8 sources filed · EN 7 · RU 1
Interface: start "task name" opens a session and returns the current SDK description; run "Python script" executes code on the server in a sandbox with the user's permissions.
2commands in the whole agent interface: start a session, run a Python script
OpenAI run: GPT-5.6 Sol and GPT 6 Astra, over $400,000 in API-priced tokens, over 1.3 million lines of Rust over several months of goal loops, about 84% compatibility at best.
$400,000+API-priced tokens spent on GPT-5.6 Sol and GPT 6 Astra, which never got past about 84% compatibility
Pricing per million tokens (prompts up to / over 100k): input $0.10 / $0.50, output $0.50 / $2.50, cache reads $0.01 / $0.05.
$0.10 / $0.50Haiku 5.5 input and output price per million tokens for prompts up to 100k, vs $1.00 / $5.00 for Haiku 4.5
Agents and models (July 2026 configurations): Codex with GPT-5.4, Claude Code with Claude Opus 5, Kimi Code with Kimi K3.
1.41-3.31xtoken usage of concurrent versus sequential execution across agents
Subscriptions are about 10% of Anthropic revenue but take over 40% of inference compute, lowering blended revenue per MW by about $36M.
~5xAPI-equivalent value of Claude plans vs OpenAI plans at the mid-tier models (Opus 5.5 vs GPT 6.1 Sol)
Median researcher daily spend: $0.17 (week ending 18 January), $10.45 (8 March), $136.68 (31 May), $601.25 (15 August).
$601.25median OpenAI researcher's daily coding-agent use at API prices, week ending 15 Aug 2026
Codebook substitution saves about 10%; instructing models to write cablese in lowercase saves 40.4% (gemma-4-31b), 48.9% (qwen3.8-27b) and 48.4% (GLM-5.3-Flash).
40-49%fewer billed output tokens when models write records in lowercase cablese
On 447 tasks, Claude Code and mini-SWE-agent differ by -1.8 points (Qwen3.6-35B-A3B) and -1.4 points (Qwen3.8-27B), equivalent within a 5-point margin.
13%median share of hard tasks whose outcome flips, both when swapping the harness and when rerunning the same one