# DeepSeek V4 Pro vs GPT-5-Codex

> DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 37.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-codex
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. DeepSeek V4 Pro scores higher in 3 categories and GPT-5-Codex in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 30.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 53.5% for DeepSeek V4 Pro and 70.3% for GPT-5-Codex.
- DeepSeek V4 Pro is cheaper at $0.66 / $1.98 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 400K.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 54.3 | 37.9 |
| Rank | 31 | 192 |
| Context | 1M | 400K |
| Input $/M | $0.66 | $1.25 |
| Output $/M | $1.98 | $10 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Pro: 52.4 (#34)
- GPT-5-Codex: 42.4 (#103)

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| WeirdML | 66.2% | 54.5% |
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| LMArena Coding | 1470 | — |
| ALE-Bench | 1,403 | — |

## Agentic & Tool Use

- DeepSeek V4 Pro: 32.8 (#58)
- GPT-5-Codex: 31.0 (#72)

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |

## Reasoning

- DeepSeek V4 Pro: 56.5 (#24)
- GPT-5-Codex: 30.9 (#83)

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 53.5% | 70.3% |
| ARC-AGI-2 | 61.3% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |

## Math

- DeepSeek V4 Pro: 64.8 (#30)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
| LMArena Math | 1455 | — |

## Knowledge

- DeepSeek V4 Pro: 59.5 (#31)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |

## Multilingual

- DeepSeek V4 Pro: 54.4 (#45)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1486 | — |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1458 | — |

## Instruction Following

- DeepSeek V4 Pro: 76.1 (#47)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1448 | — |

## Long Context

- DeepSeek V4 Pro: 45.0 (#51)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |

## Writing & Preference

- DeepSeek V4 Pro: 65.5 (#46)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Pro | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |

## FAQ

### Is DeepSeek V4 Pro better than GPT-5-Codex?

DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 37.9 on the Noometry Index.

### Which is cheaper, DeepSeek V4 Pro or GPT-5-Codex?

DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

### Is DeepSeek V4 Pro or GPT-5-Codex better for coding?

DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek V4 Pro does, with 1M tokens against 400K.

### How many benchmarks do DeepSeek V4 Pro and GPT-5-Codex share?

2 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and GPT-5-Codex has 3.