# DeepSeek LLM 67B vs DeepSeek-V3.1

> DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-deepseek-v3-1
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and DeepSeek-V3.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.0 to 7.1.

## Snapshot

| | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 24.8 | 42.2 |
| Rank | 341 | 106 |
| Context | — | 164K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.95 |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- DeepSeek-V3.1: 39.8 (#140)

| Benchmark | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| LMArena Coding | 1096 | 1417 |
| WeirdML | — | 38.4% |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- DeepSeek-V3.1: 27.3 (#109)

| Benchmark | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1417 |
| Epoch Capabilities Index | 110.54 | 139.92 |
| SimpleBench | — | 40% |
| Kagi LLM Benchmark | — | 53.2% |
| Chess Puzzles | 0% | — |
| DTBench | — | 82.7% |
| LMCA | — | 24.3% |
| ForecastBench | — | 58 |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- DeepSeek-V3.1: 36.1 (#125)

| Benchmark | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1108 | 1420 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- DeepSeek-V3.1: 43.0 (#86)

| Benchmark | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Vectara Hallucination Rate | — | 5.5% |
| LMArena Expert | — | 1403 |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- DeepSeek-V3.1: 51.8 (#100)

| Benchmark | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1073 | 1400 |
| LMArena Chinese | 1132 | 1470 |
| LMArena French | — | 1447 |
| LMArena German | — | 1412 |
| LMArena Japanese | — | 1374 |
| LMArena Korean | — | 1337 |
| LMArena Russian | — | 1405 |
| LMArena Spanish | — | 1429 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- DeepSeek-V3.1: 74.1 (#105)

| Benchmark | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1400 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- DeepSeek-V3.1: 36.3 (#227)

| Benchmark | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1092 | 1422 |
| Fiction.LiveBench | — | 52.8% |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- DeepSeek-V3.1: 60.5 (#93)

| Benchmark | DeepSeek LLM 67B | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1105 | 1420 |
| LMArena Creative Writing | 1067 | 1401 |
| LMArena Multi-Turn | 1082 | 1408 |
| EQ-Bench Creative Writing | — | 1436 |

## FAQ

### Is DeepSeek LLM 67B better than DeepSeek-V3.1?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or DeepSeek-V3.1 better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and DeepSeek-V3.1 share?

11 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and DeepSeek-V3.1 has 27.