Model comparison
Deepseek Coder v2 vs Step 1o Turbo 202506
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 35.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
StepFunSummary
- They share 13 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Step 1o Turbo 202506 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 1o Turbo 202506 leads 53.1 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 35.9 | 39.7 |
| Released | 2024-06-17 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 1o Turbo 202506 leads
Deepseek Coder v2: 38.1 (#183), Step 1o Turbo 202506: 39.2 (#160)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | 1251 | 1339 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Step 1o Turbo 202506 leads
Deepseek Coder v2: 23.6 (#176), Step 1o Turbo 202506: 26.8 (#129)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1335 |
| WinoGrande | 83.7% | — |
Math Step 1o Turbo 202506 leads
Deepseek Coder v2: 34.9 (#190), Step 1o Turbo 202506: 36.6 (#164)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | 1241 | 1318 |
| GSM8K | 94.5% | — |
Knowledge Step 1o Turbo 202506 leads
Deepseek Coder v2: 32.3 (#212), Step 1o Turbo 202506: 36.1 (#176)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | 1181 | 1308 |
| ARC (AI2) Challenge | 64.3% | — |
Multimodal Not comparable
Deepseek Coder v2: —, Step 1o Turbo 202506: 36.1 (#80)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | — | 1186 |
Multilingual Step 1o Turbo 202506 leads
Deepseek Coder v2: 36.3 (#240), Step 1o Turbo 202506: 45.3 (#173)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | 1182 | 1313 |
| LMArena Chinese | 1201 | 1380 |
| LMArena German | 1164 | 1314 |
| LMArena Russian | 1188 | 1327 |
| LMArena French | 1185 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Step 1o Turbo 202506 leads
Deepseek Coder v2: 61.7 (#242), Step 1o Turbo 202506: 69.2 (#176)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1310 |
Long Context Step 1o Turbo 202506 leads
Deepseek Coder v2: 37.0 (#224), Step 1o Turbo 202506: 41.0 (#146)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | 1219 | 1348 |
Writing & Preference Step 1o Turbo 202506 leads
Deepseek Coder v2: 38.2 (#253), Step 1o Turbo 202506: 53.1 (#160)
| Benchmark | Deepseek Coder v2 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | 1191 | 1336 |
| LMArena Creative Writing | 1120 | 1307 |
| LMArena Multi-Turn | 1177 | 1340 |
Frequently asked questions
Is Deepseek Coder v2 better than Step 1o Turbo 202506?
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Step 1o Turbo 202506 better for coding?
Step 1o Turbo 202506 scores higher on coding benchmarks: 39.2 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Step 1o Turbo 202506 share?
13 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Step 1o Turbo 202506 has 14.