Model comparison
DeepSeek-V3.1-Terminus vs Llama 3.1-405B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 30.7 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
MetaSummary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Llama 3.1-405B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 38.9.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 61.4% for Llama 3.1-405B.
Side by side
| DeepSeek-V3.1-Terminus | Llama 3.1-405B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 43.1 | 30.7 |
| Released | 2025-09-22 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 42 |
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 3.1-405B: 33.1 (#262)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1426 | 1291 |
| SciCode | 40.6% | — |
| WeirdML | — | 21.4% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Llama 3.1-405B: 21.0 (#140)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Llama 3.1-405B: 16.8 (#300)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 45% |
| LMArena Hard Prompts | 1426 | 1269 |
| DTBench | 81.3% | 61.4% |
| SimpleBench | — | 23% |
| CritPt | 1.7% | — |
| LMCA | 28.6% | — |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.75 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Llama 3.1-405B: 18.4 (#290)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1402 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Llama 3.1-405B: 30.4 (#227)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| LMArena Expert | — | 1243 |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Llama 3.1-405B: 40.7 (#214)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1407 | 1248 |
| LMArena Russian | 1436 | 1265 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1279 |
| LMArena German | — | 1252 |
| LMArena Japanese | — | 1208 |
| LMArena Korean | — | 1184 |
| LMArena Spanish | — | 1260 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Llama 3.1-405B: 65.9 (#214)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1259 |
| IFEval | — | 81.1% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Llama 3.1-405B: 38.4 (#197)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1421 | 1266 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Llama 3.1-405B: 38.9 (#251)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1419 | 1284 |
| LMArena Creative Writing | 1403 | 1262 |
| LMArena Multi-Turn | 1411 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Llama 3.1-405B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 30.7 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Llama 3.1-405B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 33.1 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Llama 3.1-405B share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Llama 3.1-405B has 42.