Compare / GLM-4.7-Flash vs Nemotron 3.5 Lightning
GLM-4.7-Flash vs Nemotron 3.5 Lightning
Updated November 2026
Verdict
GLM-4.7-Flash scores higher on the Small LM Index: 66.1 vs 63.6, although their likely ranges overlap, so the lead is not certain. On the 2 benchmarks both labs report, GLM-4.7-Flash wins 1 and Nemotron 3.5 Lightning wins 1. GLM-4.7-Flash is smaller: it needs about 20.4 GB of memory at 4-bit, against 22.4 GB for Nemotron 3.5 Lightning. Nemotron 3.5 Lightning is cheaper through an API: $0.049 per million tokens against $0.15.
Pick GLM-4.7-Flash if…
- you want the strongest model overall
- you mostly write code
- you have limited memory (about 20.4 GB at 4-bit)
- you need a permissive license (MIT)
- you want the more widely used model (more quantized builds and community support)
Pick Nemotron 3.5 Lightning if…
- API cost matters most
- you work with long documents
Specifications
| GLM-4.7-Flash | Nemotron 3.5 Lightning | |
|---|---|---|
| Small LM Index | 66.1 (likely 63–70) | 63.6 (likely 55–71) |
| Lab | Z.ai (GLM) · China | NVIDIA · United States |
| Released | 2026-01-19 | 2026-08-11 |
| Parameters | 31B (3B active, MoE) | 31.6B (3.6B active, MoE) |
| Memory at 4-bit | ~20.4 GB | ~22.4 GB |
| Context window | 200K tokens | 1M tokens |
| Input | text | text |
| Reasoning | Always thinks | Always thinks |
| License | MIT | OpenMDW-1.1 |
| API price / 1M tokens | $0.15 ($0.061 in, $0.40 out) | $0.049 ($0.025 in, $0.12 out) |
| Hugging Face downloads (30 days) | 956.4K | — |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | GLM-4.7-Flash | Nemotron 3.5 Lightning |
|---|---|---|
| MMLU-Pro Knowledge | ≈ 82 | 81.9 |
| GPQA Diamond Knowledge | 75.2 | 75.4 |
| Humanity's Last Exam Reasoning | 14.4 | ≈ 13 |
| AIME Math | 91.6 | ≈ 88 |
| LiveCodeBench Coding | 64.0 | ≈ 73 |
| SWE-bench Verified Coding | 59.2 | 51.6 |
| τ²-Bench Agentic | 79.5 | — |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, GLM-4.7-Flash or Nemotron 3.5 Lightning?
GLM-4.7-Flash scores higher on the Small LM Index: 66.1 vs 63.6, although their likely ranges overlap, so the lead is not certain. On the 2 benchmarks both labs report, GLM-4.7-Flash wins 1 and Nemotron 3.5 Lightning wins 1.
Which is cheaper to run?
Nemotron 3.5 Lightning is cheaper through an API: $0.049 per million tokens against $0.15. GLM-4.7-Flash is smaller: it needs about 20.4 GB of memory at 4-bit, against 22.4 GB for Nemotron 3.5 Lightning.
Which has the longer context window?
Nemotron 3.5 Lightning has the longer context window: 1M tokens against 200K.
Can I use GLM-4.7-Flash and Nemotron 3.5 Lightning commercially?
GLM-4.7-Flash is released under MIT and Nemotron 3.5 Lightning under OpenMDW-1.1. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.