Model comparison
DeepSeek-V3.1 vs GPT-5-Codex
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 37.9 on the Noometry Index.
Last verified . 2 shared benchmarks.
DeepSeekSummary
- They share 2 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 0 categories and GPT-5-Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 53.2% for DeepSeek-V3.1 and 70.3% for GPT-5-Codex.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | GPT-5-Codex | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.8 | 37.9 |
| Released | 2025-08-21 | 2025-09-15 |
| Weights | Open | Proprietary |
| Context window | 164K | 400K |
| Max output | 8K | 128K |
| Input $ / M tokens | $0.25 | $1.25 |
| Output $ / M tokens | $0.95 | $10 |
| Results tracked | 27 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
DeepSeek-V3.1: 40.3 (#144), GPT-5-Codex: 42.4 (#103)
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| WeirdML | 38.4% | 54.5% |
| LMArena Coding | 1417 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, GPT-5-Codex: 31.0 (#72)
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
Reasoning GPT-5-Codex leads
DeepSeek-V3.1: 27.9 (#110), GPT-5-Codex: 30.9 (#83)
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 70.3% |
| SimpleBench | 40% | — |
| LMArena Hard Prompts | 1417 | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Not comparable
DeepSeek-V3.1: 38.9 (#122), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| LMArena Math | 1420 | — |
Knowledge Not comparable
DeepSeek-V3.1: 43.7 (#90), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |
Multilingual Not comparable
DeepSeek-V3.1: 51.6 (#106), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Not comparable
DeepSeek-V3.1: 73.9 (#110), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1400 | — |
Long Context Not comparable
DeepSeek-V3.1: 36.3 (#232), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| Fiction.LiveBench | 52.8% | — |
| LMArena Longer Query | 1422 | — |
Writing & Preference Not comparable
DeepSeek-V3.1: 60.3 (#98), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1 | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1436 | — |
| LMArena Multi-Turn | 1408 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than GPT-5-Codex?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 37.9 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1 or GPT-5-Codex?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is DeepSeek-V3.1 or GPT-5-Codex better for coding?
GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 40.3 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-V3.1 and GPT-5-Codex share?
2 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and GPT-5-Codex has 3.