Model comparison
gpt-oss-20b vs Qwen-14B
gpt-oss-20b is the stronger model overall, scoring 32.5 to 31.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. gpt-oss-20b scores higher in 6 categories and Qwen-14B in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-20b leads 42.2 to 27.5.
Side by side
| gpt-oss-20b | Qwen-14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.5 | 31.4 |
| Released | 2025-08-05 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
gpt-oss-20b: 37.6 (#192), Qwen-14B: 31.2 (#288)
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| LMArena Coding | 1306 | 1071 |
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Not comparable
gpt-oss-20b: 9.3 (#154), Qwen-14B: —
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| Terminal-Bench | 3.4% | — |
Reasoning Too close to call
gpt-oss-20b: 19.3 (#261), Qwen-14B: 19.6 (#257)
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1274 | 1027 |
| Epoch Capabilities Index | 137.82 | 113.03 |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 4% | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math gpt-oss-20b leads
gpt-oss-20b: 39.4 (#103), Qwen-14B: 31.2 (#227)
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| LMArena Math | 1317 | 1068 |
| OTIS Mock AIME 2024-2025 | 65.3% | — |
| Omni-MATH | 56.5% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
gpt-oss-20b: 34.6 (#195), Qwen-14B: —
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| GPQA Diamond | 60.8% | — |
| MMLU-Pro | 74% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual gpt-oss-20b leads
gpt-oss-20b: 42.2 (#197), Qwen-14B: 27.5 (#275)
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1268 | 1041 |
| LMArena Chinese | 1314 | 1077 |
| LMArena German | 1255 | — |
| LMArena Japanese | 1244 | — |
| LMArena Korean | 1236 | — |
| LMArena Russian | 1278 | — |
| LMArena Spanish | 1267 | — |
Instruction Following gpt-oss-20b leads
gpt-oss-20b: 61.8 (#240), Qwen-14B: 52.4 (#289)
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1236 | 1031 |
| IFEval | 73.2% | — |
Long Context gpt-oss-20b leads
gpt-oss-20b: 37.9 (#209), Qwen-14B: 31.3 (#280)
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1250 | 1028 |
Writing & Preference gpt-oss-20b leads
gpt-oss-20b: 35.5 (#265), Qwen-14B: 27.6 (#299)
| Benchmark | gpt-oss-20b | Qwen-14B |
|---|---|---|
| LMArena Text | 1287 | 1051 |
| LMArena Creative Writing | 1201 | 1028 |
| LMArena Multi-Turn | 1268 | 1022 |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
Frequently asked questions
Is gpt-oss-20b better than Qwen-14B?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 31.4 on the Noometry Index.
Is gpt-oss-20b or Qwen-14B better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 31.2 in the Noometry coding category.
How many benchmarks do gpt-oss-20b and Qwen-14B share?
11 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen-14B has 18.