# Deepseek Coder v2 vs GPT-5 Nano

> Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-gpt-5-nano
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Deepseek Coder v2 scores higher in 4 categories and GPT-5 Nano in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where GPT-5 Nano leads 75.2 to 61.9.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.

## Snapshot

| | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 35.3 | 33.4 |
| Rank | 217 | 234 |
| Context | — | 400K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.40 |
| Weights | Open | Proprietary |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- GPT-5 Nano: 33.3 (#248)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Coding | 1251 | 1351 |
| SWE-bench Verified (bash only) | — | 34.8% |
| WeirdML | — | 38.1% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 718.67 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Agentic & Tool Use

- Deepseek Coder v2: —
- GPT-5 Nano: 25.6 (#99)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- GPT-5 Nano: 16.4 (#291)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1329 |
| ARC-AGI-2 | — | 2.6% |
| Kagi LLM Benchmark | — | 62.2% |
| ARC-AGI-1 | — | 20.7% |
| Chess Puzzles | — | 27% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 62.7% |
| LMCA | — | 7.9% |
| Epoch Capabilities Index | — | 139.39 |
| ForecastBench | — | 59.1 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- GPT-5 Nano: 29.1 (#221)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Math | 1241 | 1318 |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 81.1% |
| ProofBench | — | 12% |
| Omni-MATH | — | 54.6% |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- GPT-5 Nano: 35.8 (#166)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Expert | 1181 | 1321 |
| GPQA Diamond | — | 69.4% |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | — | 77.8% |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | — | 67.9% |
| ARC (AI2) Challenge | 64.3% | — |

## Multimodal

- Deepseek Coder v2: —
- GPT-5 Nano: 30.7 (#102)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Vision | — | 1159 |
| VPCT | — | 37.2% |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- GPT-5 Nano: 45.5 (#167)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1182 | 1313 |
| LMArena Chinese | 1201 | 1355 |
| LMArena German | 1164 | 1329 |
| LMArena Korean | 1104 | 1269 |
| LMArena Russian | 1188 | 1296 |
| LMArena Spanish | 1153 | 1360 |
| LMArena French | 1184 | — |
| LMArena Japanese | 1126 | — |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- GPT-5 Nano: 75.2 (#72)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Instruction Following | 1180 | 1306 |
| IFEval | — | 93.2% |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- GPT-5 Nano: 31.3 (#275)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1219 | 1313 |
| Fiction.LiveBench | — | 44.4% |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- GPT-5 Nano: 39.4 (#244)

| Benchmark | Deepseek Coder v2 | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1191 | 1320 |
| LMArena Creative Writing | 1120 | 1250 |
| LMArena Multi-Turn | 1176 | 1311 |
| EQ-Bench Creative Writing | — | 705 |
| WildBench | — | 80.6% |

## FAQ

### Is Deepseek Coder v2 better than GPT-5 Nano?

Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 33.4 on the Noometry Index.

### Is Deepseek Coder v2 or GPT-5 Nano better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 33.3 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and GPT-5 Nano share?

15 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and GPT-5 Nano has 48.