Claude Opus 5.5 vs Gemini 4 Carbon
- Score
- Claude Opus 5.5 4 · Gemini 4 Carbon 9 · 2 tied — higher isn't always better; check the caveats.
- Shared
- 15 benchmarks measured for both models
- Integrity
- 13 of 15 graded A or B
Reported scores — protocols may differ. How we compare
Each bar is drawn on its benchmark's own scale — the ceiling the record states where it has one (of 100), otherwise the best score recorded on that benchmark (rel. 2103). The margin is in points: + is Claude Opus 5.5, - is Gemini 4 Carbon.
Game Playing: Gemini 4 Carbon leads 3–0 across 3 shared game playing benchmarks (largest gap: EBR-bench, 87.62 vs 71.43 — protocols undisclosed).
Reasoning: Gemini 4 Carbon leads 3–0 across 3 shared reasoning benchmarks (largest gap: SimpleQA Verified, 77.7 vs 72.2 — protocols undisclosed).
Abstract Reasoning: Gemini 4 Carbon leads 1–0 across 2 shared abstract reasoning benchmarks (largest gap: ARC-AGI-2, 94.17 vs 93.33 — protocols undisclosed).
Math: Gemini 4 Carbon leads 1–0 across 2 shared math benchmarks (largest gap: FrontierMath-Tier-4-v2-Private, 95.12 vs 95 — protocols undisclosed).
Gemini 4 Carbon leads 9–4 across 15 shared benchmarks. Claude Opus 5.5 leads 4 benchmarks and Gemini 4 Carbon leads 9, with 2 tied. Higher isn't always better — see the integrity caveats on each benchmark.
Claude Opus 5.5 and Gemini 4 Carbon have 15 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
Gemini 4 Carbon leads game playing 3–0. Gemini 4 Carbon leads reasoning 3–0.