- Intelligence
- 34.3
- Rank 96 of 744 measured models
- Coding
- 69.1
- Rank 58 of 298 measured models
- Output speed
- 173 t/s
- Rank 57 of 403 measured models
- Price/1M
- $0.66
- Rank 313 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.22
- Rank 77 of 193 measured models
DeepSeek V4 Flash 0731 (Max) scores 34.3 on the Artificial Analysis Intelligence Index, ranking 96th of 744 measured models. The closest models on this index are DeepSeek V4 Flash Vision (Max) (34.8), Gemini 3.6 Flash (High) (34.0), and JT-4.1 Flash 236B A21B (33.9). At $0.66 per million tokens (3:1 input/output blended price), it is cheaper than Gemini 3.6 Flash (High) ($1.50), priced close to DeepSeek V4 Flash Vision (Max) ($0.66). With an output speed of 173 t/s, it is about as fast as DeepSeek V4 Flash Vision (Max) (173 t/s) and Gemini 3.6 Flash (High) (175 t/s).
Additional benchmarks8
Design Arena · 3d48.7%
Design Arena · Asciiart33.3%
Design Arena · Codecategories46.4%
Design Arena · Dataviz41.1%
Design Arena · Gamedev44.6%
Design Arena · Svg45.1%
Design Arena · Uicomponent46.8%
Design Arena · Website46.7%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- DeepSeek V4 Flash Vision (Max)
DeepSeek · $0.66 · 173 t/s
34.8+0.5$0.66173 t/sCompare - Gemini 3.6 Flash (High)
Google · $1.50 · 175 t/s
34.0−0.3$1.50175 t/sCompare - JT-4.1 Flash 236B A21B
China Mobile · — · —
33.9−0.4——Compare - GLM-5.2
Z.AI · $2.15 · 81.1 t/s
33.7−0.6$2.1581.1 t/sCompare
