Price per IQ | AI TrackerWhat a fixed level of capability costs, and how fast that price falls.https://www.justaparrot.com/enAI Tracker[Updated] Same AI, same puzzle games: 62.7% with the standard test setup, 99.9% with its maker's ownhttps://www.justaparrot.com/e/arc-agi-harness-matters/https://www.justaparrot.com/e/arc-agi-harness-matters/Added Claude Fable 5.2, the new best score with the standard harness (81.2%).. How a model is run in a test can matter as much as the model. GPT-6 Astra scored 62.7% or 99.9% depending on the software wrapped around it.Tue, 10 Nov 2026 00:00:00 GMTbenchmarksautonomycost-of-intelligenceOn an IQ-style quiz never published online, top AI scores rose from 85 to 136https://www.justaparrot.com/e/iq-style-test-scores/https://www.justaparrot.com/e/iq-style-test-scores/The quiz is kept offline so models can't have trained on it. Scores rose about 50 points since May 2024, but an AI ‘IQ’ means little.Mon, 09 Nov 2026 00:00:00 GMTcost-of-intelligencebenchmarksBuying a fixed level of AI ability gets about 13× cheaper each year, Epoch AI foundhttps://www.justaparrot.com/e/epoch-price-of-thought/https://www.justaparrot.com/e/epoch-price-of-thought/The price of answering at a fixed standard halves about every quarter: one science level got 725× cheaper in 18 months. Top models did not.Mon, 09 Nov 2026 00:00:00 GMTcost-of-intelligencebenchmarksOpenAI's unreleased Astra AI produced 10 research results, each with a computer-checked proofhttps://www.justaparrot.com/e/openai-ten-advances-astra/https://www.justaparrot.com/e/openai-ten-advances-astra/The 10 results include three Erdős problems, and anyone can re-check the proofs by computer. OpenAI reported only its successes.Mon, 09 Nov 2026 00:00:00 GMTmathcomputer-sciencecost-of-intelligenceOne fixed score on a reasoning puzzle test went from $200 a puzzle to about a pennyhttps://www.justaparrot.com/e/arc-agi-cost-per-task/https://www.justaparrot.com/e/arc-agi-cost-per-task/Passing 75% on a set of visual puzzles cost $200 a puzzle in December 2024 and $0.012 by July 2026. The best models still cost far more.Mon, 09 Nov 2026 00:00:00 GMTcost-of-intelligencebenchmarksAgents, long documents and video can use 10× to 1,000× more energy than a short AI prompthttps://www.justaparrot.com/e/heavy-ai-workloads-energy/https://www.justaparrot.com/e/heavy-ai-workloads-energy/A short prompt uses about 0.3 Wh, a very long document about 40 Wh, an agent task about 50 Wh. New data centres are built for heavy uses.Mon, 09 Nov 2026 00:00:00 GMTenergy-watercost-of-intelligenceGoogle DeepMind's AI solved 9 open Erdős maths problems, with every proof computer-checkedhttps://www.justaparrot.com/e/deepmind-alphaproof-nexus/https://www.justaparrot.com/e/deepmind-alphaproof-nexus/AlphaProof Nexus also settled 44 of 492 conjectures about number sequences, for a few hundred dollars each. It failed on most it tried.Mon, 09 Nov 2026 00:00:00 GMTmathcost-of-intelligenceGPT-4's level of ability got about 300× cheaper in under two years, then stopped fallinghttps://www.justaparrot.com/e/price-of-gpt4-level-performance/https://www.justaparrot.com/e/price-of-gpt4-level-performance/The cheapest model matching GPT-4 on PhD-level science fell from $37.50 to $0.12 per million tokens by late 2024. Top models stay pricey.Mon, 09 Nov 2026 00:00:00 GMTcost-of-intelligencebenchmarks