- Intelligence
- 20.2
- Rank 266 of 782 measured models
- Web Search
- $10 /1K calls
- Context window
- 200K
- Rank 685 of 1325 measured models
o3 (batch) scores 20.2 on the Artificial Analysis Intelligence Index, ranking 266th of 782 measured models. The closest models on this index are o3 (20.2), Ling 3.0 Flash (20.1), and Qwen3.8 27B (20.1). At $1.75 per million tokens (3:1 input/output blended price), it is cheaper than o3 ($3.50), more expensive than Ling 3.0 Flash ($0.111) and Qwen3.8 27B ($1.13).
Additional benchmarks5
Design Arena · Codecategories51.9%
Design Arena · Dataviz48.1%
Design Arena · Gamedev56.9%
Design Arena · Uicomponent53.3%
Design Arena · Website53.8%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5.1 Codex mini (High)
OpenAI · $0.688 · 142 t/s
20.4+0.2$0.688142 t/sCompare - 20.2$3.50114 t/sCompare
- Ling 3.0 Flash
InclusionAI · $0.111 · 207 t/s
20.1−0.1$0.111207 t/sCompare - Qwen3.8 27B
Alibaba · $1.13 · 43.7 t/s
20.1−0.1$1.1343.7 t/sCompare
