Model comparison
gpt-oss-20b vs Qwen3-4B
gpt-oss-20b and Qwen3-4B score almost the same on the Noometry Index (32.1 vs 31.5), so choose on price, context window or the category you care about most.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. gpt-oss-20b scores higher in 3 categories and Qwen3-4B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen3-4B leads 27.3 to 9.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 65.3% for gpt-oss-20b and 52.2% for Qwen3-4B.
Side by side
| gpt-oss-20b | Qwen3-4B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 32.1 | 31.5 |
| Released | 2025-08-05 | 2025-04-29 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.018 | — |
| Output $ / M tokens | $0.09 | — |
| Results tracked | 34 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
gpt-oss-20b: 37.1 (#185), Qwen3-4B: —
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| SciCode | 34.4% | — |
| WeirdML | 40.9% | — |
| LMArena Coding | 1307 | — |
| ALE-Bench | 566.05 | — |
Agentic & Tool Use Qwen3-4B leads
gpt-oss-20b: 9.2 (#146), Qwen3-4B: 27.3 (#94)
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| Terminal-Bench | 3.4% | — |
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Too close to call
gpt-oss-20b: 18.8 (#251), Qwen3-4B: 18.5 (#264)
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| Chess Puzzles | 4% | 4% |
| Kagi LLM Benchmark | 53.2% | — |
| CritPt | 1.4% | — |
| LMArena Hard Prompts | 1274 | — |
| DTBench | 68% | — |
| LMCA | 14.5% | — |
| Epoch Capabilities Index | 137.81 | — |
Math gpt-oss-20b leads
gpt-oss-20b: 37.6 (#93), Qwen3-4B: 28.5 (#228)
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3% | 52.2% |
| MathArena Final-Answer Competitions | — | 38.5% |
| Omni-MATH | 56.5% | — |
| LMArena Math | 1317 | — |
Knowledge gpt-oss-20b leads
gpt-oss-20b: 34.6 (#186), Qwen3-4B: 33.0 (#198)
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| GPQA Diamond | 60.8% | 52.3% |
| MMLU-Pro | 74% | — |
| Vectara Hallucination Rate | — | 5.7% |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1258 | — |
Multilingual Not comparable
gpt-oss-20b: 42.4 (#192), Qwen3-4B: —
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| LMArena Non-English | 1269 | — |
| LMArena Chinese | 1311 | — |
| LMArena German | 1249 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1239 | — |
| LMArena Russian | 1279 | — |
| LMArena Spanish | 1267 | — |
Instruction Following Not comparable
gpt-oss-20b: 62.0 (#235), Qwen3-4B: —
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| IFEval | 73.2% | — |
| LMArena Instruction Following | 1236 | — |
Long Context Not comparable
gpt-oss-20b: 37.9 (#203), Qwen3-4B: —
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| LMArena Longer Query | 1251 | — |
Writing & Preference Not comparable
gpt-oss-20b: 35.8 (#260), Qwen3-4B: —
| Benchmark | gpt-oss-20b | Qwen3-4B |
|---|---|---|
| LMArena Text | 1288 | — |
| LMArena Creative Writing | 1201 | — |
| EQ-Bench Creative Writing | 666 | — |
| WildBench | 73.7% | — |
| LMArena Multi-Turn | 1268 | — |
Frequently asked questions
Is gpt-oss-20b better than Qwen3-4B?
gpt-oss-20b and Qwen3-4B score almost the same on the Noometry Index (32.1 vs 31.5), so choose on price, context window or the category you care about most.
How many benchmarks do gpt-oss-20b and Qwen3-4B share?
3 benchmarks have published results for both models. gpt-oss-20b has 34 scored results on Noometry and Qwen3-4B has 6.