# DeepSeek LLM 67B vs o3

> o3 is the stronger model overall, scoring 47.5 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-o3
- Last updated: 2026-10-11
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and o3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 7.0.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 97.8% for o3.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek LLM 67B | o3 |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.9 | 47.5 |
| Rank | 347 | 61 |
| Context | — | 200K |
| Input $/M | — | $2 |
| Output $/M | — | $8 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- o3: 46.8 (#64)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| LMArena Coding | 1096 | 1408 |
| SWE-bench Verified | — | 62.3% |
| SWE-bench Verified (bash only) | — | 58.4% |
| Aider Polyglot | — | 81.3% |
| GSO | — | 8.8% |
| WeirdML | — | 52.4% |
| CadEval | — | 74% |
| ALE-Bench | — | 933.55 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- o3: 34.5 (#44)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 63% |
| GDPval | — | 30.8% |
| DeepResearch Bench | — | 45.2% |
| OSWorld | — | 23% |
| LMArena Search | — | 1144 |
| METR Time Horizons | — | 65.4% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- o3: 32.0 (#78)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| Chess Puzzles | 0% | 38% |
| LMArena Hard Prompts | 1070 | 1402 |
| Epoch Capabilities Index | 110.5 | 146.86 |
| ARC-AGI-2 | — | 6.5% |
| SimpleBench | — | 53.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 60.8% |
| CritPt | — | 1.4% |
| EnigmaEval | — | 13.1% |
| Mystery Game Puzzles | — | 29% |
| DTBench | — | 84.8% |
| LMCA | — | 39.7% |
| ForecastBench | — | 62.5 |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- o3: 50.2 (#58)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 84.4% |
| LMArena Math | 1108 | 1426 |
| MATH Level 5 | 6.4% | 97.8% |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| Omni-MATH | — | 71.4% |
| FrontierMath (Feb 2025 set) | — | 18.7% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- o3: 54.6 (#52)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| GPQA Diamond | 24.6% | 81.8% |
| Humanity's Last Exam | — | 20.3% |
| SimpleQA Verified | — | 49.4% |
| MMLU-Pro | — | 85.9% |
| Confabulations | — | 14.4% |
| GPQA (HELM) | — | 75.3% |
| LMArena Expert | — | 1402 |

## Multimodal

- DeepSeek LLM 67B: —
- o3: 41.4 (#36)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| LMArena Vision | — | 1214 |
| GeoBench | — | 74% |
| VPCT | — | 52% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- o3: 51.7 (#105)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| LMArena Non-English | 1073 | 1401 |
| LMArena Chinese | 1132 | 1437 |
| LMArena French | — | 1430 |
| LMArena German | — | 1420 |
| LMArena Japanese | — | 1403 |
| LMArena Korean | — | 1370 |
| LMArena Russian | — | 1406 |
| LMArena Spanish | — | 1395 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- o3: 72.8 (#127)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1368 |
| IFEval | — | 86.9% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- o3: 53.3 (#6)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| LMArena Longer Query | 1092 | 1372 |
| Fiction.LiveBench | — | 88.9% |
| CL-bench | — | 17.8% |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- o3: 63.5 (#64)

| Benchmark | DeepSeek LLM 67B | o3 |
|---|---|---|
| LMArena Text | 1105 | 1410 |
| LMArena Creative Writing | 1067 | 1359 |
| LMArena Multi-Turn | 1082 | 1405 |
| Short-Story Creative Writing | — | 83.9% |
| EQ-Bench Creative Writing | — | 1676 |
| WildBench | — | 86.1% |

## FAQ

### Is DeepSeek LLM 67B better than o3?

o3 is the stronger model overall, scoring 47.5 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or o3 better for coding?

o3 scores higher on coding benchmarks: 46.8 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and o3 share?

15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and o3 has 63.