Model comparison
DeepSeek Coder 33B vs Step 1o Turbo 202506
Step 1o Turbo 202506 has enough public results to be ranked (#160); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
StepFunSummary
- DeepSeek Coder 33B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek Coder 33B | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 38.3 | 39.1 |
| Released | 2023-11-02 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 1o Turbo 202506 leads
DeepSeek Coder 33B: 37.4 (#180), Step 1o Turbo 202506: 38.6 (#158)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| BigCodeBench Instruct | 42% | — |
| LMArena Coding | — | 1339 |
| BigCodeBench Complete | 51.1% | — |
| HumanEval+ | 75% | — |
| MBPP+ | 70.1% | — |
Reasoning Not comparable
DeepSeek Coder 33B: —, Step 1o Turbo 202506: 25.7 (#127)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | — | 1336 |
| Epoch Capabilities Index | 95.74 | — |
| WinoGrande | 62% | — |
Math Not comparable
DeepSeek Coder 33B: —, Step 1o Turbo 202506: 33.9 (#163)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | — | 1318 |
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, Step 1o Turbo 202506: 35.5 (#174)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | — | 1308 |
| ARC (AI2) Challenge | 42.2% | — |
| MMLU | 39.4% | — |
Multimodal Not comparable
DeepSeek Coder 33B: —, Step 1o Turbo 202506: 35.4 (#75)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | — | 1186 |
Multilingual Not comparable
DeepSeek Coder 33B: —, Step 1o Turbo 202506: 45.5 (#168)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | — | 1313 |
| LMArena Chinese | — | 1380 |
| LMArena German | — | 1315 |
| LMArena Russian | — | 1327 |
Instruction Following Not comparable
DeepSeek Coder 33B: —, Step 1o Turbo 202506: 69.4 (#171)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | — | 1311 |
Long Context Not comparable
DeepSeek Coder 33B: —, Step 1o Turbo 202506: 41.1 (#141)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | — | 1350 |
Writing & Preference Not comparable
DeepSeek Coder 33B: —, Step 1o Turbo 202506: 53.4 (#154)
| Benchmark | DeepSeek Coder 33B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | — | 1336 |
| LMArena Creative Writing | — | 1308 |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is DeepSeek Coder 33B better than Step 1o Turbo 202506?
Step 1o Turbo 202506 has enough public results to be ranked (#160); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 33B or Step 1o Turbo 202506 better for coding?
Step 1o Turbo 202506 scores higher on coding benchmarks: 38.6 versus 37.4 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 33B and Step 1o Turbo 202506 share?
0 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Step 1o Turbo 202506 has 14.