- Intelligence
- 39.8
- Rank 65 of 747 measured models
- Coding
- 73.1
- Rank 39 of 298 measured models
- Output speed
- 51.6 t/s
- Rank 325 of 403 measured models
- Price/1M
- $0.23
- Rank 181 of 660 measured models
- Context window
- 256K
- Rank 521 of 1203 measured models
- Cost per task
- $0.372
- Rank 94 of 193 measured models
Qwen3.8-Flash-Next scores 39.8 on the Artificial Analysis Intelligence Index, ranking 65th of 747 measured models. The closest models on this index are Qwen3.8 2.4T A95B (39.9), Muse Spark 1.2 (Xhigh) (39.6), and DeepSeek V4.1 Flash (39.5). At $0.23 per million tokens (3:1 input/output blended price), it is cheaper than Qwen3.8 2.4T A95B ($3), Muse Spark 1.2 (Xhigh) ($2), and DeepSeek V4.1 Flash ($0.525). With an output speed of 51.6 t/s, it is faster than Qwen3.8 2.4T A95B (39.1 t/s), slower than Muse Spark 1.2 (Xhigh) (361 t/s) and DeepSeek V4.1 Flash (180 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Qwen3.8 Max
Alibaba · $3 · 40.1 t/s
40.2+0.4$340.1 t/sCompare - Qwen3.8 2.4T A95B
Alibaba · $3 · 39.1 t/s
39.9+0.1$339.1 t/sCompare - Muse Spark 1.2 (Xhigh)
Meta · $2 · 361 t/s
39.6−0.2$2361 t/sCompare - DeepSeek V4.1 Flash
DeepSeek · $0.525 · 180 t/s
39.5−0.3$0.525180 t/sCompare
