# DeepSeek LLM 67B vs GPT-4o mini

> DeepSeek LLM 67B and GPT-4o mini score almost the same on the Noometry Index (24.8 vs 25.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-gpt-4o-mini
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 2 categories and GPT-4o mini in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4o mini leads 42.2 to 29.5.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 52.6% for GPT-4o mini.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.8 | 25.4 |
| Rank | 341 | 337 |
| Context | — | 128K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- GPT-4o mini: 21.6 (#330)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Coding | 1096 | 1290 |
| Aider Polyglot | — | 3.6% |
| WeirdML | — | 11.8% |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- GPT-4o mini: 27.2 (#95)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| BALROG | — | 17.4% |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- GPT-4o mini: 8.7 (#343)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1070 | 1267 |
| Epoch Capabilities Index | 110.54 | 126.56 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 10.7% |
| Kagi LLM Benchmark | — | 28.8% |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 54.4% |
| LiveBench Data Analysis | — | 50% |
| LMCA | — | 10.4% |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- GPT-4o mini: 9.9 (#307)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 6.9% |
| LMArena Math | 1108 | 1267 |
| MATH Level 5 | 6.4% | 52.6% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| GSM8K | — | 91.3% |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- GPT-4o mini: 17.7 (#279)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 24.6% | 37.7% |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| GPQA (HELM) | — | 36.8% |
| LMArena Expert | — | 1235 |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |

## Multimodal

- DeepSeek LLM 67B: —
- GPT-4o mini: 25.3 (#117)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Vision | — | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- GPT-4o mini: 42.2 (#194)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1073 | 1266 |
| LMArena Chinese | 1132 | 1264 |
| LMArena French | — | 1296 |
| LMArena German | — | 1272 |
| LMArena Japanese | — | 1216 |
| LMArena Korean | — | 1195 |
| LMArena Russian | — | 1275 |
| LMArena Spanish | — | 1276 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- GPT-4o mini: 62.1 (#234)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1079 | 1259 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- GPT-4o mini: 39.1 (#181)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1092 | 1289 |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- GPT-4o mini: 39.7 (#243)

| Benchmark | DeepSeek LLM 67B | GPT-4o mini |
|---|---|---|
| LMArena Text | 1105 | 1286 |
| LMArena Creative Writing | 1067 | 1268 |
| LMArena Multi-Turn | 1082 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |

## FAQ

### Is DeepSeek LLM 67B better than GPT-4o mini?

DeepSeek LLM 67B and GPT-4o mini score almost the same on the Noometry Index (24.8 vs 25.4), so choose on price, context window or the category you care about most.

### Is DeepSeek LLM 67B or GPT-4o mini better for coding?

DeepSeek LLM 67B scores higher on coding benchmarks: 31.3 versus 21.6 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and GPT-4o mini share?

15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-4o mini has 60.