SpaceXSI
Grok 3
Closed weights
- Intelligence
- 12.1
- Rank 371 of 744 measured models
- Output speed
- 100 t/s
- Rank 166 of 403 measured models
- Price/1M
- $6
- Rank 587 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
Grok 3 scores 12.1 on the Artificial Analysis Intelligence Index, ranking 371st of 744 measured models. The closest models on this index are JT-MINI (12.2), Seed-OSS-36B-Instruct (12.1), and Qwen3 235B A22B 2507 Instruct (12.0). At $6 per million tokens (3:1 input/output blended price), it is more expensive than Seed-OSS-36B-Instruct ($0.30) and Qwen3 235B A22B 2507 Instruct ($0.385). With an output speed of 100 t/s, it is faster than Seed-OSS-36B-Instruct (40.9 t/s) and Qwen3 235B A22B 2507 Instruct (43.3 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- JT-MINI
China Mobile · — · —
12.2+0.1——Compare - Seed-OSS-36B-Instruct
ByteDance · $0.30 · 40.9 t/s
12.1$0.3040.9 t/sCompare - Qwen3 235B A22B 2507 Instruct
Alibaba · $0.385 · 43.3 t/s
12.0−0.1$0.38543.3 t/sCompare - Qwen3 235B A22B Instruct 2507
Qwen · $0.205 · —
12.0−0.1$0.205—Compare
