Model comparison
GPT-5.1-Codex vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 38.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
NVIDIASummary
- They share 1 benchmark with published results for both. GPT-5.1-Codex scores higher in 2 categories and Nemotron 3 Ultra in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.1-Codex leads 38.0 to 23.4.
- The biggest single-benchmark swing is ProofBench: 9% for GPT-5.1-Codex and 2% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
- GPT-5.1-Codex accepts more context: 400K tokens versus 262K.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1-Codex | Nemotron 3 Ultra | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 38.6 | 42.5 |
| Released | 2025-11-12 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 128K |
| Input $ / M tokens | $1.25 | $0.50 |
| Output $ / M tokens | $10 | $2.20 |
| Results tracked | 6 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1-Codex leads
GPT-5.1-Codex: 41.9 (#116), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1337 | — |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| LMArena Coding | — | 1468 |
| ALE-Bench | 1,245 | — |
Agentic & Tool Use GPT-5.1-Codex leads
GPT-5.1-Codex: 38.0 (#33), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| Terminal-Bench | 60.4% | — |
| APEX-Agents | — | 22.7% |
| METR Time Horizons | 70.8% | — |
Reasoning Not comparable
GPT-5.1-Codex: —, Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | — | 1452 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math Nemotron 3 Ultra leads
GPT-5.1-Codex: 30.3 (#235), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| ProofBench | 9% | 2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| LMArena Math | — | 1457 |
Knowledge Not comparable
GPT-5.1-Codex: —, Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | — | 85.4% |
| LMArena Expert | — | 1472 |
Multilingual Not comparable
GPT-5.1-Codex: —, Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |
Instruction Following Not comparable
GPT-5.1-Codex: —, Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | — | 1418 |
Long Context Not comparable
GPT-5.1-Codex: —, Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |
Writing & Preference Not comparable
GPT-5.1-Codex: —, Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | GPT-5.1-Codex | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | — | 1445 |
| LMArena Creative Writing | — | 1398 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1411 |
Frequently asked questions
Is GPT-5.1-Codex better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 38.6 on the Noometry Index.
Which is cheaper, GPT-5.1-Codex or Nemotron 3 Ultra?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.
Is GPT-5.1-Codex or Nemotron 3 Ultra better for coding?
GPT-5.1-Codex scores higher on coding benchmarks: 41.9 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1-Codex does, with 400K tokens against 262K.
How many benchmarks do GPT-5.1-Codex and Nemotron 3 Ultra share?
1 benchmark has published results for both models. GPT-5.1-Codex has 6 scored results on Noometry and Nemotron 3 Ultra has 30.