GPT-5.2-Codex vs NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
| Spec | GPT-5.2-Codex | NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 |
|---|---|---|
| Respan Index | 30.1 (#90) | 30.9 (#88) |
| Blended price per 1M | $4.81 | $0.175 |
| Context window | 400K | 1M |
| Input / output per 1M | $1.75 / $14 | $0.1 / $0.4 |
| Max output | 128K | - |
| Input | text, vision | text, vision, video |
| Released | 2025-12-18 | 2026-10-15 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | GPT-5.2-Codex | NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 |
|---|---|---|
| Coding | 18.8 GPT-5.2-Codex | 10.2 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 |
| Agents | 22.2 GPT-5.2-Codex | 39.3 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 |
| Reasoning | 35.8 GPT-5.2-Codex | 33.4 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 |
| Knowledge & language | 34.4 GPT-5.2-Codex | 25.2* NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 |
| Human preference | 49.4 GPT-5.2-Codex | 50.9 NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 leads on 2 of the 2 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-5.2-Codex | NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 |
|---|---|---|
| LMArena WebDev (LMArena) | 1339 | 1402 |
| OSWorld-Verified | 38.2% | 52.3% |
FAQ
Is GPT-5.2-Codex better than NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4?
NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 scores 30.9 on the Respan Index (#88), ahead of GPT-5.2-Codex at 30.1 (#90). NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 leads on 2 of the 2 benchmarks both report.
Which is cheaper, GPT-5.2-Codex or NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4?
GPT-5.2-Codex lists at $1.75 input and $14 output per 1M tokens; NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 at $0.1 and $0.4. NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 is 27x cheaper per token at list price.
Which has the larger context window?
GPT-5.2-Codex accepts 400K tokens and NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 1M tokens.
Compare other models
- vsClaude Opus 5.5 vs GPT-5.2-Codex
- vsClaude Fable 5.2 vs NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4
- vsGPT-5.2-Codex vs MiMo-V2.5-Pro
- vsGPT-5.2-Codex vs Muse Glimmer
- vsGPT-5.2-Codex vs Gemini 3.5 Flash-Lite
- vsNVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 vs Claude Opus 4.1
- vsNVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 vs MiMo-V2.5-Pro
- vsNVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4 vs MiniMax M3