# DeepSeek-V3 vs Olmo 3.1 32b Instruct

> DeepSeek-V3 and Olmo 3.1 32b Instruct score almost the same on the Noometry Index (39.2 vs 38.8), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-v3-vs-olmo-3-1-32b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. DeepSeek-V3 scores higher in 5 categories and Olmo 3.1 32b Instruct in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3 leads 57.6 to 50.4.

## Snapshot

| | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 39.2 | 38.8 |
| Rank | 157 | 168 |
| Context | 164K | — |
| Input $/M | $0.24 | — |
| Output $/M | $0.90 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3: 41.9 (#99)
- Olmo 3.1 32b Instruct: 38.9 (#154)

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Coding | 1368 | 1346 |
| Aider Polyglot | 55.1% | — |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |

## Agentic & Tool Use

- DeepSeek-V3: —
- Olmo 3.1 32b Instruct: —

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| METR Time Horizons | 49.6% | — |

## Reasoning

- DeepSeek-V3: 20.0 (#226)
- Olmo 3.1 32b Instruct: 25.4 (#131)

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1365 | 1322 |
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 65.8% | — |
| DTBench | 64.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| Epoch Capabilities Index | 135.95 | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |

## Math

- DeepSeek-V3: 30.4 (#208)
- Olmo 3.1 32b Instruct: 33.6 (#169)

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Math | 1373 | 1305 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |

## Knowledge

- DeepSeek-V3: 37.5 (#147)
- Olmo 3.1 32b Instruct: 35.4 (#175)

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Expert | 1352 | 1307 |
| GPQA Diamond | 67.6% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |

## Multilingual

- DeepSeek-V3: 48.8 (#138)
- Olmo 3.1 32b Instruct: 42.8 (#185)

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | 1358 | 1275 |
| LMArena Chinese | 1390 | 1304 |
| LMArena French | 1386 | 1328 |
| LMArena German | 1374 | 1283 |
| LMArena Korean | 1321 | 1206 |
| LMArena Russian | 1372 | 1268 |
| LMArena Spanish | 1358 | 1337 |
| LMArena Japanese | 1333 | — |

## Instruction Following

- DeepSeek-V3: 73.0 (#125)
- Olmo 3.1 32b Instruct: 68.8 (#182)

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1345 | 1298 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |

## Long Context

- DeepSeek-V3: 34.0 (#248)
- Olmo 3.1 32b Instruct: 39.9 (#161)

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1353 | 1312 |
| Fiction.LiveBench | 50% | — |

## Writing & Preference

- DeepSeek-V3: 57.6 (#124)
- Olmo 3.1 32b Instruct: 50.4 (#179)

| Benchmark | DeepSeek-V3 | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | 1375 | 1311 |
| LMArena Creative Writing | 1364 | 1264 |
| LMArena Multi-Turn | 1389 | 1309 |
| Short-Story Creative Writing | 77% | — |
| EQ-Bench Creative Writing | 1472 | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |

## FAQ

### Is DeepSeek-V3 better than Olmo 3.1 32b Instruct?

DeepSeek-V3 and Olmo 3.1 32b Instruct score almost the same on the Noometry Index (39.2 vs 38.8), so choose on price, context window or the category you care about most.

### Is DeepSeek-V3 or Olmo 3.1 32b Instruct better for coding?

DeepSeek-V3 scores higher on coding benchmarks: 41.9 versus 38.9 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3 and Olmo 3.1 32b Instruct share?

16 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Olmo 3.1 32b Instruct has 16.