Model comparison
GPT-5.3 Codex vs Nemotron 3 Super
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 40.1 on the Noometry Index. Nemotron 3 Super costs 28× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
NVIDIASummary
- They share 2 benchmarks with published results for both. GPT-5.3 Codex scores higher in 1 category and Nemotron 3 Super in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 39.4.
- The biggest single-benchmark swing is WeirdML: 79.3% for GPT-5.3 Codex and 38% for Nemotron 3 Super.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- GPT-5.3 Codex accepts more context: 400K tokens versus 262K.
- Nemotron 3 Super has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Codex | Nemotron 3 Super | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 45.8 | 40.1 |
| Released | 2026-02-05 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 400K | 262K |
| Max output | 128K | 131K |
| Input $ / M tokens | $1.75 | $0.08 |
| Output $ / M tokens | $14 | $0.45 |
| Results tracked | 8 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
GPT-5.3 Codex: 48.6 (#56), Nemotron 3 Super: 39.4 (#158)
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| WeirdML | 79.3% | 38% |
| ALE-Bench | 1,655 | 213.9 |
| SWE-bench Verified | 74.8% | — |
| LMArena WebDev | 1409 | — |
| SciCode | — | 36% |
| LMArena Coding | — | 1403 |
Agentic & Tool Use Not comparable
GPT-5.3 Codex: 48.0 (#9), Nemotron 3 Super: —
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, Nemotron 3 Super: 18.7 (#276)
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| LMArena Hard Prompts | — | 1386 |
| Epoch Capabilities Index | 156.77 | — |
Math Not comparable
GPT-5.3 Codex: —, Nemotron 3 Super: 39.6 (#101)
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| MathArena Final-Answer Competitions | — | 60.4% |
| LMArena Math | — | 1380 |
Knowledge Not comparable
GPT-5.3 Codex: —, Nemotron 3 Super: 38.9 (#139)
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | — | 1398 |
Multilingual Not comparable
GPT-5.3 Codex: —, Nemotron 3 Super: 48.4 (#144)
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | — | 1355 |
| LMArena Chinese | — | 1432 |
| LMArena French | — | 1405 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1336 |
| LMArena Spanish | — | 1417 |
Instruction Following Not comparable
GPT-5.3 Codex: —, Nemotron 3 Super: 71.2 (#154)
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | — | 1347 |
Long Context Not comparable
GPT-5.3 Codex: —, Nemotron 3 Super: 41.5 (#139)
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | — | 1362 |
Writing & Preference Not comparable
GPT-5.3 Codex: —, Nemotron 3 Super: 55.9 (#140)
| Benchmark | GPT-5.3 Codex | Nemotron 3 Super |
|---|---|---|
| LMArena Text | — | 1378 |
| LMArena Creative Writing | — | 1317 |
| LMArena Multi-Turn | — | 1369 |
Frequently asked questions
Is GPT-5.3 Codex better than Nemotron 3 Super?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 40.1 on the Noometry Index. Nemotron 3 Super costs 28× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Which is cheaper, GPT-5.3 Codex or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is GPT-5.3 Codex or Nemotron 3 Super better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 39.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.3 Codex does, with 400K tokens against 262K.
How many benchmarks do GPT-5.3 Codex and Nemotron 3 Super share?
2 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Nemotron 3 Super has 21.