# DeepSeek-V2 (MoE-236B, May 2024) vs GPT-5.6 Sol

> GPT-5.6 Sol has enough public results to be ranked (#6); 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-5-6-sol
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 0 categories and GPT-5.6 Sol in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.6 Sol leads 61.1 to 39.8.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 39.7 | 64.4 |
| Rank | — | 6 |
| Context | — | 1.05M |
| Input $/M | — | $4 |
| Output $/M | — | $20 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)
- GPT-5.6 Sol: 61.1 (#7)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| DeepSWE | — | 72.7% |
| FrontierCode | — | 47.5% |
| CursorBench | — | 41.7% |
| LMArena WebDev | — | 1619 |
| FrontierSWE | — | 32.2% |
| SciCode | — | 57.1% |
| WeirdML | — | 89.4% |
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1493 |
| MirrorCode | — | 20% |
| BigCodeBench Complete | 59.4% | — |
| ALE-Bench | — | 2,177 |

## Agentic & Tool Use

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 50.2 (#7)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| APEX-Agents | — | 51.4% |
| OSWorld 2.0 | — | 27.3% |
| τ²-bench Banking | — | 46.9% |
| PostTrainBench | — | 36.2% |
| BALROG | — | 60% |
| GBAEval | — | 52.6% |
| GDP.pdf | — | 30.7% |
| LMArena Search | — | 1257 |
| Vending-Bench 2 | — | 9,619 |

## Reasoning

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 74.7 (#6)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| Epoch Capabilities Index | 124.78 | 161.99 |
| ARC-AGI-2 | — | 92.5% |
| SimpleBench | — | 71.7% |
| Kagi LLM Benchmark | — | 67% |
| NYT Connections (extended) | — | 93.8% |
| ARC-AGI-1 | — | 97.5% |
| CritPt | — | 32.3% |
| Chess Puzzles | — | 64% |
| EnigmaEval | — | 37.1% |
| EBR-Bench | — | 44.8% |
| LMArena Hard Prompts | — | 1481 |
| Mystery Game Puzzles | — | 58% |
| DTBench | — | 96% |
| LMCA | — | 59.2% |
| Surface Evolver Bench | — | 93.1% |
| Bench to the Future 3 | — | 0.14 |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |

## Math

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 85.5 (#7)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 89.1% |
| FrontierMath Tier 4 | — | 82.9% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 83% |
| LMArena Math | — | 1472 |
| FrontierMath Erdős | — | 0% |

## Knowledge

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 64.3 (#16)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| GPQA Diamond | — | 93.5% |
| SimpleQA Verified | — | 69.7% |
| Vectara Hallucination Rate | — | 12.4% |
| LMArena Expert | — | 1517 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |

## Multimodal

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 48.9 (#8)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| LMArena Vision | — | 1281 |
| Blueprint-Bench 2 | — | 33.6% |
| Furniture Assembly | — | 56.7% |
| LMArena Document | — | 1483 |

## Multilingual

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 55.4 (#32)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| LMArena Non-English | — | 1450 |
| LMArena Chinese | — | 1523 |
| LMArena French | — | 1475 |
| LMArena German | — | 1476 |
| LMArena Japanese | — | 1475 |
| LMArena Korean | — | 1434 |
| LMArena Russian | — | 1466 |
| LMArena Spanish | — | 1449 |

## Instruction Following

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 77.8 (#16)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| LMArena Instruction Following | — | 1480 |

## Long Context

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 45.3 (#42)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| LMArena Longer Query | — | 1479 |

## Writing & Preference

- DeepSeek-V2 (MoE-236B, May 2024): —
- GPT-5.6 Sol: 73.5 (#12)

| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | GPT-5.6 Sol |
|---|---|---|
| LMArena Text | — | 1456 |
| LMArena Creative Writing | — | 1450 |
| EQ-Bench Creative Writing | — | 1972 |
| EQ-Bench 4 | — | 1250 |
| LMArena Multi-Turn | — | 1456 |

## FAQ

### Is DeepSeek-V2 (MoE-236B, May 2024) better than GPT-5.6 Sol?

GPT-5.6 Sol has enough public results to be ranked (#6); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.

### Is DeepSeek-V2 (MoE-236B, May 2024) or GPT-5.6 Sol better for coding?

GPT-5.6 Sol scores higher on coding benchmarks: 61.1 versus 39.8 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and GPT-5.6 Sol share?

1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and GPT-5.6 Sol has 64.