Model comparison
Deepseek Coder v2 vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 35.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
StepFunSummary
- They share 12 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Step 2 16k Exp 202412 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 2 16k Exp 202412 leads 52.3 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 35.9 | 39.2 |
| Released | 2024-06-17 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Deepseek Coder v2: 38.1 (#183), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Deepseek Coder v2 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1251 | 1316 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Step 2 16k Exp 202412 leads
Deepseek Coder v2: 23.6 (#176), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Deepseek Coder v2 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1299 |
| WinoGrande | 83.7% | — |
Math Step 2 16k Exp 202412 leads
Deepseek Coder v2: 34.9 (#190), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Deepseek Coder v2 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1241 | 1304 |
| GSM8K | 94.5% | — |
Knowledge Step 2 16k Exp 202412 leads
Deepseek Coder v2: 32.3 (#212), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Deepseek Coder v2 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1181 | 1279 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Step 2 16k Exp 202412 leads
Deepseek Coder v2: 36.3 (#240), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Deepseek Coder v2 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1182 | 1290 |
| LMArena Chinese | 1201 | 1331 |
| LMArena Russian | 1188 | 1324 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Step 2 16k Exp 202412 leads
Deepseek Coder v2: 61.7 (#242), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Deepseek Coder v2 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1180 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Deepseek Coder v2: 37.0 (#224), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Deepseek Coder v2 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1219 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Deepseek Coder v2: 38.2 (#253), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Deepseek Coder v2 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1191 | 1321 |
| LMArena Creative Writing | 1120 | 1328 |
| LMArena Multi-Turn | 1177 | 1292 |
Frequently asked questions
Is Deepseek Coder v2 better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Step 2 16k Exp 202412 better for coding?
They score almost the same on coding (38.1 vs 38.5); test both on your own repository before choosing.
How many benchmarks do Deepseek Coder v2 and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Step 2 16k Exp 202412 has 12.