Model comparison
DeepSeek V4.1 Flash vs Step 2 16k Exp 202412
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 39.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
DeepSeek
StepFunSummary
- They share 12 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Step 2 16k Exp 202412 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 36.3.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 52.8 | 39.2 |
| Released | 2026-09-09 | — |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 37 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1506 | 1316 |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| ALE-Bench | 1,092 | — |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: 31.2 (#69), Step 2 16k Exp 202412: —
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1299 |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| Epoch Capabilities Index | 154.9 | — |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1477 | 1304 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 54% | — |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1506 | 1279 |
| GPQA Diamond | 89.8% | — |
Multimodal Not comparable
DeepSeek V4.1 Flash: 39.1 (#61), Step 2 16k Exp 202412: —
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1448 | 1290 |
| LMArena Chinese | 1497 | 1331 |
| LMArena Russian | 1471 | 1324 |
| LMArena French | 1452 | — |
| LMArena German | 1484 | — |
| LMArena Japanese | 1412 | — |
| LMArena Korean | 1452 | — |
| LMArena Spanish | 1459 | — |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1474 | 1287 |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1475 | 1307 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | DeepSeek V4.1 Flash | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1462 | 1321 |
| LMArena Creative Writing | 1435 | 1328 |
| LMArena Multi-Turn | 1457 | 1292 |
| EQ-Bench Creative Writing | 1540 | — |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Step 2 16k Exp 202412?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 39.2 on the Noometry Index.
Is DeepSeek V4.1 Flash or Step 2 16k Exp 202412 better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 38.5 in the Noometry coding category.
How many benchmarks do DeepSeek V4.1 Flash and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Step 2 16k Exp 202412 has 12.