Model comparison
Qwen2.5-Coder-32B vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 33.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Qwen2.5-Coder-32B scores higher in 1 category and Qwen3-Next 80B-A3B Instruct in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3-Next 80B-A3B Instruct leads 42.5 to 22.6.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $0.50 / $2 for Qwen3-Next 80B-A3B Instruct.
- Qwen3-Next 80B-A3B Instruct accepts more context: 131K tokens versus 33K.
Side by side
| Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 33.4 | 43.0 |
| Released | 2024-09-18 | 2025-09 |
| Weights | Open | Open |
| Context window | 33K | 131K |
| Max output | 29K | 33K |
| Input $ / M tokens | $0.66 | $0.50 |
| Output $ / M tokens | $1 | $2 |
| Results tracked | 31 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Next 80B-A3B Instruct leads
Qwen2.5-Coder-32B: 22.6 (#333), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1276 | 1440 |
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| BigCodeBench Complete | 58% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
Qwen2.5-Coder-32B: 21.2 (#225), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1428 |
| Kagi LLM Benchmark | — | 66.7% |
| LiveBench Reasoning | 42.1% | — |
| LiveBench Data Analysis | 49.9% | — |
| Epoch Capabilities Index | 119.49 | — |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |
Math Qwen3-Next 80B-A3B Instruct leads
Qwen2.5-Coder-32B: 33.3 (#204), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Math | 1251 | 1440 |
| Omni-MATH | — | 46.7% |
| LiveBench Math | 46.6% | — |
| GSM8K | 93% | — |
Knowledge Qwen3-Next 80B-A3B Instruct leads
Qwen2.5-Coder-32B: 33.4 (#203), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Expert | 1221 | 1417 |
| MMLU-Pro | — | 78.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 63% |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |
Multilingual Qwen3-Next 80B-A3B Instruct leads
Qwen2.5-Coder-32B: 37.8 (#235), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1205 | 1407 |
| LMArena Chinese | 1222 | 1460 |
| LMArena Russian | 1228 | 1404 |
| LMArena French | — | 1413 |
| LMArena German | — | 1417 |
| LMArena Japanese | — | 1395 |
| LMArena Korean | — | 1364 |
| LMArena Spanish | — | 1435 |
Instruction Following Qwen3-Next 80B-A3B Instruct leads
Qwen2.5-Coder-32B: 61.4 (#245), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Instruction Following | 1223 | 1389 |
| LiveBench Instruction Following | 58.7% | — |
| IFEval | — | 81% |
Long Context Too close to call
Qwen2.5-Coder-32B: 38.0 (#208), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Longer Query | 1251 | 1403 |
| Fiction.LiveBench | — | 55.6% |
Writing & Preference Qwen3-Next 80B-A3B Instruct leads
Qwen2.5-Coder-32B: 41.6 (#240), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
| Benchmark | Qwen2.5-Coder-32B | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1230 | 1417 |
| LMArena Creative Writing | 1174 | 1334 |
| LMArena Multi-Turn | 1222 | 1416 |
| WildBench | — | 80.7% |
| LiveBench Language | 23.3% | — |
Frequently asked questions
Is Qwen2.5-Coder-32B better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 33.4 on the Noometry Index.
Which is cheaper, Qwen2.5-Coder-32B or Qwen3-Next 80B-A3B Instruct?
Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.
Is Qwen2.5-Coder-32B or Qwen3-Next 80B-A3B Instruct better for coding?
Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Next 80B-A3B Instruct does, with 131K tokens against 33K.
How many benchmarks do Qwen2.5-Coder-32B and Qwen3-Next 80B-A3B Instruct share?
12 benchmarks have published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.