SpaceXSI
Grok 4.3
ReasoningClosed weights
- Intelligence
- 24.8
- Rank 178 of 744 measured models
- Output speed
- 100 t/s
- Rank 167 of 403 measured models
- Price/1M
- $1.56
- Rank 441 of 659 measured models
- Context window
- 1M
- Rank 84 of 1199 measured models
Grok 4.3 (Medium) scores 24.8 on the Artificial Analysis Intelligence Index, ranking 178th of 744 measured models. The closest models on this index are GPT-5 Codex (High) (24.9), Claude Sonnet 4.6 (24.7), and GPT-5.1 (24.7). At $1.56 per million tokens (3:1 input/output blended price), it is cheaper than GPT-5 Codex (High) ($3.44), Claude Sonnet 4.6 ($6), and GPT-5.1 ($3.44). With an output speed of 100 t/s, it is faster than Claude Sonnet 4.6 (45.2 t/s), slower than GPT-5 Codex (High) (166 t/s) and GPT-5.1 (112 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- GPT-5 Codex (High)
OpenAI · $3.44 · 166 t/s
24.9+0.1$3.44166 t/sCompare - Claude Sonnet 4.6
Anthropic · $6 · 45.2 t/s
24.7−0.1$645.2 t/sCompare - GPT-5.1
OpenAI · $3.44 · 112 t/s
24.7−0.1$3.44112 t/sCompare - Solar Open2 250B
Upstage · — · —
24.7−0.1——Compare
