Gemini 4 Carbon wins more areas, narrowly.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the two areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Coding and agents rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Gemini 4 Carbon costs 33% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemini 4 Carbon pulls ahead
- Complex command-line tasks across many fieldsTerminal-Bench 4.0+1.6points ahead
Where Gemini 4 Neon pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results8 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AA IntelligenceGemini 4 Carbon by 166044+16
- Science and math (RiemannBench)Gemini 4 Neon by 127284+12
- CritPt v2 HardGemini 4 Carbon by 8.56960.5+8.5
- Terminal-Bench-Science 0.1Gemini 4 Neon by 5.264.870+5.2
- RiemannBenchGemini 4 Neon by 48084+4
- Knowledge work (AutomationBench)Gemini 4 Neon by 2.453.956.3+2.4
- HLE-DiamondGemini 4 Neon by 2.269.171.3+2.2
- GDP (Surge AI)tie28.428tie
Questions people ask
Which is better, Gemini 4 Carbon or Gemini 4 Neon?
Gemini 4 Carbon wins one of the two areas where both have results: agents. Gemini 4 Neon wins none. They are level on coding.
Which is better for coding?
Neither. All 1 coding tests both models report are ties.
Which is cheaper?
Gemini 4 Carbon costs $2.00 per million input tokens and $10.00 per million output tokens; Gemini 4 Neon costs $3.00 and $15.00. That makes Gemini 4 Carbon about 33% cheaper for the same work.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.