Model comparison
gpt-oss-120b vs Qwen3 14B
gpt-oss-120b and Qwen3 14B score almost the same on the Noometry Index (36.0 vs 35.0), so choose on price, context window or the category you care about most.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. gpt-oss-120b scores higher in 3 categories and Qwen3 14B in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Qwen3 14B leads 29.4 to 12.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for gpt-oss-120b and 66.4% for Qwen3 14B.
- gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.35 / $1.40 for Qwen3 14B.
Side by side
| gpt-oss-120b | Qwen3 14B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.0 | 35.0 |
| Released | 2025-08-05 | 2025-04 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 41K | 8K |
| Input $ / M tokens | $0.037 | $0.35 |
| Output $ / M tokens | $0.17 | $1.40 |
| Results tracked | 48 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 14B leads
gpt-oss-120b: 33.2 (#251), Qwen3 14B: 36.7 (#191)
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| SciCode | 36% | 31.6% |
| SWE-bench Verified (bash only) | 26% | — |
| Aider Polyglot | 41.8% | — |
| WeirdML | 48.2% | — |
| LMArena Coding | 1380 | — |
| ALE-Bench | 575.62 | — |
| AlgoTune | 1.41 | — |
Agentic & Tool Use Qwen3 14B leads
gpt-oss-120b: 12.1 (#145), Qwen3 14B: 29.4 (#78)
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| Terminal-Bench | 18.7% | — |
| APEX-Agents | 4.4% | — |
| Berkeley Function Calling Leaderboard | — | 41% |
| METR Time Horizons | 56.6% | — |
| Vending-Bench 2 | -21.53 | — |
Reasoning gpt-oss-120b leads
gpt-oss-120b: 19.5 (#236), Qwen3 14B: 18.1 (#272)
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| Kagi LLM Benchmark | 58.6% | 49.1% |
| CritPt | 1.1% | 0% |
| Chess Puzzles | 20% | 4% |
| DTBench | 76.3% | 64% |
| LMCA | 22.1% | 18.2% |
| Epoch Capabilities Index | 139.94 | 138.23 |
| SimpleBench | 22.1% | — |
| LMArena Hard Prompts | 1364 | — |
| Mystery Game Puzzles | 2% | — |
| Surface Evolver Bench | 25% | — |
Math gpt-oss-120b leads
gpt-oss-120b: 50.6 (#43), Qwen3 14B: 37.0 (#102)
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 66.4% |
| Omni-MATH | 68.8% | — |
| LMArena Math | 1388 | — |
Knowledge gpt-oss-120b leads
gpt-oss-120b: 42.3 (#89), Qwen3 14B: 39.2 (#124)
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| GPQA Diamond | 75.8% | 63.8% |
| Vectara Hallucination Rate | 14.2% | 5.4% |
| MMLU-Pro | 79.5% | — |
| Confabulations | 15.7% | — |
| GPQA (HELM) | 68.4% | — |
| LMArena Expert | 1356 | — |
Multilingual Not comparable
gpt-oss-120b: 48.2 (#142), Qwen3 14B: —
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| 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 14B: —
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| IFEval | 83.6% | — |
| LMArena Instruction Following | 1318 | — |
Long Context Qwen3 14B leads
gpt-oss-120b: 31.4 (#273), Qwen3 14B: 38.0 (#201)
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | 44.4% | 62.5% |
| LMArena Longer Query | 1319 | — |
Writing & Preference Not comparable
gpt-oss-120b: 46.7 (#213), Qwen3 14B: —
| Benchmark | gpt-oss-120b | Qwen3 14B |
|---|---|---|
| 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 14B?
gpt-oss-120b and Qwen3 14B score almost the same on the Noometry Index (36.0 vs 35.0), so choose on price, context window or the category you care about most.
Which is cheaper, gpt-oss-120b or Qwen3 14B?
gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Qwen3 14B lists at $0.35 and $1.40.
Is gpt-oss-120b or Qwen3 14B better for coding?
Qwen3 14B scores higher on coding benchmarks: 36.7 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do gpt-oss-120b and Qwen3 14B share?
11 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Qwen3 14B has 12.