Model comparison
gpt-oss-120b vs Qwen3-Next 80B-A3B Instruct
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 36.3 on the Noometry Index. gpt-oss-120b costs 12× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Qwen3-Next 80B-A3B Instruct in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 52.5 to 38.8.
- The biggest single-benchmark swing is Omni-MATH: 68.8% for gpt-oss-120b and 46.7% for Qwen3-Next 80B-A3B Instruct.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.50 / $2 for Qwen3-Next 80B-A3B Instruct.
Side by side
| gpt-oss-120b | Qwen3-Next 80B-A3B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.3 | 43.0 |
| Released | 2025-08-05 | 2025-09 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 41K | 33K |
| Input $ / M tokens | $0.037 | $0.50 |
| Output $ / M tokens | $0.17 | $2 |
| Results tracked | 48 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Next 80B-A3B Instruct leads
gpt-oss-120b: 33.5 (#256), Qwen3-Next 80B-A3B Instruct: 42.5 (#98)
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Coding | 1380 | 1440 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.2 (#153), Qwen3-Next 80B-A3B Instruct: —
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Qwen3-Next 80B-A3B Instruct leads
gpt-oss-120b: 20.0 (#245), Qwen3-Next 80B-A3B Instruct: 31.1 (#81)
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 58.6% | 66.7% |
| LMArena Hard Prompts | 1364 | 1428 |
| SimpleBench | 22.1% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | 20% | — |
| Mystery Game Puzzles | 2% | — |
| DTBench | 76.3% | — |
| LMCA | 22.1% | — |
| Surface Evolver Bench | 25% | — |
| Epoch Capabilities Index | 139.93 | — |
Math gpt-oss-120b leads
gpt-oss-120b: 52.5 (#50), Qwen3-Next 80B-A3B Instruct: 38.8 (#126)
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Omni-MATH | 68.8% | 46.7% |
| LMArena Math | 1389 | 1440 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
Knowledge Too close to call
gpt-oss-120b: 42.4 (#96), Qwen3-Next 80B-A3B Instruct: 41.8 (#106)
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| MMLU-Pro | 79.5% | 78.6% |
| Vectara Hallucination Rate | 14.2% | 9.3% |
| GPQA (HELM) | 68.4% | 63% |
| LMArena Expert | 1356 | 1417 |
| GPQA Diamond | 75.8% | — |
| Confabulations | 15.7% | — |
Multilingual Qwen3-Next 80B-A3B Instruct leads
gpt-oss-120b: 48.0 (#147), Qwen3-Next 80B-A3B Instruct: 52.1 (#93)
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Non-English | 1351 | 1407 |
| LMArena Chinese | 1385 | 1460 |
| LMArena French | 1369 | 1413 |
| LMArena German | 1353 | 1417 |
| LMArena Japanese | 1331 | 1395 |
| LMArena Korean | 1282 | 1364 |
| LMArena Russian | 1343 | 1404 |
| LMArena Spanish | 1389 | 1435 |
Instruction Following Qwen3-Next 80B-A3B Instruct leads
gpt-oss-120b: 69.3 (#173), Qwen3-Next 80B-A3B Instruct: 70.8 (#159)
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| IFEval | 83.6% | 81% |
| LMArena Instruction Following | 1318 | 1389 |
Long Context Qwen3-Next 80B-A3B Instruct leads
gpt-oss-120b: 31.4 (#278), Qwen3-Next 80B-A3B Instruct: 37.0 (#223)
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| Fiction.LiveBench | 44.4% | 55.6% |
| LMArena Longer Query | 1319 | 1403 |
Writing & Preference Qwen3-Next 80B-A3B Instruct leads
gpt-oss-120b: 46.5 (#217), Qwen3-Next 80B-A3B Instruct: 58.0 (#121)
| Benchmark | gpt-oss-120b | Qwen3-Next 80B-A3B Instruct |
|---|---|---|
| LMArena Text | 1365 | 1417 |
| LMArena Creative Writing | 1275 | 1334 |
| WildBench | 84.5% | 80.7% |
| LMArena Multi-Turn | 1340 | 1416 |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
Frequently asked questions
Is gpt-oss-120b better than Qwen3-Next 80B-A3B Instruct?
Qwen3-Next 80B-A3B Instruct is the stronger model overall, scoring 43.0 to 36.3 on the Noometry Index. gpt-oss-120b costs 12× less per token, which makes it the better buy when Qwen3-Next 80B-A3B Instruct's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Qwen3-Next 80B-A3B Instruct?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Qwen3-Next 80B-A3B Instruct lists at $0.50 and $2.
Is gpt-oss-120b or Qwen3-Next 80B-A3B Instruct better for coding?
Qwen3-Next 80B-A3B Instruct scores higher on coding benchmarks: 42.5 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do gpt-oss-120b and Qwen3-Next 80B-A3B Instruct share?
25 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Qwen3-Next 80B-A3B Instruct has 25.