Model comparison
DeepSeek-V3.1-Terminus vs GPT-5-Codex
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 37.3 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and GPT-5-Codex in 2 categories; one gap is clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 25.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 70.3% for GPT-5-Codex.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 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-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | GPT-5-Codex | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.6 | 37.3 |
| Released | 2025-09-22 | 2025-09-15 |
| Weights | Open | Proprietary |
| Context window | 164K | 400K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $1.25 |
| Output $ / M tokens | $1 | $10 |
| Results tracked | 16 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3.1-Terminus: 41.5 (#114), GPT-5-Codex: 41.9 (#100)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5-Codex |
|---|---|---|
| SciCode | 40.6% | — |
| WeirdML | — | 54.5% |
| LMArena Coding | 1426 | — |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, GPT-5-Codex: 30.8 (#66)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
Reasoning GPT-5-Codex leads
DeepSeek-V3.1-Terminus: 25.7 (#126), GPT-5-Codex: 30.0 (#80)
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 70.3% |
| CritPt | 1.7% | — |
| LMArena Hard Prompts | 1427 | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Not comparable
DeepSeek-V3.1-Terminus: 35.7 (#138), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5-Codex |
|---|---|---|
| LMArena Math | 1402 | — |
Multilingual Not comparable
DeepSeek-V3.1-Terminus: 52.3 (#87), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1407 | — |
| LMArena Russian | 1434 | — |
Instruction Following Not comparable
DeepSeek-V3.1-Terminus: 74.4 (#96), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1406 | — |
Long Context Not comparable
DeepSeek-V3.1-Terminus: 43.5 (#88), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 1426 | — |
Writing & Preference Not comparable
DeepSeek-V3.1-Terminus: 61.3 (#87), GPT-5-Codex: —
| Benchmark | DeepSeek-V3.1-Terminus | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1404 | — |
| LMArena Multi-Turn | 1411 | — |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than GPT-5-Codex?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 37.3 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or GPT-5-Codex?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; GPT-5-Codex lists at $1.25 and $10.
Is DeepSeek-V3.1-Terminus or GPT-5-Codex better for coding?
They score almost the same on coding (41.5 vs 41.9); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5-Codex does, with 400K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and GPT-5-Codex share?
1 benchmark has published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and GPT-5-Codex has 3.