GPT-5.2-Codex vs Nemotron 3 Ultra
GPT-5.2-Codex leads Nemotron 3 Ultra on coding, 45.4 to 30.0 on the Vibe Coding Index, and Nemotron 3 Ultra costs 5.8x less per output token ($2.40 vs $14.00 per million). Updated October 22, 2026; 10 benchmarks have a result for both.
GPT-5.2-Codex or Nemotron 3 Ultra: which to pick
Pick GPT-5.2-Codex for coding: it scores 45.4 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra.
Pick Nemotron 3 Ultra for output tokens 5.8x cheaper ($2.40 vs $14.00 per million) and work measured by IFBench, where it leads.
- Shared results
- 10
- GPT-5.2-Codex only
- 12
- Nemotron 3 Ultra only
- 60
- Like-for-like categories
- 5 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
GPT-5.2-Codex
GPT-5.2-Codex scores 45.4 against 30.0.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-5.2-Codex
GPT-5.2-Codex leads, 28.5 against 22.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Nemotron 3 Ultra has a AA Agentic Index result, 20.1.
Directional only
Reasoning
GPQA Diamond
No call
Only Nemotron 3 Ultra has a GPQA Diamond result, 86.1%.
Directional only
Knowledge
MMLU Pro
No call
Only Nemotron 3 Ultra has a MMLU Pro result, 85.8%.
Directional only
Web design
Design Arena: websites
No call
Only Nemotron 3 Ultra has a Design Arena: websites result, 1145.
Directional only
Long documents
Listed context window
GPT-5.2-Codex
GPT-5.2-Codex takes 400K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Nemotron 3 Ultra
GPT-5.2-Codex $0.0088, Nemotron 3 Ultra $0.0018 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.2-Codex has the number, $0.43.
Directional only
At a glance
- Coding index
- GPT-5.2-Codex 45.4 from 3 benchmarks, Nemotron 3 Ultra 30.0 from 3 benchmarks.
- Widest category
- Coding, 9.1 points apart on average over 4 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): GPT-5.2-Codex 37.9% against Nemotron 3 Ultra 7.6%, 30.3 points apart on a 0 to 100 scale.
- Output price
- GPT-5.2-Codex $14.00 against Nemotron 3 Ultra $2.40 per million output tokens, 5.8x apart.
- Context window
- GPT-5.2-Codex takes 400K tokens, Nemotron 3 Ultra 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5.2-Codex | Bars | Nemotron 3 Ultra | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 0 | ||
| General | 1 | 1 | ||
| All shared boards | 9 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| SWE-bench Verified | 72.8% | Not measured | Only GPT-5.2-Codex measured |
| SWE-bench Multilingual | 66.3% | Not measured | Only GPT-5.2-Codex measured |
| LMArena WebDev | 1339 | Not measured | Only GPT-5.2-Codex measured |
| AA Coding Index | Not measured | 49.3 | Only Nemotron 3 Ultra measured |
| LiveCodeBench (Vals AI) | 88.0% | 86.0% | GPT-5.2-Codex |
| SWE-bench Verified (Vals AI) | 72.4% | 69.0% | GPT-5.2-Codex |
| Vibe Code Bench (Vals AI) | 37.9% | 7.6% | GPT-5.2-Codex |
| Code migration (Vals AI) | Not measured | 4.9% | Only Nemotron 3 Ultra measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Nemotron 3 Ultra measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 50.9% | Only Nemotron 3 Ultra measured |
| SciCode | Not measured | 40.3% | Only Nemotron 3 Ultra measured |
| Terminal-Bench Hard (Artificial Analysis run) | 37.1% | 36.4% | GPT-5.2-Codex |
| Terminal-Bench | 66.5% | Not measured | Only GPT-5.2-Codex measured |
| FrontierCode | Not measured | 13.6% | Only Nemotron 3 Ultra measured |
| WeirdML | Not measured | 43.5% | Only Nemotron 3 Ultra measured |
| ALE-Bench | 1299.9 | Not measured | Only GPT-5.2-Codex measured |
| LMArena Text: coding | Not measured | 1468 | Only Nemotron 3 Ultra measured |
| LMArena Text: software and IT | Not measured | 1468 | Only Nemotron 3 Ultra measured |
| LMArena WebDev: React | 1329 | Not measured | Only GPT-5.2-Codex measured |
| LMArena WebDev: HTML | 1348 | Not measured | Only GPT-5.2-Codex measured |
| Neither model has a result on the other 19 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| AA Intelligence Index | 28.5 | 22.9 | GPT-5.2-Codex |
| Epoch Capabilities Index | Not measured | 146.0 | Only Nemotron 3 Ultra measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 20.1 | Only Nemotron 3 Ultra measured |
| Design Arena: agents building web apps | 1051 | Not measured | Only GPT-5.2-Codex measured |
| Design Arena: agents building full-stack apps | 993 | Not measured | Only GPT-5.2-Codex measured |
| Design Arena: agents building mobile apps | 1090 | Not measured | Only GPT-5.2-Codex measured |
| Design Arena: agents building Android apps | 1176 | Not measured | Only GPT-5.2-Codex measured |
| Design Arena: agents building Godot games | 1142 | Not measured | Only GPT-5.2-Codex measured |
| Finance Agent (Vals AI) | Not measured | 37.7% | Only Nemotron 3 Ultra measured |
| Legal Research Bench (Vals AI) | Not measured | 15.4% | Only Nemotron 3 Ultra measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 31.7% | Only Nemotron 3 Ultra measured |
| τ²-Bench Telecom | 92.1% | 83.3% | GPT-5.2-Codex |
| APEX-Agents | Not measured | 22.7% | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 30 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 86.1% | Only Nemotron 3 Ultra measured |
| GPQA Diamond (Artificial Analysis run) | 89.9% | 86.7% | GPT-5.2-Codex |
| Humanity's Last Exam (Artificial Analysis run) | 35.7% | 28.4% | GPT-5.2-Codex |
| GPQA Diamond (Epoch AI run) | Not measured | 85.4% | Only Nemotron 3 Ultra measured |
| Mystery game puzzles | Not measured | 20.0% | Only Nemotron 3 Ultra measured |
| LMArena Text: hard prompts | Not measured | 1452 | Only Nemotron 3 Ultra measured |
| LMArena Text: expert | Not measured | 1472 | Only Nemotron 3 Ultra measured |
| LMArena Text: hard prompts in English | Not measured | 1453 | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 86.7% | Only Nemotron 3 Ultra measured |
| ProofBench | Not measured | 2.0% | Only Nemotron 3 Ultra measured |
| LMArena Text: math | Not measured | 1457 | Only Nemotron 3 Ultra measured |
| LMArena Text: mathematical work | Not measured | 1461 | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 85.8% | Only Nemotron 3 Ultra measured |
| LegalBench (Vals AI) | Not measured | 82.1% | Only Nemotron 3 Ultra measured |
| CorpFin (Vals AI) | Not measured | 65.5% | Only Nemotron 3 Ultra measured |
| TaxEval (Vals AI) | Not measured | 73.1% | Only Nemotron 3 Ultra measured |
| MedCode (Vals AI) | Not measured | 38.6% | Only Nemotron 3 Ultra measured |
| LMArena Text: science | Not measured | 1465 | Only Nemotron 3 Ultra measured |
| LMArena Text: medicine and healthcare | Not measured | 1456 | Only Nemotron 3 Ultra measured |
| LMArena Text: legal and government | Not measured | 1452 | Only Nemotron 3 Ultra measured |
| LMArena Text: business and finance | Not measured | 1434 | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 9 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1145 | Only Nemotron 3 Ultra measured |
| Design Arena: UI components | Not measured | 1136 | Only Nemotron 3 Ultra measured |
| Design Arena: game dev | Not measured | 1138 | Only Nemotron 3 Ultra measured |
| Design Arena: data viz | Not measured | 1142 | Only Nemotron 3 Ultra measured |
| Design Arena: 3D | Not measured | 1131 | Only Nemotron 3 Ultra measured |
| Design Arena: all code categories | Not measured | 1146 | Only Nemotron 3 Ultra measured |
| Design Arena: SVG | Not measured | 1069 | Only Nemotron 3 Ultra measured |
| Design Arena: ASCII art | Not measured | 1100 | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| IFBench | 77.6% | 81.4% | Nemotron 3 Ultra |
| Long context reasoning (AA-LCR) | 82.3% | 79.3% | GPT-5.2-Codex |
| DTBench | Not measured | 90.1% | Only Nemotron 3 Ultra measured |
| LMCA | Not measured | 36.9% | Only Nemotron 3 Ultra measured |
| LMArena Text | Not measured | 1445 | Only Nemotron 3 Ultra measured |
| LMArena Text: instruction following | Not measured | 1418 | Only Nemotron 3 Ultra measured |
| LMArena Text: creative writing | Not measured | 1399 | Only Nemotron 3 Ultra measured |
| LMArena Text: English | Not measured | 1455 | Only Nemotron 3 Ultra measured |
| LMArena Text: non-English | Not measured | 1427 | Only Nemotron 3 Ultra measured |
| LMArena Text: Chinese | Not measured | 1497 | Only Nemotron 3 Ultra measured |
| LMArena Text: German | Not measured | 1472 | Only Nemotron 3 Ultra measured |
| LMArena Text: Korean | Not measured | 1384 | Only Nemotron 3 Ultra measured |
| LMArena Text: French | Not measured | 1472 | Only Nemotron 3 Ultra measured |
| LMArena Text: Spanish | Not measured | 1455 | Only Nemotron 3 Ultra measured |
| LMArena Text: Russian | Not measured | 1417 | Only Nemotron 3 Ultra measured |
| LMArena Text: Polish | Not measured | 1385 | Only Nemotron 3 Ultra measured |
| LMArena Text: multi-turn | Not measured | 1411 | Only Nemotron 3 Ultra measured |
| LMArena Text: longer queries | Not measured | 1437 | Only Nemotron 3 Ultra measured |
| LMArena Text: writing and language | Not measured | 1406 | Only Nemotron 3 Ultra measured |
| LMArena Text: entertainment and media | Not measured | 1397 | Only Nemotron 3 Ultra measured |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2-Codex | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Nemotron 3 Ultra costs less
Repository review
50K input + 3K output tokens
Nemotron 3 Ultra costs less
Agent loop
200K input + 10K output tokens
Nemotron 3 Ultra costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5.2-Codex | NVIDIA Nemotron 3 Ultra |
|---|---|---|
| Maker | OpenAI | NVIDIA |
| Weights | No public weights listed | Open weights |
| Released | January 14, 2026 | June 4, 2026 |
| Context window | 400K | 262K |
| Input $/Mtok | $1.75 | $0.60 |
| Output $/Mtok | $14.00 | $2.40 |
| Coding index | 45.4 | 30.0 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $0.43 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2-Codex better than Nemotron 3 Ultra for coding?
Pick GPT-5.2-Codex for coding: it scores 45.4 on the Vibe Coding Index against 30.0 for Nemotron 3 Ultra. Pick Nemotron 3 Ultra for output tokens 5.8x cheaper ($2.40 vs $14.00 per million) and work measured by IFBench, where it leads.
Which is cheaper, GPT-5.2-Codex or Nemotron 3 Ultra?
GPT-5.2-Codex costs $1.75 per million input tokens and $14.00 per million output tokens; Nemotron 3 Ultra costs $0.60 and $2.40. Cost per solved task is known for GPT-5.2-Codex only.
Which has the bigger context window, GPT-5.2-Codex or Nemotron 3 Ultra?
GPT-5.2-Codex, with 400K tokens against 262K.
How many benchmarks is the GPT-5.2-Codex vs Nemotron 3 Ultra comparison based on?
10 benchmarks have a result for both models as of October 22, 2026. GPT-5.2-Codex's coding index rests on 3 independent benchmarks and Nemotron 3 Ultra's on 3. Where only one model has a result, the page says so instead of naming a winner.