Google

Gemini 4 Carbon

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.
Intelligence
58.3
Rank 3 of 771 measured models
Output speed
91.5 t/s
Rank 208 of 426 measured models
Price/1M
$8
Rank 662 of 730 measured models
Context window
1M
Rank 104 of 1301 measured models
Cost per task
$6.59
Rank 204 of 218 measured models

Gemini 4 Carbon (Medium) scores 58.3 on the Artificial Analysis Intelligence Index, ranking 3rd of 771 measured models. The closest models on this index are Claude Opus 5.5 (Default Fallback) (59.1), GPT-6 Astra (56.9), and GPT-6.1 Sol (54.6). 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 91.5 t/s, it is faster than GPT-6 Astra (47 t/s) and GPT-6.1 Sol (60.4 t/s), about as fast as Claude Opus 5.5 (Default Fallback) (94.6 t/s).

Not publicly available

Artificial Analysis marks this model as not publicly available (checkered pattern in its charts). Its measurements remain listed for comparison.

Artificial Analysis Indices
Medium
Intelligence58.3
Rank 3 of 771 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Cost per task
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting59.6
Rank 2 of 243 measured models
Strategy & Ops57.8
Rank 9 of 243 measured models
Legal59.5
Rank 2 of 243 measured models
Engineering63.9
Rank 3 of 242 measured models
Economics57.5
Rank 7 of 250 measured models
Standard Benchmarks
Terminal-Bench 4.060.6%
Rank 5 of 241 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy