token.app › Compare › Qwen2.5 72B Instruct vs gpt-oss-20b
Qwen2.5 72B Instruct vs gpt-oss-20b
gpt-oss-20b leads on 2 of 2 shared benchmarks. gpt-oss-20b is 10× cheaper per token on a blended 3:1 basis. gpt-oss-20b accepts the larger context window (131K).
Head to head
Blended price uses a 3:1 input:output mix
| Qwen2.5 72B Instruct | gpt-oss-20b | |
|---|---|---|
| Provider | Alibaba | OpenAI |
| Input $/1M | $0.360 | $0.018 |
| Output $/1M | $0.400 | $0.090 |
| Blended $/1M | $0.370 | $0.036 |
| Context window | 33K | 131K |
| Max output | 16K | 33K |
| Released | Sep 2024 | Aug 2025 |
| Licence | Open weights | Open weights |
| GPQA Diamond | 49.1% | 60.8% |
| OTIS Mock AIME | 8.1% | 65.3% |
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Qwen2.5 72B Instruct if…
- No clear advantage on the data we hold.
Choose gpt-oss-20b if…
- Costs less per token — $0.036 vs $0.370 blended
- Higher GPQA Diamond (60.8% vs 49.1%)
- Higher OTIS Mock AIME (65.3% vs 8.1%)
- Larger context window (131K)
- Newer model (released Aug 2025)
FAQ
Which is better, Qwen2.5 72B Instruct or gpt-oss-20b?
Across the 2 benchmarks both models have independently-run scores for, Qwen2.5 72B Instruct leads on 0 and gpt-oss-20b leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Qwen2.5 72B Instruct cheaper than gpt-oss-20b?
gpt-oss-20b is cheaper: $0.036 versus $0.370 per million tokens blended at 3:1 input:output. Input alone: $0.360 vs $0.018. Output alone: $0.400 vs $0.090.
What context windows do Qwen2.5 72B Instruct and gpt-oss-20b have?
Qwen2.5 72B Instruct: 32,768 tokens. gpt-oss-20b: 131,072 tokens.
Who makes Qwen2.5 72B Instruct and gpt-oss-20b?
Qwen2.5 72B Instruct is made by Alibaba. gpt-oss-20b is made by OpenAI.
Related comparisons
Qwen2.5 72B Instruct full details
gpt-oss-20b full details
Qwen2.5 72B Instruct vs Flint (free)
Qwen2.5 72B Instruct vs MiniMax M3.1 Flash (free)
Qwen2.5 72B Instruct vs DeepSeek V4.1 Flash 1017
Qwen2.5 72B Instruct vs Glimpse
Qwen2.5 72B Instruct vs Xing4.0 29B A4B (free)
Qwen2.5 72B Instruct vs Beam 1.0 501B A23B