# DeepSeek-V2 (MoE-236B, May 2024) vs GPT-4.1 mini

> GPT-4.1 mini has enough public results to be ranked (#232); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-v2-vs-gpt-4-1-mini
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and GPT-4.1 mini in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 39.8 to 30.4.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 39.7 | 33.5 |
| Rank | — | 232 |
| Context | — | 1.05M |
| Input $/M | — | $0.40 |
| Output $/M | — | $1.60 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)
- GPT-4.1 mini: 30.4 (#286)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 48.9% |
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| SciCode | — | 40.4% |
| WeirdML | — | 37.6% |
| LMArena Coding | — | 1367 |
| BigCodeBench Complete | 59.4% | — |
| CadEval | — | 16% |

## Agentic & Tool Use

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 33.0 (#52)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 50.5% |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 10.9 (#335)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| Epoch Capabilities Index | 124.78 | 135.01 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 48.6% |
| ARC-AGI-1 | — | 3.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 7% |
| LMArena Hard Prompts | — | 1349 |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LMCA | — | 21.1% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Math

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 23.1 (#264)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 6.7% |
| OTIS Mock AIME 2024-2025 | — | 44.7% |
| Omni-MATH | — | 49.1% |
| LMArena Math | — | 1343 |
| MATH Level 5 | — | 87.3% |
| FrontierMath (Feb 2025 set) | — | 4.5% |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 34.7 (#183)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | — | 65.8% |
| SimpleQA Verified | — | 12.7% |
| MMLU-Pro | — | 78.3% |
| GPQA (HELM) | — | 61.4% |
| LMArena Expert | — | 1338 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## Multimodal

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 35.2 (#77)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | — | 1181 |

## Multilingual

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 45.9 (#161)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | — | 1318 |
| LMArena Chinese | — | 1329 |
| LMArena French | — | 1357 |
| LMArena German | — | 1349 |
| LMArena Japanese | — | 1291 |
| LMArena Korean | — | 1298 |
| LMArena Russian | — | 1324 |
| LMArena Spanish | — | 1319 |

## Instruction Following

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 73.9 (#113)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| IFEval | — | 90.4% |
| LMArena Instruction Following | — | 1332 |

## Long Context

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 31.8 (#270)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| Fiction.LiveBench | — | 44.4% |
| LMArena Longer Query | — | 1344 |

## Writing & Preference

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-4.1 mini: 48.8 (#193)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-4.1 mini |
|---|---|---|
| LMArena Text | — | 1341 |
| LMArena Creative Writing | — | 1300 |
| EQ-Bench Creative Writing | — | 1147 |
| WildBench | — | 83.8% |
| LMArena Multi-Turn | — | 1354 |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than GPT-4.1 mini?

GPT-4.1 mini has enough public results to be ranked (#232); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is DeepSeek-V2 (MoE-236B, May 2024) or GPT-4.1 mini better for coding?

DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 30.4 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and GPT-4.1 mini share?

2 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and GPT-4.1 mini has 47.