# DeepSeek LLM 67B vs GPT-4.1

> GPT-4.1 is the stronger model overall, scoring 35.7 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-gpt-4-1
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and GPT-4.1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 leads 37.0 to 7.1.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 83% for GPT-4.1.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.8 | 35.7 |
| Rank | 341 | 215 |
| Context | — | 1.05M |
| Input $/M | — | $2 |
| Output $/M | — | $8 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek LLM 67B: 31.3 (#273)
- GPT-4.1: 34.2 (#228)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| LMArena Coding | 1096 | 1391 |
| SWE-bench Verified | — | 48.5% |
| SWE-bench Verified (bash only) | — | 39.6% |
| Aider Polyglot | — | 52.4% |
| WeirdML | — | 39% |
| CadEval | — | 42% |
| ALE-Bench | — | 558.1 |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- GPT-4.1: 34.4 (#40)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 54% |

## Reasoning

- DeepSeek LLM 67B: 15.9 (#300)
- GPT-4.1: 11.7 (#334)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| Chess Puzzles | 0% | 6% |
| LMArena Hard Prompts | 1070 | 1384 |
| Epoch Capabilities Index | 110.54 | 136.79 |
| ARC-AGI-2 | — | 0.4% |
| SimpleBench | — | 27% |
| Kagi LLM Benchmark | — | 52.3% |
| ARC-AGI-1 | — | 5.5% |
| EnigmaEval | — | 2.2% |
| DTBench | — | 68.3% |
| LMCA | — | 25.6% |
| ForecastBench | — | 61.5 |

## Math

- DeepSeek LLM 67B: 8.1 (#318)
- GPT-4.1: 21.4 (#269)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 38.3% |
| LMArena Math | 1108 | 1369 |
| MATH Level 5 | 6.4% | 83% |
| FrontierMath (Tiers 1-3) | — | 6% |
| Omni-MATH | — | 47.1% |
| FrontierMath (Feb 2025 set) | — | 5.5% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- DeepSeek LLM 67B: 7.1 (#308)
- GPT-4.1: 37.0 (#152)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| GPQA Diamond | 24.6% | 66.9% |
| Humanity's Last Exam | — | 5.4% |
| SimpleQA Verified | — | 31.1% |
| MMLU-Pro | — | 81.1% |
| Vectara Hallucination Rate | — | 5.6% |
| GPQA (HELM) | — | 65.9% |
| LMArena Expert | — | 1364 |

## Multimodal

- DeepSeek LLM 67B: —
- GPT-4.1: 37.5 (#66)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| LMArena Vision | — | 1210 |
| GeoBench | — | 72% |

## Multilingual

- DeepSeek LLM 67B: 29.5 (#262)
- GPT-4.1: 49.6 (#128)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| LMArena Non-English | 1073 | 1370 |
| LMArena Chinese | 1132 | 1382 |
| LMArena French | — | 1383 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1320 |
| LMArena Korean | — | 1339 |
| LMArena Russian | — | 1377 |
| LMArena Spanish | — | 1375 |

## Instruction Following

- DeepSeek LLM 67B: 55.7 (#272)
- GPT-4.1: 71.5 (#148)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1367 |
| IFEval | — | 83.8% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#260)
- GPT-4.1: 40.0 (#158)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| LMArena Longer Query | 1092 | 1385 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- DeepSeek LLM 67B: 31.8 (#277)
- GPT-4.1: 57.8 (#120)

| Benchmark | DeepSeek LLM 67B | GPT-4.1 |
|---|---|---|
| LMArena Text | 1105 | 1383 |
| LMArena Creative Writing | 1067 | 1363 |
| LMArena Multi-Turn | 1082 | 1398 |
| EQ-Bench Creative Writing | — | 1420 |
| WildBench | — | 85.4% |

## FAQ

### Is DeepSeek LLM 67B better than GPT-4.1?

GPT-4.1 is the stronger model overall, scoring 35.7 to 24.8 on the Noometry Index.

### Is DeepSeek LLM 67B or GPT-4.1 better for coding?

GPT-4.1 scores higher on coding benchmarks: 34.2 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and GPT-4.1 share?

15 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and GPT-4.1 has 52.