SpaceXSI
Grok 4.7
ReasoningClosed weights
- Intelligence
- 46.3
- Rank 33 of 744 measured models
- Output speed
- 73.8 t/s
- Rank 244 of 403 measured models
- Price/1M
- $3
- Rank 487 of 659 measured models
- Context window
- 500K
- Rank 349 of 1199 measured models
- Cost per task
- $2.73
- Rank 174 of 193 measured models
Grok 4.7 (High) scores 46.3 on the Artificial Analysis Intelligence Index, ranking 33rd of 744 measured models. The closest models on this index are GPT-5.6 Sol (47.0), MiMo-V2.6-Pro (46.3), and Qwen3.8 Max (0902) (45.4). At $3 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5.6 Sol ($8), priced close to Qwen3.8 Max (0902) ($3), more expensive than MiMo-V2.6-Pro ($0.544). With an output speed of 73.8 t/s, it is faster than MiMo-V2.6-Pro (45.8 t/s) and Qwen3.8 Max (0902) (42 t/s), slower than GPT-5.6 Sol (85.8 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-6 Sol
OpenAI · $4 · 94.1 t/s
47.6+1.3$494.1 t/sCompare - GPT-5.6 Sol
OpenAI · $8 · 85.8 t/s
47.0+0.7$885.8 t/sCompare - MiMo-V2.6-Pro
Xiaomi · $0.544 · 45.8 t/s
46.3$0.54445.8 t/sCompare - Qwen3.8 Max (0902)
Alibaba · $3 · 42 t/s
45.4−0.9$342 t/sCompare
