# DeepSeek-V3.2-Exp vs GPT-5-Codex

> DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 37.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-2-exp-vs-gpt-5-codex
- Last updated: 2026-10-11
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 2 categories and GPT-5-Codex in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 22.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 52.2% for DeepSeek-V3.2-Exp and 70.3% for GPT-5-Codex.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 164K.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 44.3 | 37.9 |
| Rank | 78 | 192 |
| Context | 164K | 400K |
| Input $/M | $0.26 | $1.25 |
| Output $/M | $0.38 | $10 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.2-Exp: 46.5 (#65)
- GPT-5-Codex: 42.4 (#103)

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| WeirdML | 39.5% | 54.5% |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| LMArena Coding | 1454 | — |

## Agentic & Tool Use

- DeepSeek-V3.2-Exp: 32.7 (#59)
- GPT-5-Codex: 31.0 (#72)

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | 39.6% | 44.3% |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |

## Reasoning

- DeepSeek-V3.2-Exp: 22.1 (#208)
- GPT-5-Codex: 30.9 (#83)

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 70.3% |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| LMArena Hard Prompts | 1434 | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.27 | — |

## Math

- DeepSeek-V3.2-Exp: 41.7 (#87)
- GPT-5-Codex: —

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| LMArena Math | 1435 | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- DeepSeek-V3.2-Exp: 51.7 (#66)
- GPT-5-Codex: —

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
| LMArena Expert | 1436 | — |

## Multilingual

- DeepSeek-V3.2-Exp: 52.2 (#90)
- GPT-5-Codex: —

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1409 | — |
| LMArena Chinese | 1461 | — |
| LMArena French | 1433 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1371 | — |
| LMArena Russian | 1424 | — |
| LMArena Spanish | 1440 | — |

## Instruction Following

- DeepSeek-V3.2-Exp: 74.5 (#93)
- GPT-5-Codex: —

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1413 | — |

## Long Context

- DeepSeek-V3.2-Exp: 47.6 (#16)
- GPT-5-Codex: —

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
| LMArena Longer Query | 1428 | — |

## Writing & Preference

- DeepSeek-V3.2-Exp: 62.4 (#77)
- GPT-5-Codex: —

| Benchmark | DeepSeek-V3.2-Exp | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1425 | — |
| LMArena Creative Writing | 1403 | — |
| EQ-Bench Creative Writing | 1515 | — |
| LMArena Multi-Turn | 1427 | — |

## FAQ

### Is DeepSeek-V3.2-Exp better than GPT-5-Codex?

DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 37.9 on the Noometry Index.

### Which is cheaper, DeepSeek-V3.2-Exp or GPT-5-Codex?

DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

### Is DeepSeek-V3.2-Exp or GPT-5-Codex better for coding?

DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

GPT-5-Codex does, with 400K tokens against 164K.

### How many benchmarks do DeepSeek-V3.2-Exp and GPT-5-Codex share?

3 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and GPT-5-Codex has 3.