Model comparison
Qwen2-72B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 30.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 17 benchmarks with published results for both. Qwen2-72B scores higher in 1 category and Step 3.5 Flash in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3.5 Flash leads 39.6 to 21.2.
Side by side
| Qwen2-72B | Step 3.5 Flash | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 30.0 | 42.3 |
| Released | 2024-06-07 | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 26 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Qwen2-72B: 29.1 (#310), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1196 | 1436 |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Not comparable
Qwen2-72B: 17.0 (#146), Step 3.5 Flash: —
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Too close to call
Qwen2-72B: 23.2 (#181), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| Epoch Capabilities Index | 125.28 | — |
Math Step 3.5 Flash leads
Qwen2-72B: 30.2 (#236), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1235 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| MATH Level 5 | 39.1% | — |
Knowledge Step 3.5 Flash leads
Qwen2-72B: 21.2 (#275), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1171 | 1421 |
| GPQA Diamond | 40.8% | — |
| MMLU | 82.4% | — |
Multilingual Step 3.5 Flash leads
Qwen2-72B: 35.9 (#244), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1176 | 1385 |
| LMArena Chinese | 1240 | 1447 |
| LMArena French | 1170 | 1421 |
| LMArena German | 1151 | 1405 |
| LMArena Japanese | 1111 | 1354 |
| LMArena Korean | 1083 | 1352 |
| LMArena Russian | 1169 | 1385 |
| LMArena Spanish | 1169 | 1419 |
Instruction Following Step 3.5 Flash leads
Qwen2-72B: 61.7 (#241), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1181 | 1385 |
Long Context Step 3.5 Flash leads
Qwen2-72B: 36.1 (#235), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1192 | 1402 |
Writing & Preference Step 3.5 Flash leads
Qwen2-72B: 40.8 (#241), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Qwen2-72B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1203 | 1403 |
| LMArena Creative Writing | 1181 | 1357 |
| LMArena Multi-Turn | 1196 | 1405 |
Frequently asked questions
Is Qwen2-72B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 30.0 on the Noometry Index.
Is Qwen2-72B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Step 3.5 Flash share?
17 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Step 3.5 Flash has 19.