Model comparison
Qwen2.5 72B Instruct vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 31.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 12 benchmarks with published results for both. Qwen2.5 72B Instruct 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 math, where Step 2 16k Exp 202412 leads 36.3 to 19.3.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 72B Instruct | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.9 | 39.2 |
| Released | 2024-09 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $5.60 | — |
| Results tracked | 43 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Qwen2.5 72B Instruct: 33.2 (#260), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1292 | 1316 |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| BigCodeBench Complete | 55.9% | — |
Agentic & Tool Use Not comparable
Qwen2.5 72B Instruct: 22.1 (#133), Step 2 16k Exp 202412: —
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Step 2 16k Exp 202412 leads
Qwen2.5 72B Instruct: 22.3 (#199), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1271 | 1299 |
| DTBench | 62.9% | — |
| LMCA | 13.4% | — |
| BIG-Bench Hard | 79.8% | — |
| Epoch Capabilities Index | 129 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |
Math Step 2 16k Exp 202412 leads
Qwen2.5 72B Instruct: 19.3 (#287), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1283 | 1304 |
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| Omni-MATH | 33% | — |
| MATH Level 5 | 63.2% | — |
Knowledge Step 2 16k Exp 202412 leads
Qwen2.5 72B Instruct: 27.0 (#253), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1245 | 1279 |
| GPQA Diamond | 49.1% | — |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |
Multilingual Step 2 16k Exp 202412 leads
Qwen2.5 72B Instruct: 41.0 (#213), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1252 | 1290 |
| LMArena Chinese | 1272 | 1331 |
| LMArena Russian | 1264 | 1324 |
| LMArena French | 1280 | — |
| LMArena German | 1234 | — |
| LMArena Japanese | 1180 | — |
| LMArena Korean | 1188 | — |
| LMArena Spanish | 1256 | — |
Instruction Following Step 2 16k Exp 202412 leads
Qwen2.5 72B Instruct: 65.5 (#221), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1287 |
| IFEval | 80.6% | — |
Long Context Too close to call
Qwen2.5 72B Instruct: 38.9 (#188), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1282 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Qwen2.5 72B Instruct: 46.7 (#215), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Qwen2.5 72B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1269 | 1321 |
| LMArena Creative Writing | 1221 | 1328 |
| LMArena Multi-Turn | 1272 | 1292 |
| WildBench | 80.2% | — |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 31.9 on the Noometry Index.
Is Qwen2.5 72B Instruct or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 33.2 in the Noometry coding category.
How many benchmarks do Qwen2.5 72B Instruct and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Step 2 16k Exp 202412 has 12.