Model comparison
DeepSeek-V3.1-Terminus vs Llama 3.1 Nemotron Ultra 253b v1
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 36.7 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Llama 3.1 Nemotron Ultra 253b v1 in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where DeepSeek-V3.1-Terminus leads 52.1 to 43.1.
Side by side
| DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 43.1 | 36.7 |
| Released | 2025-09-22 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Coding | 1426 | 1312 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 10% |
Reasoning Too close to call
DeepSeek-V3.1-Terminus: 26.4 (#133), Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1316 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Too close to call
DeepSeek-V3.1-Terminus: 38.5 (#137), Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Math | 1402 | 1360 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Non-English | 1407 | 1282 |
| LMArena Russian | 1436 | 1284 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1308 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Longer Query | 1421 | 1299 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Text | 1419 | 1320 |
| LMArena Creative Writing | 1403 | 1314 |
| LMArena Multi-Turn | 1411 | 1317 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Llama 3.1 Nemotron Ultra 253b v1?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 36.7 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Llama 3.1 Nemotron Ultra 253b v1 better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 38.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Llama 3.1 Nemotron Ultra 253b v1 share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Llama 3.1 Nemotron Ultra 253b v1 has 11.