Polarison

Claude Sonnet 5 vs Gemini 3.1 Pro: pricing and benchmarks

Both charge $2.00 per 1M input tokens. Claude Sonnet 5 is 17% cheaper on output tokens ($10.00 vs $12.00 per 1M). On our document Q&A workload (50,000 questions a month), Claude Sonnet 5 costs $1,100 a month versus $1,160 for Gemini 3.1 Pro, 5% less. Roughly tied. Claude Sonnet 5 scores 156.2 and Gemini 3.1 Pro scores 155.0 on the Epoch Capabilities Index, and their confidence intervals overlap.

Prices verified September 14, 2026.

Which should you choose?

Overall capability
Too close to call

Roughly tied. Claude Sonnet 5 scores 156.2 and Gemini 3.1 Pro scores 155.0 on the Epoch Capabilities Index, and their confidence intervals overlap.

Coding
Claude Sonnet 5

Claude Sonnet 5 scores 53.8% on DeepSWE vs 11.7% for Gemini 3.1 Pro.

Advanced math
Claude Sonnet 5

Claude Sonnet 5 scores 65.6% on FrontierMath (Tiers 1–3) vs 59.6% for Gemini 3.1 Pro.

Price
Claude Sonnet 5

Claude Sonnet 5 costs $4.00 per 1M tokens (3:1 input-to-output mix) vs $4.50 for Gemini 3.1 Pro, 11% less.

Best value
Claude Sonnet 5

Claude Sonnet 5 delivers equal or higher overall capability for 11% less.

Pricing and specs

Claude Sonnet 5Gemini 3.1 Pro
ProviderAnthropicGoogle
API model IDclaude-sonnet-5gemini-3.1-pro-preview
Input / 1M tokens$2.00$2.00
Cached input / 1M tokens$0.20$0.20
Output / 1M tokens$10.00$12.00
Long-context rates$4.00 in / $18.00 out above 200K prompt tokens
Context window1M tokens1.05M tokens
Max output128K tokens66K tokens
Batch discount50% off

Benchmarks

Claude Sonnet 5Gemini 3.1 Pro
Epoch Capabilities Index156.2155.0
GPQA Diamond· Science reasoning87.4%92.6%
FrontierMath (Tiers 1–3)· Advanced math65.6%59.6%
SimpleQA Verified· Factual accuracy33.7%73.5%
ARC-AGI-2· Abstract reasoning77.1%
DeepSWE· Coding53.8%11.7%
APEX-Agents· Agentic work32.5%33.5%

Source: Epoch AI, best recorded result per model (CC BY 4.0). A dash means no published score. See all benchmarks

Monthly cost for real workloads

WorkloadClaude Sonnet 5Gemini 3.1 ProDifference
Support chatbot
100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each.
$700.00$780.00Claude Sonnet 5 10% cheaper
Document Q&A (RAG)
50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each.
$1,100$1,160Claude Sonnet 5 5% cheaper
Coding agent
10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens.
$496.00$536.00Claude Sonnet 5 7% cheaper

Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.

Claude Sonnet 5 vs Gemini 3.1 Pro cost calculator

Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.

Claude Sonnet 5 pricing notes

Anthropic’s best combination of speed and intelligence.

  • The $2 / $10 launch price is now the standard price; the planned rise to $3 / $15 will not happen.
  • Cache writes cost $2.50 (5-minute cache) or $4 (1-hour cache) per 1M tokens.
  • Uses Anthropic’s newer tokenizer, which produces roughly 30% more tokens for the same text.
Anthropic official pricing ↗

Gemini 3.1 Pro pricing notes

Google’s Gemini 3.1 Pro model, currently offered as a preview.

  • Prompts over 200K tokens are billed at $4 input / $18 output per 1M tokens.
  • No free tier on the Gemini API.
  • Output price includes thinking tokens.
Google official pricing ↗

Frequently asked questions

Is Claude Sonnet 5 cheaper than Gemini 3.1 Pro?
Both charge $2.00 per 1M input tokens. Claude Sonnet 5 is 17% cheaper on output tokens ($10.00 vs $12.00 per 1M). On our document Q&A workload (50,000 questions a month), Claude Sonnet 5 costs $1,100 a month versus $1,160 for Gemini 3.1 Pro, 5% less.
Which is more capable, Claude Sonnet 5 or Gemini 3.1 Pro?
Roughly tied. Claude Sonnet 5 scores 156.2 and Gemini 3.1 Pro scores 155.0 on the Epoch Capabilities Index, and their confidence intervals overlap.
How much does Claude Sonnet 5 cost per 1M tokens?
Claude Sonnet 5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens, and $0.20 per 1M cached input tokens on Anthropic’s standard tier.
How much does Gemini 3.1 Pro cost per 1M tokens?
Gemini 3.1 Pro costs $2.00 per 1M input tokens and $12.00 per 1M output tokens, and $0.20 per 1M cached input tokens on Google’s standard tier.
Which has the larger context window, Claude Sonnet 5 or Gemini 3.1 Pro?
Gemini 3.1 Pro has the larger context window: 1.05M tokens versus 1M for Claude Sonnet 5.

Related comparisons