Model comparison
Deepseek Coder v2 vs Step 3.7 Flash
Step 3.7 Flash is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
StepFunSummary
- The widest gap is in math, where Step 3.7 Flash leads 42.9 to 34.9.
Side by side
| Deepseek Coder v2 | Step 3.7 Flash | |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 35.9 | 37.3 |
| Released | 2024-06-17 | 2026-05-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.18 |
| Output $ / M tokens | — | $1.11 |
| Results tracked | 24 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.7 Flash leads
Deepseek Coder v2: 38.1 (#183), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| SciCode | — | 40% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 694.12 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | — | 39.7% |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1207 | — |
| WinoGrande | 83.7% | — |
Math Step 3.7 Flash leads
Deepseek Coder v2: 34.9 (#190), Step 3.7 Flash: 42.9 (#82)
| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Step 3.7 Flash: —
| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), Step 3.7 Flash: —
| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Not comparable
Deepseek Coder v2: 61.7 (#242), Step 3.7 Flash: —
| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), Step 3.7 Flash: —
| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Not comparable
Deepseek Coder v2: 38.2 (#253), Step 3.7 Flash: —
| Benchmark | Deepseek Coder v2 | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than Step 3.7 Flash?
Step 3.7 Flash is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Step 3.7 Flash better for coding?
Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Step 3.7 Flash share?
0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Step 3.7 Flash has 5.