Claude Sonnet 4.6 vs GPT-5 mini

Claude Sonnet 4.6 vs GPT-5 mini: GPT-5 mini is cheaper by 92% on average. Claude Sonnet 4.6 from Azure AI Foundry (1,000,000-token context, reasoning, tool calls) vs. GPT-5 mini from OpenAI (272,000-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
01,000,000
400
0128,000
5,000
01,000,000
Azure AI Foundry
$2,283/mo
Input $3.00/M · Output $15.00/M
GPT-5 miniCheaper
OpenAI
$236/mo
Input $0.250/M · Output $2.00/M
At this workload, GPT-5 mini is 90% cheaper than Claude Sonnet 4.6 — a savings of $2,047/month ($24,563/year).
Production recipe — Agent Command Center
strategy: cost-optimized
primary:
  model: gpt-5-mini
  provider: openai
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 GPT-5 mini
Input price $3.00/M $0.250/M
Output price $15.00/M $2.00/M
Context window 1,000,000 272,000
Max output 64,000 128,000
Function calling
Vision
Audio input
Reasoning
Prompt caching
Structured output
Pricing verified May 12, 2026 May 12, 2026
Cheaper option
~92% cheaper than Claude Sonnet 4.6
Larger context
1,000,000 tokens
More capabilities
5 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
GPT-5 mini
1,395
HumanEvalcode
Claude Sonnet 4.6
GPT-5 mini
93.5%
τ-bench (retail)agent
Claude Sonnet 4.6
91.7%
GPT-5 mini
AIME 2024math
Claude Sonnet 4.6
GPT-5 mini
91.1%
GPQA Diamondreasoning
Claude Sonnet 4.6
89.9%
GPT-5 mini
78.4%
MMLUgeneral
Claude Sonnet 4.6
89.3%
GPT-5 mini
MMLU-Proreasoning
Claude Sonnet 4.6
GPT-5 mini
82.0%
SWE-bench Verifiedagent
Claude Sonnet 4.6
79.6%
GPT-5 mini
68.0%
MMMU-Promultimodal
Claude Sonnet 4.6
74.5%
GPT-5 mini
ARC-AGI-2reasoning
Claude Sonnet 4.6
58.3%
GPT-5 mini
Humanity's Last Examreasoning
Claude Sonnet 4.6
33.2%
GPT-5 mini