Model comparison
gpt-oss-120b vs Qwen3.6 Flash
Qwen3.6 Flash is the stronger model overall, scoring 38.4 to 36.0 on the Noometry Index. gpt-oss-120b costs 6.0× less per token, which makes it the better buy when Qwen3.6 Flash's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. gpt-oss-120b scores higher in 2 categories and Qwen3.6 Flash in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-120b leads 50.6 to 38.0.
- The biggest single-benchmark swing is Mystery Game Puzzles: 2% for gpt-oss-120b and 18% for Qwen3.6 Flash.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.19 / $1.13 for Qwen3.6 Flash.
- Qwen3.6 Flash accepts more context: 1M tokens versus 131K.
- gpt-oss-120b has downloadable open weights; the other is API-only.
Side by side
| gpt-oss-120b | Qwen3.6 Flash | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.0 | 38.4 |
| Released | 2025-08-05 | 2026-04-27 |
| Weights | Open | Proprietary |
| Context window | 131K | 1M |
| Max output | 41K | 66K |
| Input $ / M tokens | $0.037 | $0.19 |
| Output $ / M tokens | $0.17 | $1.13 |
| Results tracked | 48 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
gpt-oss-120b: 33.2 (#251), Qwen3.6 Flash: —
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| ALE-Bench | 575.62 | 326.4 |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| SciCode | 36% | — |
| WeirdML | 48.2% | — |
| LMArena Coding | 1380 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Not comparable
gpt-oss-120b: 12.1 (#145), Qwen3.6 Flash: —
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning Qwen3.6 Flash leads
gpt-oss-120b: 19.5 (#236), Qwen3.6 Flash: 28.4 (#90)
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| SimpleBench | 22.1% | 35.2% |
| Chess Puzzles | 20% | 20% |
| Mystery Game Puzzles | 2% | 18% |
| DTBench | 76.3% | 77.1% |
| LMCA | 22.1% | 31% |
| Epoch Capabilities Index | 139.94 | 143.26 |
| Kagi LLM Benchmark | 58.6% | — |
| CritPt | 1.1% | — |
| LMArena Hard Prompts | 1364 | — |
| Surface Evolver Bench | 25% | — |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), Qwen3.6 Flash: 38.0 (#88)
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 84.4% |
| FrontierMath (Tiers 1-3) | — | 22.5% |
| Omni-MATH | 68.8% | — |
| LMArena Math | 1388 | — |
| FrontierMath (Feb 2025 set) | — | 10.3% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Too close to call
gpt-oss-120b: 42.3 (#89), Qwen3.6 Flash: 42.2 (#90)
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| GPQA Diamond | 75.8% | 83.3% |
| SimpleQA Verified | — | 15.9% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| Vectara Hallucination Rate | 14.2% | — |
| GPQA (HELM) | 68.4% | — |
| LMArena Expert | 1356 | — |
Multilingual Not comparable
gpt-oss-120b: 48.2 (#142), Qwen3.6 Flash: —
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| LMArena Non-English | 1350 | — |
| LMArena Chinese | 1384 | — |
| LMArena French | 1370 | — |
| LMArena German | 1355 | — |
| LMArena Japanese | 1332 | — |
| LMArena Korean | 1283 | — |
| LMArena Russian | 1343 | — |
| LMArena Spanish | 1388 | — |
Instruction Following Not comparable
gpt-oss-120b: 69.5 (#168), Qwen3.6 Flash: —
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| IFEval | 83.6% | — |
| LMArena Instruction Following | 1318 | — |
Long Context Not comparable
gpt-oss-120b: 31.4 (#273), Qwen3.6 Flash: —
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| Fiction.LiveBench | 44.4% | — |
| LMArena Longer Query | 1319 | — |
Writing & Preference Not comparable
gpt-oss-120b: 46.7 (#213), Qwen3.6 Flash: —
| Benchmark | gpt-oss-120b | Qwen3.6 Flash |
|---|---|---|
| LMArena Text | 1366 | — |
| LMArena Creative Writing | 1274 | — |
| Short-Story Creative Writing | 77.1% | — |
| EQ-Bench Creative Writing | 961 | — |
| WildBench | 84.5% | — |
| LMArena Multi-Turn | 1340 | — |
Frequently asked questions
Is gpt-oss-120b better than Qwen3.6 Flash?
Qwen3.6 Flash is the stronger model overall, scoring 38.4 to 36.0 on the Noometry Index. gpt-oss-120b costs 6.0× less per token, which makes it the better buy when Qwen3.6 Flash's lead doesn't matter for your workload.
Which is cheaper, gpt-oss-120b or Qwen3.6 Flash?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Qwen3.6 Flash lists at $0.19 and $1.13.
Which has the bigger context window?
Qwen3.6 Flash does, with 1M tokens against 131K.
How many benchmarks do gpt-oss-120b and Qwen3.6 Flash share?
9 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Qwen3.6 Flash has 13.