GLM-5 vs Nemotron 3 Super-120B-A12B
GLM-5 (2026) and Nemotron 3 Super-120B-A12B (2026) are frontier reasoning models from Zhipu AI and NVIDIA AI. GLM-5 ships a 200k-token context window, while Nemotron 3 Super-120B-A12B ships a 1.05m-token context window. On MMLU PRO, GLM-5 leads by 2.4 pts. On pricing, Nemotron 3 Super-120B-A12B costs $0.09/1M input tokens versus $0.60/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Nemotron 3 Super-120B-A12B is ~567% cheaper at $0.09/1M; pay for GLM-5 only for reasoning depth.
Decision scorecard
Local evidence first| Signal | GLM-5 | Nemotron 3 Super-120B-A12B |
|---|---|---|
| Best for | reasoning-heavy apps, tool-calling agents, and provider-routed production | long-context analysis and provider-routed production |
| Decision fit | Coding, RAG, and Agents | Coding, RAG, and Agents |
| Context window | 200k | 1.05m |
| Cheapest output | $2.08/1M tokens | $0.45/1M tokens |
| Provider routes | 7 tracked | 6 tracked |
| Shared benchmarks | MMLU PRO leader | 6 shared |
Decision tradeoffs
- GLM-5 holds a shared-benchmark lead on MMLU PRO, ahead by 2.4 points.
- GLM-5 has broader tracked provider coverage for fallback and procurement flexibility.
- GLM-5 uniquely exposes Reasoning, Function calling, and Tool use in local model data.
- Local decision data tags GLM-5 for Coding, RAG, and Agents.
- Nemotron 3 Super-120B-A12B has the larger context window for long prompts, retrieval packs, or transcript analysis.
- Nemotron 3 Super-120B-A12B has the lower cheapest tracked output price at $0.45/1M tokens.
- Local decision data tags Nemotron 3 Super-120B-A12B for Coding, RAG, and Agents.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
GLM-5
$1,000
Cheapest tracked route/tier: OpenRouter
Nemotron 3 Super-120B-A12B
$185
Cheapest tracked route/tier: OpenRouter
Estimated monthly gap: $816. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on NVIDIA NIM, OpenRouter, and Fireworks AI; start route-level A/B tests there.
- Nemotron 3 Super-120B-A12B is $1.63/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Reasoning, Function calling, and Tool use before moving production traffic.
- Provider overlap exists on Fireworks AI, OpenRouter, and NVIDIA NIM; start route-level A/B tests there.
- GLM-5 is $1.63/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- GLM-5 adds Reasoning, Function calling, and Tool use in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2026-02-11 | 2026-03-11 |
| Context window | 200k | 1.05m |
| Parameters | 744B total, 40B active | 120B |
| Architecture | Mixture of Experts | Decoder Only |
| License | MITOSI-approved | NVIDIA Open Model |
| Openness | Open source | Open weights |
| Commercial use | Commercial use: permitted | Commercial use: permitted |
| Knowledge cutoff | 2025-11 | - |
Pricing and availability
| Pricing attribute | GLM-5 | Nemotron 3 Super-120B-A12B |
|---|---|---|
| Input price | $0.60/1M tokens | $0.09/1M tokens |
| Output price | $2.08/1M tokens | $0.45/1M tokens |
| Providers |
Capabilities
| Capability | GLM-5 | Nemotron 3 Super-120B-A12B |
|---|---|---|
| Vision | No | No |
| Multimodal | No | No |
| Reasoning | Yes | No |
| Function calling | Yes | No |
| Tool use | Yes | No |
| Structured outputs | Yes | Yes |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
| Benchmark | GLM-5 | Nemotron 3 Super-120B-A12B |
|---|---|---|
| MMLU PRO | 86.0 | 83.6 |
| SWE-bench Verified | 77.8 | 60.5 |
| Google-Proof Q&A | 86.0 | 80.0 |
| AIME 2025 | 92.7 | 90.2 |
| LiveCodeBench | 81.9 | 78.4 |
| τ-bench | 82.1 | 61.1 |
Deep dive
On shared benchmark coverage, MMLU PRO has GLM-5 at 86 and Nemotron 3 Super-120B-A12B at 83.6, with GLM-5 ahead by 2.4 points; SWE-bench Verified has GLM-5 at 77.8 and Nemotron 3 Super-120B-A12B at 60.5, with GLM-5 ahead by 17.3 points; Google-Proof Q&A has GLM-5 at 86 and Nemotron 3 Super-120B-A12B at 80, with GLM-5 ahead by 6 points. The largest visible gap is 17.3 points on SWE-bench Verified, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.
The capability footprint differs most on reasoning mode: GLM-5, function calling: GLM-5, and tool use: GLM-5. Both models share structured outputs, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.
For cost, GLM-5 lists $0.60/1M input and $2.08/1M output tokens on the cheapest tracked provider, while Nemotron 3 Super-120B-A12B lists $0.09/1M input and $0.45/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Nemotron 3 Super-120B-A12B lower by about $0.85 per million blended tokens. Availability is 7 providers versus 6, so concentration risk also matters.
Choose GLM-5 when reasoning depth and broader provider choice are central to the workload. Choose Nemotron 3 Super-120B-A12B when long-context analysis, larger context windows, and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which has a larger context window, GLM-5 or Nemotron 3 Super-120B-A12B?
Nemotron 3 Super-120B-A12B supports 1.05m tokens, while GLM-5 supports 200k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.
Which is cheaper, GLM-5 or Nemotron 3 Super-120B-A12B?
Nemotron 3 Super-120B-A12B is cheaper on tracked token pricing. GLM-5 costs $0.60/1M input and $2.08/1M output tokens. Nemotron 3 Super-120B-A12B costs $0.09/1M input and $0.45/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is GLM-5 or Nemotron 3 Super-120B-A12B open source?
GLM-5 is listed under MIT. Nemotron 3 Super-120B-A12B is listed under NVIDIA Open Model. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for reasoning mode, GLM-5 or Nemotron 3 Super-120B-A12B?
GLM-5 has the clearer documented reasoning mode signal in this comparison. If reasoning mode is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Which is better for function calling, GLM-5 or Nemotron 3 Super-120B-A12B?
GLM-5 has the clearer documented function calling signal in this comparison. If function calling is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.
Where can I run GLM-5 and Nemotron 3 Super-120B-A12B?
GLM-5 is available on Fireworks AI, OpenRouter, Together AI, GCP Vertex AI, and NVIDIA NIM. Nemotron 3 Super-120B-A12B is available on Cloudflare Workers AI, DeepInfra, NVIDIA NIM, OpenRouter, and Fireworks AI. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-06-15. Data sourced from public model cards and provider documentation.