Claude Opus 5 Max vs Gemini 4 Carbon High compared

Claude Opus 5 (Max) (Anthropic) and Gemini 4 Carbon (High) (Google) are not peers on the headline index, which makes the trade-offs the interesting part. The biggest separation is in overall capability: 60.0 for Gemini 4 Carbon High against 44.2 for Claude Opus 5 Max. All numbers are the catalogue's recorded values; nobody ran either model by hand for this page.

Overall capability: 15.8 points apart

Claude Opus 5 Max records 44.2 on the intelligence index and Gemini 4 Carbon High records 60.0. A gap this large suggests the two are built for different jobs. In relative terms, Gemini 4 Carbon High scores 36% higher.

Among 109 active scored models, Claude Opus 5 Max sits 26th and Gemini 4 Carbon High 1st.

Specialist coding and math indexes are missing for both, so treat the overall score as the only capability signal here.

Gemini 4 Carbon High is the faster writer

Once a response is under way, Claude Opus 5 Max produces roughly 50 tokens per second against 91 tokens per second for Gemini 4 Carbon High. Gemini 4 Carbon High is ahead by 82% on throughput. Before any text appears, Claude Opus 5 Max takes 62 seconds and Gemini 4 Carbon High 2.0 minutes. So the two pull in opposite directions, with Claude Opus 5 Max quicker off the mark and Gemini 4 Carbon High quicker once it gets going; the crossover is around 6,500 tokens. A first-token wait of that length suits background work better than live conversation.

Put together, a 1,000-token answer would take about 82 seconds from Claude Opus 5 Max and 2.2 minutes from Gemini 4 Carbon High, counting the first-token wait.

When they came out

Gemini 4 Carbon High arrived on October 28, 2026, about 3 months after Claude Opus 5 Max (July 24, 2026).

Running costs

Claude Opus 5 Max lists $5.00 per million input tokens and $25.00 per million output tokens; Gemini 4 Carbon High lists $4.00 and $20.00. For output tokens, Claude Opus 5 Max is 1.3 times the price of Gemini 4 Carbon High.

For a sample workload of 1 million input tokens and 200,000 output tokens, Claude Opus 5 Max would cost $10.00 and Gemini 4 Carbon High $8.00, a difference of $2.00. For writing 2,000 drafts of 2,000 output tokens from 300-token prompts, Gemini 4 Carbon High would come in 20% lower: $103 for Claude Opus 5 Max against $82.40 for Gemini 4 Carbon High. Blended at three input tokens per output token, the effective rates are $10.00 for Claude Opus 5 Max and $8.00 for Gemini 4 Carbon High.

Cost per point of intelligence

Dividing the blended price by the intelligence index gives a rough cost per point: $0.23 for Claude Opus 5 Max and $0.13 for Gemini 4 Carbon High, per million tokens. With the higher score and the lower cost per point, Gemini 4 Carbon High is the better value per point on these numbers.