# DeepSeek-V3.1-Terminus vs Llama 13b

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-llama-13b
- Last updated: 2026-10-12
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 13.8.

## Snapshot

| | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 43.1 | 24.4 |
| Rank | 97 | 348 |
| Context | 164K | — |
| Input $/M | $0.27 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 42.0 (#113)
- Llama 13b: 21.4 (#337)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| LMArena Coding | 1426 | 683 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |

## Reasoning

- DeepSeek-V3.1-Terminus: 26.4 (#133)
- Llama 13b: 14.0 (#329)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1426 | 728 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |

## Math

- DeepSeek-V3.1-Terminus: 38.5 (#137)
- Llama 13b: 26.7 (#256)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| LMArena Math | 1402 | 838 |
| GSM8K | — | 20.6% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Llama 13b: —

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |

## Multimodal

- DeepSeek-V3.1-Terminus: —
- Llama 13b: —

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.1 (#92)
- Llama 13b: 16.6 (#297)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| LMArena Non-English | 1407 | 819 |
| LMArena Russian | 1436 | — |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.0 (#106)
- Llama 13b: 36.7 (#305)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1404 | 781 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.4 (#97)
- Llama 13b: —

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1421 | — |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.0 (#92)
- Llama 13b: 13.8 (#312)

| Benchmark | DeepSeek-V3.1-Terminus | Llama 13b |
|---|---|---|
| LMArena Text | 1419 | 834 |
| LMArena Creative Writing | 1403 | 794 |
| LMArena Multi-Turn | 1411 | 753 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Llama 13b?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 24.4 on the Noometry Index.

### Is DeepSeek-V3.1-Terminus or Llama 13b better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 21.4 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1-Terminus and Llama 13b share?

8 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Llama 13b has 21.