Model comparison
DeepSeek LLM 67B vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
StepFunSummary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Step 2 16k Exp 202412 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 2 16k Exp 202412 leads 35.2 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 24.9 | 39.2 |
| Released | 2023-11-29 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
DeepSeek LLM 67B: 31.9 (#278), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | DeepSeek LLM 67B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1096 | 1316 |
Reasoning Step 2 16k Exp 202412 leads
DeepSeek LLM 67B: 16.5 (#304), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | DeepSeek LLM 67B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1299 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Step 2 16k Exp 202412 leads
DeepSeek LLM 67B: 8.7 (#324), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | DeepSeek LLM 67B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1108 | 1304 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Step 2 16k Exp 202412 leads
DeepSeek LLM 67B: 7.0 (#313), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | DeepSeek LLM 67B | Step 2 16k Exp 202412 |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1279 |
Multilingual Step 2 16k Exp 202412 leads
DeepSeek LLM 67B: 29.4 (#267), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | DeepSeek LLM 67B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1073 | 1290 |
| LMArena Chinese | 1132 | 1331 |
| LMArena Russian | — | 1324 |
Instruction Following Step 2 16k Exp 202412 leads
DeepSeek LLM 67B: 55.4 (#277), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | DeepSeek LLM 67B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1079 | 1287 |
Long Context Step 2 16k Exp 202412 leads
DeepSeek LLM 67B: 33.1 (#265), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | DeepSeek LLM 67B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1092 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
DeepSeek LLM 67B: 31.6 (#282), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | DeepSeek LLM 67B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1105 | 1321 |
| LMArena Creative Writing | 1067 | 1328 |
| LMArena Multi-Turn | 1082 | 1292 |
Frequently asked questions
Is DeepSeek LLM 67B better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Step 2 16k Exp 202412 share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Step 2 16k Exp 202412 has 12.