AIBenchmarks
RankingsCompareClaude 3.5 Sonnet vs Gemini 1.5 Pro

Claude 3.5 SonnetvsGemini 1.5 Pro

Anthropic

Claude 3.5 Sonnet

🏆 Overall Winner

Anthropic's most intelligent model

Arena ELO
1298
Context
200K
Speed
85 t/s
Input/1M
$3
Google

Gemini 1.5 Pro

Google's 1M-token multimodal model

Arena ELO
1261
Context
1000K
Speed
150 t/s
Input/1M
$1.25

Capability Radar

Category performance across 6 domains

Benchmark Scores

MMLU · HumanEval · MATH · GSM8K · GPQA · BBH

Claude 3.5 Sonnet

Pros

Best coding (SWE-bench leader)
200K context window
Exceptional instruction following

Cons

Slower than GPT-4o
No native audio capabilities

Gemini 1.5 Pro

Pros

1M token context window
Fastest response times
Best price-to-performance

Cons

Slightly lower reasoning vs GPT-4o/Claude
Less consistent instruction following

🏆 Our Verdict

Based on overall benchmark averages, Claude 3.5 Sonnet has the edge with an average score of 84.6% across all benchmarks. However, the best choice depends on your use case — Claude 3.5 Sonnet excels in best coding (swe-bench leader), while Gemini 1.5 Pro stands out for 1m token context window.

More Comparisons

Claude 3.5 Sonnet vs GPT-4oGemini 1.5 Pro vs GPT-4oClaude 3.5 Sonnet vs Llama 3.1 405BGemini 1.5 Pro vs Llama 3.1 405BClaude 3.5 Sonnet vs Grok 2Gemini 1.5 Pro vs Grok 2Claude 3.5 Sonnet vs Mistral Large 2Gemini 1.5 Pro vs Mistral Large 2