Model comparison
gpt-oss-20b vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 32.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
NVIDIASummary
- They share 16 benchmarks with published results for both. gpt-oss-20b scores higher in 5 categories and Nemotron 4 340b Instruct in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 4 340b Instruct leads 42.7 to 35.5.
Side by side
| gpt-oss-20b | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | OpenAI | NVIDIA |
| Noometry Index | 32.5 | 35.9 |
| Released | 2025-08-05 | 2024-06-14 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.6 (#192), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1306 | 1209 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Nemotron 4 340b Instruct: —
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Nemotron 4 340b Instruct leads
gpt-oss-20b: 19.3 (#261), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1202 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.82 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1317 | 1216 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#195), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1258 | 1171 |
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual gpt-oss-20b leads
gpt-oss-20b: 42.2 (#197), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1268 | 1206 |
| LMArena Chinese | 1314 | 1214 |
| LMArena German | 1255 | 1192 |
| LMArena Japanese | 1244 | 1128 |
| LMArena Korean | 1236 | 1148 |
| LMArena Russian | 1278 | 1219 |
| LMArena Spanish | 1267 | 1195 |
| LMArena French | — | 1197 |
Instruction Following Nemotron 4 340b Instruct leads
gpt-oss-20b: 61.8 (#240), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1236 | 1203 |
| IFEval | 73.2% | — |
Long Context Too close to call
gpt-oss-20b: 37.9 (#209), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1250 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
gpt-oss-20b: 35.5 (#265), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | gpt-oss-20b | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1287 | 1225 |
| LMArena Creative Writing | 1201 | 1203 |
| LMArena Multi-Turn | 1268 | 1214 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 32.5 on the Noometry Index.
Is gpt-oss-20b or Nemotron 4 340b Instruct better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 35.2 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Nemotron 4 340b Instruct share?
16 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Nemotron 4 340b Instruct has 17.