Model comparison
DeepSeek Coder 33B vs GPT-5-Codex
GPT-5-Codex has enough public results to be ranked (#192); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in coding, where GPT-5-Codex leads 42.4 to 38.0.
- DeepSeek Coder 33B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek Coder 33B | GPT-5-Codex | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 38.9 | 37.9 |
| Released | 2023-11-02 | 2025-09-15 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $10 |
| Results tracked | 9 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5-Codex leads
DeepSeek Coder 33B: 38.0 (#184), GPT-5-Codex: 42.4 (#103)
| Benchmark | DeepSeek Coder 33B | GPT-5-Codex |
|---|---|---|
| WeirdML | — | 54.5% |
| BigCodeBench Instruct | 42% | — |
| BigCodeBench Complete | 51.1% | — |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Agentic & Tool Use Not comparable
DeepSeek Coder 33B: —, GPT-5-Codex: 31.0 (#72)
| Benchmark | DeepSeek Coder 33B | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
Reasoning Not comparable
DeepSeek Coder 33B: —, GPT-5-Codex: 30.9 (#83)
| Benchmark | DeepSeek Coder 33B | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | — | 70.3% |
| Epoch Capabilities Index | 96.32 | — |
| WinoGrande | 62% | — |
Math Not comparable
DeepSeek Coder 33B: —, GPT-5-Codex: —
| Benchmark | DeepSeek Coder 33B | GPT-5-Codex |
|---|---|---|
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, GPT-5-Codex: —
| Benchmark | DeepSeek Coder 33B | GPT-5-Codex |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |
Frequently asked questions
Is DeepSeek Coder 33B better than GPT-5-Codex?
GPT-5-Codex has enough public results to be ranked (#192); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or GPT-5-Codex better for coding?
GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 38.0 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and GPT-5-Codex share?
0 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and GPT-5-Codex has 3.