04 vs $0.20, 80% less
- Cheaper on all four workloads
- Larger context window 1,048,576 tokens
- Longer maximum output 262,144 tokens
- Higher expert-exam performance (Humanity's Last Exam) 30.7 vs 29.3
- Higher physics research reasoning (CritPt) 10.6 vs 2
GLM 5
- Higher overall intelligence (Intelligence Index) 27.9 vs 26.5
- Higher long-context reasoning (AA-LCR) 75.7 vs 69
- Higher factual accuracy (Omniscience Accuracy) 26.3 vs 23.3
- Ahead on 6 more benchmark figures
What four workloads cost
One run, and the same run a thousand times.
Nemotron-3.5 Super-120b-a12b is cheaper on all four workloads, by much the same margin each time — about 5.4 times, from $0.0005 against $0.0026 on a chat turn to $0.0390 against $0.2048 on a long document.
| Workload | Nemotron-3.5 Super-120b-a12b | GLM 5 | ×1,000 | Difference |
|---|---|---|---|---|
| Chat turn 1,000 in / 500 out | $0.0005 | $0.0026 | $0.4500 / $2.60 | Nemotron-3.5 Super-120b-a12b is 83% cheaper |
| RAG answer 10,000 in / 800 out | $0.0024 | $0.0126 | $2.40 / $12.56 | Nemotron-3.5 Super-120b-a12b is 81% cheaper |
| Agent loop 32,000 in / 700 out × 20 calls | $0.0390 | $0.2048 | $39.00 / $204.80 | Nemotron-3.5 Super-120b-a12b is 81% cheaper |
| Long document 400,000 in / 3,000 out | GLM 5's context window holds 204,800 tokens, so a 400,000-token prompt does not fit. | |||
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 | Difference |
|---|---|---|---|---|
| Any prompt length | Input | $0.20 | $1.00 | Nemotron-3.5 Super-120b-a12b is 80% cheaper |
| Any prompt length | Cached input | $0.04 | $0.20 | Nemotron-3.5 Super-120b-a12b is 80% cheaper |
| Any prompt length | Output | $0.50 | $3.20 | Nemotron-3.5 Super-120b-a12b is 84% cheaper |
Blended: Nemotron-3.5 Super-120b-a12b $0.275, GLM 5 $1.55 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 by Z.ai. Standard tier, pay-as-you-go.
Benchmarks
They share 11 figures: Nemotron-3.5 Super-120b-a12b leads on 2, GLM 5 on 9. The widest gap is 122 points, on Gamedev Elo.
Overall intelligence
Intelligence Index — Overall intelligence across reasoning, knowledge & math evals
GLM 5 ahead by 1.4
Expert-exam performance
Humanity's Last Exam — Expert-level questions across many academic domains
Nemotron-3.5 Super-120b-a12b ahead by 1.4
Long-context reasoning
AA-LCR — Long-context reasoning across large inputs
GLM 5 ahead by 6.7
Physics research reasoning
CritPt — Unpublished physics research reasoning problems
Nemotron-3.5 Super-120b-a12b ahead by 8.6
Factual accuracy
Omniscience Accuracy — Breadth of factual knowledge across domains
GLM 5 ahead by 3
Answer reliability
Omniscience Non-Hallucination — How reliably the model avoids fabricated answers
GLM 5 ahead by 0.5
3d Elo
Design Arena head-to-head rating in the 3d category
GLM 5 ahead by 109
Codecategories Elo
Design Arena head-to-head rating in the codecategories category
GLM 5 ahead by 92
Gamedev Elo
Design Arena head-to-head rating in the gamedev category
GLM 5 ahead by 122
Uicomponent Elo
Design Arena head-to-head rating in the uicomponent category
GLM 5 ahead by 76
Website Elo
Design Arena head-to-head rating in the website category
GLM 5 ahead by 78
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 843,776 more input tokens in one request. Nemotron-3.5 Super-120b-a12b also takes audio, file, image and video. Only Nemotron-3.5 Super-120b-a12b lists code execution; only GLM 5 lists prompt caching.
| Specification | Nemotron-3.5 Super-120b-a12b | GLM 5 |
|---|---|---|
| Context window | 1,048,576 tokens | 204,800 tokens |
| Max output | 262,144 tokens | 128,000 tokens |
| Takes in | Text, audio, image, video, file | Text |
| Puts out | Text | Text |
| Released | 15 Oct 2026 | 11 Feb 2026 |
| Status | Active | Active |
| Sold by | 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 | Not listed |
| Computer use | Not listed | Not listed |
| Open weights | Yes | Yes |
| Reasoning | Yes | Yes |
FAQs
- Is Nemotron-3.5 Super-120b-a12b cheaper than GLM 5?
- Yes. A 1,000-token prompt with a 500-token reply costs $0.0005 on Nemotron-3.5 Super-120b-a12b and $0.0026 on GLM 5, and the same model is cheaper on every workload on this page.
- How much do Nemotron-3.5 Super-120b-a12b and GLM 5 cost per 1M tokens?
- Nemotron-3.5 Super-120b-a12b costs $0.20 for input and $0.50 for output. GLM 5 costs $1.00 and $3.20. Standard pay-as-you-go rates, as of 16 Oct 2026.
- Which is better, Nemotron-3.5 Super-120b-a12b or GLM 5?
- On published benchmarks, GLM 5. It leads on 9 of the 11 figures both models report, including overall intelligence (Intelligence Index), where it scores 27.9 against 26.5.
- Does Nemotron-3.5 Super-120b-a12b or GLM 5 have a bigger context window?
- Nemotron-3.5 Super-120b-a12b, at 1,048,576 tokens against 204,800. That is 843,776 more input tokens in a single request.
Explore these models
Perplexity · 1,048,576-token context