Model comparison
DeepSeek-V3.1-Terminus vs Llama 3-70B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 28.5 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 3-70B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 35.7 to 12.0.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 54.2% for Llama 3-70B.
Side by side
| DeepSeek-V3.1-Terminus | Llama 3-70B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 42.6 | 28.5 |
| Released | 2025-09-22 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 31 |
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: 41.5 (#114), Llama 3-70B: 35.3 (#215)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1426 | 1206 |
| SciCode | 40.6% | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| ALE-Bench | 745.17 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Llama 3-70B: 20.9 (#132)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Llama 3-70B: 17.4 (#284)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 35.1% |
| LMArena Hard Prompts | 1427 | 1195 |
| DTBench | 81.3% | 54.2% |
| CritPt | 1.7% | — |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 122.91 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Llama 3-70B: 12.0 (#299)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Math | 1402 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Llama 3-70B: 20.8 (#272)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| MMLU | — | 79.3% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Llama 3-70B: 33.8 (#246)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1407 | 1142 |
| LMArena Russian | 1434 | 1159 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1231 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Spanish | — | 1241 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Llama 3-70B: 62.8 (#233)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1406 | 1194 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Llama 3-70B: 35.6 (#235)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1426 | 1174 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Llama 3-70B: 43.0 (#225)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Text | 1420 | 1221 |
| LMArena Creative Writing | 1404 | 1210 |
| LMArena Multi-Turn | 1411 | 1223 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Llama 3-70B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 28.5 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Llama 3-70B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 35.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Llama 3-70B share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Llama 3-70B has 31.