Model comparison
Llama 3.1 Nemotron Ultra 253b v1 vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 36.7 on the Noometry Index.
Last verified . 10 shared benchmarks.
NVIDIA
StepFunSummary
- They share 10 benchmarks with published results for both. Llama 3.1 Nemotron Ultra 253b v1 scores higher in 3 categories and Step 2 16k Exp 202412 in 4 categories; 2 gaps are clear of the uncertainty.
- Llama 3.1 Nemotron Ultra 253b v1 has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 36.7 | 39.2 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1312 | 1316 |
Agentic & Tool Use Not comparable
Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149), Step 2 16k Exp 202412: —
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10% | — |
Reasoning Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1316 | 1299 |
Math Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1360 | 1304 |
Knowledge Not comparable
Llama 3.1 Nemotron Ultra 253b v1: —, Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | — | 1279 |
Multilingual Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1282 | 1290 |
| LMArena Russian | 1284 | 1324 |
| LMArena Chinese | — | 1331 |
Instruction Following Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1308 | 1287 |
Long Context Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1299 | 1307 |
Writing & Preference Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1320 | 1321 |
| LMArena Creative Writing | 1314 | 1328 |
| LMArena Multi-Turn | 1317 | 1292 |
Frequently asked questions
Is Llama 3.1 Nemotron Ultra 253b v1 better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 36.7 on the Noometry Index.
Is Llama 3.1 Nemotron Ultra 253b v1 or Step 2 16k Exp 202412 better for coding?
They score almost the same on coding (38.4 vs 38.5); test both on your own repository before choosing.
How many benchmarks do Llama 3.1 Nemotron Ultra 253b v1 and Step 2 16k Exp 202412 share?
10 benchmarks have published results for both models. Llama 3.1 Nemotron Ultra 253b v1 has 11 scored results on Noometry and Step 2 16k Exp 202412 has 12.