- Intelligence
- 10.0
- Rank 424 of 744 measured models
- Output speed
- 309 t/s
- Rank 10 of 403 measured models
- Price/1M
- $0.106
- Rank 96 of 659 measured models
- Context window
- 131K
- Rank 738 of 1199 measured models
gpt-oss-20b (Low) scores 10.0 on the Artificial Analysis Intelligence Index, ranking 424th of 744 measured models. The closest models on this index are MiniMax M1 40k (10.0), Nova 2.0 Pro Preview (10.0), and Gemini 2.5 Flash (9.9). At $0.106 per million tokens (3:1 input/output blended price), it is cheaper than Nova 2.0 Pro Preview ($3.78) and Gemini 2.5 Flash ($0.85). With an output speed of 309 t/s, it is faster than Nova 2.0 Pro Preview (106 t/s) and Gemini 2.5 Flash (203 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- MiniMax M1 40k
MiniMax · — · —
10.0——Compare - Nova 2.0 Pro Preview
Amazon · $3.78 · 106 t/s
10.0$3.78106 t/sCompare - Gemini 2.5 Flash
Google · $0.85 · 203 t/s
9.9−0.1$0.85203 t/sCompare - K2-V2
Institute of Foundation Models · — · —
9.9−0.1——Compare
