- Intelligence
- 36.0
- Rank 86 of 744 measured models
- Coding
- 68.8
- Rank 59 of 298 measured models
- Output speed
- 83.3 t/s
- Rank 218 of 403 measured models
- Price/1M
- $1.98
- Rank 463 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
- Cost per task
- $0.674
- Rank 114 of 193 measured models
DeepSeek V4 Pro 0813 (Max) scores 36.0 on the Artificial Analysis Intelligence Index, ranking 86th of 744 measured models. The closest models on this index are Agnes 3.0 Flash (35.5), Agnes 2.5 Pro Beta (35.2), and DeepSeek V4 Flash Vision (Max) (34.8). At $1.98 per million tokens (3:1 input/output blended price), it is more expensive than Agnes 3.0 Flash ($0.075), Agnes 2.5 Pro Beta ($0.15), and DeepSeek V4 Flash Vision (Max) ($0.66). With an output speed of 83.3 t/s, it is slower than Agnes 2.5 Pro Beta (120 t/s) and DeepSeek V4 Flash Vision (Max) (173 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5.6 Luna
OpenAI · $0.45 · 115 t/s
37.3+1.3$0.45115 t/sCompare - Agnes 3.0 Flash
Sapiens AI · $0.075 · —
35.5−0.5$0.075—Compare - Agnes 2.5 Pro Beta
Sapiens AI · $0.15 · 120 t/s
35.2−0.8$0.15120 t/sCompare - DeepSeek V4 Flash Vision (Max)
DeepSeek · $0.66 · 173 t/s
34.8−1.2$0.66173 t/sCompare
