Gemini 4 Carbon (High)
Not publicly available. Artificial Analysis measured this model but marks it as not publicly available (checkered pattern in its charts). Its rank still follows its measurements.ReasoningClosed weights
- Intelligence
- 59.4
- Rank 1 of 760 measured models
- Output speed
- 99.8 t/s
- Rank 203 of 419 measured models
- Price/1M
- $8
- Rank 649 of 713 measured models
- Context window
- 1M
- Rank 88 of 1279 measured models
- Cost per task
- $7.76
- Rank 205 of 212 measured models
Gemini 4 Carbon (High) scores 59.4 on the Artificial Analysis Intelligence Index, ranking 1st of 760 measured models. The closest models on this index are Claude Opus 5.5 (Default Fallback) (58.4), GPT-6 Astra (56.9), and GPT-6.1 Sol (54.5). At $8 per million tokens (3:1 input/output blended price), it is cheaper than GPT-6 Astra ($20), priced close to Claude Opus 5.5 (Default Fallback) ($8), more expensive than GPT-6.1 Sol ($4). With an output speed of 99.8 t/s, it is faster than GPT-6 Astra (73.1 t/s) and GPT-6.1 Sol (83 t/s), about as fast as Claude Opus 5.5 (Default Fallback) (98.3 t/s).
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.
- Claude Opus 5.5 (Default Fallback)
Anthropic · $8 · 98.3 t/s
58.4−1.0$898.3 t/sCompare - GPT-6 Astra
OpenAI · $20 · 73.1 t/s
56.9−2.5$2073.1 t/sCompare - GPT-6.1 Sol
OpenAI · $4 · 83 t/s
54.5−4.9$483 t/sCompare - Claude Sonnet 5.5 (Default Fallback)
Anthropic · $4 · 138 t/s
54.2−5.2$4138 t/sCompare
