Artificial Analysis launches Progress Index, a single capability scale for every LLM since 2022
scaling01 · x · 2026-10-30
Artificial Analysis announced the Progress Index, a single capability scale covering every language model since 2022, launched alongside Intelligence Index v5.
- The Intelligence Index remains the primary measure of current model intelligence, using the evaluations most relevant to developers today; its mix changes over time and scores across versions aren't comparable.
- The Progress Index is built for cross-time comparison: it applies item response theory (the statistical method behind standardized testing) to estimate one general capability score per model from underlying tasks across all evaluations, including retired ones.
- Guidance: use the Intelligence Index to pick a model today, the Progress Index to track how capability has evolved.
The accompanying chart shows steady stepwise capability gains from Google, Anthropic, OpenAI, Meta and xAI from November 2022 to late 2026.
More from Models
- Local Gemma 'completely good enough' for non-coding tasks, designer finds — michalmalewicz · 2026-10-30
- Gemini Pro silently downgraded to Flash all day citing high demand — General_Internet_511 · 2026-10-30
- Baseten releases joey-1, a 2B open-source decision model with single-forward-pass probabilities — baseten · 2026-10-30
- Counting plans, the cheap Chinese model costs 51x Claude Haiku — rickasaurus · 2026-10-30
- Dream raises $17M seed from a16z to build spatial-reasoning AI for AEC — a16z · 2026-10-30
- Investor bets speech-to-speech will be massive, praises Phonic's model — graceisford · 2026-10-30