- Intelligence
- 39.5
- Rank 74 of 753 measured models
- Output speed
- 178 t/s
- Rank 65 of 412 measured models
- Price/1M
- $0.521
- Rank 293 of 682 measured models
- Context window
- 1M
- Rank 90 of 1261 measured models
- Cost per task
- $0.48
- Rank 106 of 201 measured models
DeepSeek V4.1 Flash (Max) scores 39.5 on the Artificial Analysis Intelligence Index, ranking 74th of 753 measured models. The closest models on this index are Qwen3.8 2.4T A95B (39.9), Qwen3.8-Flash-Next (39.8), and Muse Spark 1.2 (Xhigh) (39.6). At $0.521 per million tokens (3:1 input/output blended price), it is cheaper than Qwen3.8 2.4T A95B ($3) and Muse Spark 1.2 (Xhigh) ($2), more expensive than Qwen3.8-Flash-Next ($0.23). With an output speed of 178 t/s, it is faster than Qwen3.8 2.4T A95B (41.2 t/s) and Qwen3.8-Flash-Next (51.7 t/s), slower than Muse Spark 1.2 (Xhigh) (272 t/s).
Additional benchmarks9
Design Arena · 3d46.6%
Design Arena · Asciiart50.8%
Design Arena · Codecategories48.3%
Design Arena · Dataviz51.6%
Design Arena · Gamedev43.5%
Design Arena · Spreadsheet51.2%
Design Arena · Svg51.3%
Design Arena · Uicomponent53.5%
Design Arena · Website55.6%
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Qwen3.8 2.4T A95B
Alibaba · $3 · 41.2 t/s
39.9+0.4$341.2 t/sCompare - Qwen3.8-Flash-Next
Alibaba · $0.23 · 51.7 t/s
39.8+0.3$0.2351.7 t/sCompare - Muse Spark 1.2 (Xhigh)
Meta · $2 · 272 t/s
39.6+0.1$2272 t/sCompare - Gemini 3.7 Flash
Google · $1.50 · 383 t/s
39.1−0.4$1.50383 t/sCompare
