# DeepSeek V4 Flash vs GPT-5-Codex

> DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-flash-vs-gpt-5-codex
- Last updated: 2026-10-11
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 2 categories and GPT-5-Codex in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 30.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 52.2% for DeepSeek V4 Flash and 70.3% for GPT-5-Codex.
- DeepSeek V4 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 400K.
- DeepSeek V4 Flash has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 53.6 | 37.9 |
| Rank | 35 | 192 |
| Context | 1M | 400K |
| Input $/M | $0.15 | $1.25 |
| Output $/M | $0.60 | $10 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek V4 Flash: 47.9 (#59)
- GPT-5-Codex: 42.4 (#103)

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| WeirdML | 63% | 54.5% |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| LMArena Coding | 1457 | — |
| ALE-Bench | 1,306 | — |

## Agentic & Tool Use

- DeepSeek V4 Flash: —
- GPT-5-Codex: 31.0 (#72)

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |

## Reasoning

- DeepSeek V4 Flash: 53.7 (#30)
- GPT-5-Codex: 30.9 (#83)

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 70.3% |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| LMArena Hard Prompts | 1444 | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.49 | — |

## Math

- DeepSeek V4 Flash: 60.3 (#37)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
| LMArena Math | 1427 | — |

## Knowledge

- DeepSeek V4 Flash: 55.4 (#48)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
| LMArena Expert | 1441 | — |

## Multilingual

- DeepSeek V4 Flash: 53.0 (#72)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1468 | — |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1436 | — |

## Instruction Following

- DeepSeek V4 Flash: 74.9 (#81)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1421 | — |

## Long Context

- DeepSeek V4 Flash: 43.8 (#85)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 1434 | — |

## Writing & Preference

- DeepSeek V4 Flash: 63.8 (#61)
- GPT-5-Codex: —

| Benchmark | DeepSeek V4 Flash | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1432 | — |
| LMArena Creative Writing | 1403 | — |
| EQ-Bench Creative Writing | 1559 | — |
| LMArena Multi-Turn | 1449 | — |

## FAQ

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

DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 37.9 on the Noometry Index.

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

DeepSeek V4 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

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

DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

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

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

2 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and GPT-5-Codex has 3.