# DeepSeek-V2 (MoE-236B, May 2024) vs Olmo 3.1 32b Instruct

> Olmo 3.1 32b Instruct has enough public results to be ranked (#168); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-v2-vs-olmo-3-1-32b-instruct
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 40.3 | 39.4 |
| Rank | — | 168 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
- Olmo 3.1 32b Instruct: 39.5 (#157)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1347 |
| BigCodeBench Complete | 59.4% | — |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- Olmo 3.1 32b Instruct: 26.4 (#132)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 1322 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.77 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Math

- DeepSeek-V2 (MoE-236B, May 2024): —
- Olmo 3.1 32b Instruct: 36.3 (#167)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Math | — | 1305 |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- Olmo 3.1 32b Instruct: 36.1 (#175)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Expert | — | 1308 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## Multilingual

- DeepSeek-V2 (MoE-236B, May 2024): —
- Olmo 3.1 32b Instruct: 42.6 (#191)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | — | 1275 |
| LMArena Chinese | — | 1304 |
| LMArena French | — | 1328 |
| LMArena German | — | 1282 |
| LMArena Korean | — | 1206 |
| LMArena Russian | — | 1268 |
| LMArena Spanish | — | 1336 |

## Instruction Following

- DeepSeek-V2 (MoE-236B, May 2024): —
- Olmo 3.1 32b Instruct: 68.6 (#187)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1299 |

## Long Context

- DeepSeek-V2 (MoE-236B, May 2024): —
- Olmo 3.1 32b Instruct: 39.9 (#166)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1312 |

## Writing & Preference

- DeepSeek-V2 (MoE-236B, May 2024): —
- Olmo 3.1 32b Instruct: 50.2 (#185)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | — | 1311 |
| LMArena Creative Writing | — | 1264 |
| LMArena Multi-Turn | — | 1309 |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than Olmo 3.1 32b Instruct?

Olmo 3.1 32b Instruct has enough public results to be ranked (#168); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is DeepSeek-V2 (MoE-236B, May 2024) or Olmo 3.1 32b Instruct better for coding?

They score almost the same on coding (40.4 vs 39.5); test both on your own repository before choosing.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Olmo 3.1 32b Instruct share?

0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Olmo 3.1 32b Instruct has 16.