Skip to catalog
FbFable
CatalogLabsScoresCompare

How to read the board · 2026-08-28

Scores

A leaderboard is a compressed story. These are the axes Fable uses, and the jobs they actually speak to.

The top is crowded on purpose
Claude Opus 5 at 63, Fable 5 at 62, Sol and Grok 4.6 at 61. That spread is close to noise. When quality ties, cost per task, speed, context pricing cliffs, and whether you can download the weights decide.
  1. 01 · 0–100

    Intelligence Index

    Artificial Analysis composite of nine evals: agents, coding, scientific reasoning, and long-context work.

    The single number most people mean by “how smart.” It is a blend, so a specialist can lose here and still win the job you care about.

  2. 02 · %

    GPQA Diamond

    198 PhD-level science questions written so Google does not help a smart non-expert.

    A clean test of hard reasoning. PhD experts sit around 65%. It says little about writing, tools, or taste.

  3. 03 · %

    Terminal-Bench 2.1

    The model has to finish real tasks in a shell: install, debug, patch, verify.

    Closest public proxy for coding agents that live in a terminal. A high index score with a weak terminal score is a warning.

  4. 04 · Elo

    Code Arena Elo

    Blind pairwise human votes on coding answers.

    Captures taste and usefulness that unit tests miss. Sample size varies by model, so treat gaps under ~100 Elo as noise.

  5. 05 · 0–100

    Agentic Index

    Independent composite of multi-step tool use: plan, act, check, retry.

    Chat quality and agent quality have split. Some models think well and stall in a loop. Others grind through jobs.

  6. 06 · tok/s

    Output speed

    Tokens generated per second on a hosted API, averaged over a rolling window.

    Matters for streaming chat and agent loops. Irrelevant for overnight batch jobs. Price per task usually matters more.

  7. 07 · USD

    Cost per task

    Measured spend to finish a standard independent task, not the sticker price per million tokens.

    Verbose reasoning, retries, and long-context surcharges eat cheap rates. This is the number that shows up on the invoice.

Compiled 2026-08-28 from public Artificial Analysis, LMSYS-style arena, and first-party price sheets. Scores move. Recheck before you spend.

A two-point gap on the intelligence index is noise for most work. Cost per finished task is the number that shows up on the invoice.