Model comparison
Qwen3.7 Max vs Step 2 16k Exp 202412
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 39.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 12 benchmarks with published results for both. Qwen3.7 Max 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 knowledge, where Qwen3.7 Max leads 61.6 to 35.2.
Side by side
| Qwen3.7 Max | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 51.5 | 39.2 |
| Released | 2026-05-19 | — |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 33 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Qwen3.7 Max: 50.4 (#45), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1498 | 1316 |
| SWE-bench Verified | 77.3% | — |
| LMArena WebDev | 1515 | — |
| SciCode | 48.8% | — |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use Not comparable
Qwen3.7 Max: 22.1 (#135), Step 2 16k Exp 202412: —
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| GBAEval | 0.4% | — |
Reasoning Qwen3.7 Max leads
Qwen3.7 Max: 49.2 (#38), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1299 |
| SimpleBench | 70.4% | — |
| NYT Connections (extended) | 85.1% | — |
| CritPt | 13.4% | — |
| Chess Puzzles | 19% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 32% | — |
| DTBench | 92.3% | — |
| LMCA | 44% | — |
| Epoch Capabilities Index | 153.68 | — |
Math Qwen3.7 Max leads
Qwen3.7 Max: 62.4 (#32), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1490 | 1304 |
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 34.1% | — |
| OTIS Mock AIME 2024-2025 | 95.6% | — |
| ProofBench | 26% | — |
Knowledge Qwen3.7 Max leads
Qwen3.7 Max: 61.6 (#28), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1488 | 1279 |
| GPQA Diamond | 90.9% | — |
| SimpleQA Verified | 55.8% | — |
Multilingual Qwen3.7 Max leads
Qwen3.7 Max: 56.9 (#15), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1474 | 1290 |
| LMArena Chinese | 1530 | 1331 |
| LMArena Russian | 1484 | 1324 |
Instruction Following Qwen3.7 Max leads
Qwen3.7 Max: 76.7 (#38), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1460 | 1287 |
Long Context Qwen3.7 Max leads
Qwen3.7 Max: 45.4 (#40), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1482 | 1307 |
Writing & Preference Qwen3.7 Max leads
Qwen3.7 Max: 65.0 (#54), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Qwen3.7 Max | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1476 | 1321 |
| LMArena Creative Writing | 1449 | 1328 |
| LMArena Multi-Turn | 1481 | 1292 |
| EQ-Bench 4 | 1110 | — |
Frequently asked questions
Is Qwen3.7 Max better than Step 2 16k Exp 202412?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 39.2 on the Noometry Index.
Is Qwen3.7 Max or Step 2 16k Exp 202412 better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 38.5 in the Noometry coding category.
How many benchmarks do Qwen3.7 Max and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Qwen3.7 Max has 33 scored results on Noometry and Step 2 16k Exp 202412 has 12.