Skip to content
Agents tracked: 502 Releases (7d): 613 Agent status: 4 with issuesSince last limit reset: Claude 7d · Codex 5d For AI agents: Markdown Updated Nov 18, 2026

GPT-6.1 Sol is within 2.7 points of the top for 5x less

Gid Bench against the API price of an example task (1M input + 100K output tokens). Live chart from AgentGid, updated daily.

GPT-6.1 Sol is within 2.7 points of the top for 5x less

Gid Bench against the API price of an example task (1M input + 100K output tokens)

4050607080$0.10$0.20$0.50$1.00$2.00$5.00$10$20Price of the example task, USD (log scale)Gid BenchClaude Sonnet 5.5 (Anthropic): Gid Bench 66.2, example task $3.00Claude Sonnet 5.5Gemini 3.8 Flash (Google): Gid Bench 50.0, example task $1.12Gemini 3.8 FlashKimi K3 (Moonshot): Gid Bench 46.2, example task $4.50Kimi K3Grok 4.7 (xAI): Gid Bench 45.8, example task $2.60Grok 4.7GPT-6 Luna (OpenAI): Gid Bench 40.5, example task $0.15GPT-6 LunaGPT-6 Astra (OpenAI): Gid Bench 73.9, example task $15GPT-6 AstraClaude Opus 5.5 (Anthropic): Gid Bench 72.3, example task $6.00Claude Opus 5.5GPT-6.1 Sol (OpenAI): Gid Bench 71.2, example task $3.00GPT-6.1 SolClaude Haiku 5.5 (Anthropic): Gid Bench 51.8, example task $0.15Claude Haiku 5.5
The dashed line joins the best score at each price. List prices per token, not the cost of a real job: reasoning models spend more tokens on the same task. Source: Gid Bench by AgentGid (Epoch AI, CC BY 4.0); prices from LiteLLM's open price list · Nov 17, 2026.

Put this chart on your site

The chart updates by itself. Please keep the link to the source.

More charts