Claude Sonnet 4.6 vs Gemini 3.1 Pro preview

Claude Sonnet 4.6 vs Gemini 3.1 Pro preview: Gemini 3.1 Pro preview is cheaper by 33% on average. Claude Sonnet 4.6 from Azure AI Foundry (1,000,000-token context, reasoning, tool calls) vs. Gemini 3.1 Pro preview from Google Vertex AI (1,048,576-token context, reasoning, tool calls). Use Agent Command Center to A/B both in shadow mode and pick the winner per workload.

Side-by-side cost

Live workload comparison

Same workload run through both models. The cheaper one is highlighted.

3,000
01,048,576
400
065,536
5,000
01,000,000
Azure AI Foundry
$2,283/mo
Input $3.00/M · Output $15.00/M
Google Vertex AI
$1,644/mo
Input $2.00/M · Output $12.00/M
At this workload, Gemini 3.1 Pro preview is 28% cheaper than Claude Sonnet 4.6 — a savings of $639/month ($7,670/year).
Production recipe — Agent Command Center
strategy: cost-optimized
primary:
  model: gemini-3-1-pro-preview
  provider: vertex-ai
fallback:
  model: claude-sonnet-4-6
  provider: azure-ai-foundry
shadow: { sample_rate: 0.05 }   # mirror 5% of traffic to compare quality live
Claude Sonnet 4.6 Gemini 3.1 Pro preview
Input price $3.00/M $2.00/M
Output price $15.00/M $12.00/M
Context window 1,000,000 1,048,576
Max output 64,000 65,536
Function calling
Vision
Audio input
Reasoning
Prompt caching
Structured output
Pricing verified May 12, 2026 May 12, 2026
Cheaper option
~33% cheaper than Claude Sonnet 4.6
Larger context
1,048,576 tokens
More capabilities
6 of 6 capability flags advertised

Benchmark comparison

Side-by-side public benchmark scores. Greener bar = winner.

Chatbot Arena ELOgeneral
Claude Sonnet 4.6
1,466
Gemini 3.1 Pro preview
1,492
GPQA Diamondreasoning
Claude Sonnet 4.6
89.9%
Gemini 3.1 Pro preview
94.3%
τ-bench (retail)agent
Claude Sonnet 4.6
91.7%
Gemini 3.1 Pro preview
MMLUgeneral
Claude Sonnet 4.6
89.3%
Gemini 3.1 Pro preview
SWE-bench Verifiedagent
Claude Sonnet 4.6
79.6%
Gemini 3.1 Pro preview
80.6%
MMMU-Promultimodal⚠ different settings
Claude Sonnet 4.6
74.5%
Gemini 3.1 Pro preview
80.5%
ARC-AGI-2reasoning⚠ different settings
Claude Sonnet 4.6
58.3%
Gemini 3.1 Pro preview
77.1%
SciCodecode
Claude Sonnet 4.6
Gemini 3.1 Pro preview
59.0%
Humanity's Last Examreasoning⚠ different settings
Claude Sonnet 4.6
33.2%
Gemini 3.1 Pro preview
44.4%