token.app › Compare › Mixtral 8x22B Instruct vs gpt-oss-20b

Mixtral 8x22B Instruct vs gpt-oss-20b

gpt-oss-20b leads on 1 of 1 shared benchmarks. gpt-oss-20b is 83× 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
Mixtral 8x22B Instructgpt-oss-20b
ProviderMistral AIOpenAI
Input $/1M$2.00$0.018
Output $/1M$6.00$0.090
Blended $/1M$3.00$0.036
Context window66K131K
Max output52K33K
ReleasedApr 2024Aug 2025
LicenceOpen weightsOpen weights
GPQA Diamond 34.1% 60.8%
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 Mixtral 8x22B Instruct if…
  • No clear advantage on the data we hold.
Choose gpt-oss-20b if…
  • Costs less per token — $0.036 vs $3.00 blended
  • Higher GPQA Diamond (60.8% vs 34.1%)
  • Larger context window (131K)
  • Newer model (released Aug 2025)
FAQ
Which is better, Mixtral 8x22B Instruct or gpt-oss-20b?
Across the 1 benchmark both models have independently-run scores for, Mixtral 8x22B Instruct leads on 0 and gpt-oss-20b leads on 1. Benchmarks are one input — price and context window are on this page too.
Is Mixtral 8x22B Instruct cheaper than gpt-oss-20b?
gpt-oss-20b is cheaper: $0.036 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $2.00 vs $0.018. Output alone: $6.00 vs $0.090.
What context windows do Mixtral 8x22B Instruct and gpt-oss-20b have?
Mixtral 8x22B Instruct: 65,536 tokens. gpt-oss-20b: 131,072 tokens.
Who makes Mixtral 8x22B Instruct and gpt-oss-20b?
Mixtral 8x22B Instruct is made by Mistral AI. gpt-oss-20b is made by OpenAI.
Related comparisons
Mixtral 8x22B Instruct full details gpt-oss-20b full details Mixtral 8x22B Instruct vs Flint (free) Mixtral 8x22B Instruct vs MiniMax M3.1 Flash (free) Mixtral 8x22B Instruct vs DeepSeek V4.1 Flash 1017 Mixtral 8x22B Instruct vs Glimpse Mixtral 8x22B Instruct vs Xing4.0 29B A4B (free) Mixtral 8x22B Instruct vs Beam 1.0 501B A23B