Model comparison
Qwen3-Coder 480B-A35B Instruct vs Step 2 16k Exp 202412
Qwen3-Coder 480B-A35B Instruct and Step 2 16k Exp 202412 score almost the same on the Noometry Index (37.7 vs 38.6), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 12 benchmarks with published results for both. Qwen3-Coder 480B-A35B Instruct scores higher in 6 categories and Step 2 16k Exp 202412 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen3-Coder 480B-A35B Instruct leads 47.8 to 43.9.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 37.7 | 38.6 |
| Released | 2025-04 | — |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.50 | — |
| Output $ / M tokens | $7.50 | — |
| Results tracked | 25 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Qwen3-Coder 480B-A35B Instruct: 36.2 (#199), Step 2 16k Exp 202412: 37.9 (#170)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1413 | 1316 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1275 | — |
| GSO | 4.9% | — |
| WeirdML | 41.2% | — |
| ALE-Bench | 461.45 | — |
| AlgoTune | 1.44 | — |
Agentic & Tool Use Not comparable
Qwen3-Coder 480B-A35B Instruct: 23.7 (#116), Step 2 16k Exp 202412: —
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| Terminal-Bench | 27.2% | — |
Reasoning Too close to call
Qwen3-Coder 480B-A35B Instruct: 24.7 (#141), Step 2 16k Exp 202412: 24.8 (#140)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1299 |
| Kagi LLM Benchmark | 49.5% | — |
Math Qwen3-Coder 480B-A35B Instruct leads
Qwen3-Coder 480B-A35B Instruct: 34.9 (#151), Step 2 16k Exp 202412: 33.6 (#171)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1364 | 1305 |
Knowledge Qwen3-Coder 480B-A35B Instruct leads
Qwen3-Coder 480B-A35B Instruct: 36.4 (#159), Step 2 16k Exp 202412: 34.6 (#187)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1337 | 1279 |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
Qwen3-Coder 480B-A35B Instruct: 47.8 (#143), Step 2 16k Exp 202412: 43.9 (#176)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1345 | 1290 |
| LMArena Chinese | 1356 | 1331 |
| LMArena Russian | 1367 | 1324 |
| LMArena French | 1394 | — |
| LMArena German | 1324 | — |
| LMArena Japanese | 1309 | — |
| LMArena Korean | 1307 | — |
| LMArena Spanish | 1360 | — |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
Qwen3-Coder 480B-A35B Instruct: 71.8 (#142), Step 2 16k Exp 202412: 68.1 (#187)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1356 | 1287 |
Long Context Qwen3-Coder 480B-A35B Instruct leads
Qwen3-Coder 480B-A35B Instruct: 42.0 (#126), Step 2 16k Exp 202412: 39.7 (#165)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1379 | 1307 |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
Qwen3-Coder 480B-A35B Instruct: 55.5 (#142), Step 2 16k Exp 202412: 52.5 (#168)
| Benchmark | Qwen3-Coder 480B-A35B Instruct | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1356 | 1321 |
| LMArena Creative Writing | 1333 | 1328 |
| LMArena Multi-Turn | 1365 | 1292 |
Frequently asked questions
Is Qwen3-Coder 480B-A35B Instruct better than Step 2 16k Exp 202412?
Qwen3-Coder 480B-A35B Instruct and Step 2 16k Exp 202412 score almost the same on the Noometry Index (37.7 vs 38.6), so choose on price, context window or the category you care about most.
Is Qwen3-Coder 480B-A35B Instruct or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 37.9 versus 36.2 in the Noometry coding category.
How many benchmarks do Qwen3-Coder 480B-A35B Instruct and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Qwen3-Coder 480B-A35B Instruct has 25 scored results on Noometry and Step 2 16k Exp 202412 has 12.