# DeepSeek-V3.1-Terminus vs Llama 3-70B

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-llama-3-70b
- Last updated: 2026-10-12
- Shared benchmarks: 12

## Summary

- 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 38.5 to 12.8.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 54.2% for Llama 3-70B.

## Snapshot

| | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 43.1 | 28.8 |
| Rank | 97 | 323 |
| Context | 164K | — |
| Input $/M | $0.27 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 42.0 (#113)
- Llama 3-70B: 35.8 (#218)

| 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

- DeepSeek-V3.1-Terminus: —
- Llama 3-70B: 21.1 (#139)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |

## Reasoning

- DeepSeek-V3.1-Terminus: 26.4 (#133)
- Llama 3-70B: 18.0 (#288)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 35.1% |
| LMArena Hard Prompts | 1426 | 1195 |
| DTBench | 81.3% | 54.2% |
| CritPt | 1.7% | — |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |

## Math

- DeepSeek-V3.1-Terminus: 38.5 (#137)
- Llama 3-70B: 12.8 (#305)

| 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

- DeepSeek-V3.1-Terminus: —
- Llama 3-70B: 20.8 (#277)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| GPQA Diamond | — | 40.6% |
| LMArena Expert | — | 1149 |
| MMLU | — | 79.3% |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.1 (#92)
- Llama 3-70B: 33.6 (#251)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1407 | 1142 |
| LMArena Russian | 1436 | 1159 |
| LMArena Chinese | — | 1114 |
| LMArena French | — | 1232 |
| LMArena German | — | 1169 |
| LMArena Japanese | — | 1017 |
| LMArena Korean | — | 1017 |
| LMArena Spanish | — | 1241 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.0 (#106)
- Llama 3-70B: 62.5 (#238)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1194 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.4 (#97)
- Llama 3-70B: 35.6 (#240)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1421 | 1174 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.0 (#92)
- Llama 3-70B: 42.8 (#231)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 3-70B |
|---|---|---|
| LMArena Text | 1419 | 1221 |
| LMArena Creative Writing | 1403 | 1210 |
| LMArena Multi-Turn | 1411 | 1223 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Llama 3-70B?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 28.8 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: 42.0 versus 35.8 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.