All projects on Base matching “eval”

Exact symbolic computation (SymPy): simplify, differentiate, integrate, solve equations/systems, limits, series, Laplace/Fourier transforms, arbitrary-precision eval. Expressions are JSON ASTs; every result is numerically verified. Paid in USDC on Base or Solana.

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence for each. Built for routing, classification, triage and policy checks where a fast, predictable, machine-readable answer beats prose.

Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence for each. Built for routing, classification, triage and policy checks where a fast, predictable, machine-readable answer beats prose.

Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence for each. Built for routing, classification, triage and policy checks where a fast, predictable, machine-readable answer beats prose.

Verify a claim against supplied context or live web evidence.

Custom-weight rerank of every cryptocurrency covered by True Value Rankings: the full TVR table recomputed with the caller's own weights for the 8 fundamental metrics, using TVR's non-public score transformation. $0.05 USDC per call. Educational model output, not a recommendation.

Evaluate a chess position with Stockfish: best move, centipawn/mate score, principal variation, and optional multipv. No mocks — a real single-threaded Stockfish 10 (asm.js) runs in-isolate per call.

Marketing copy quality gate and pre-publish copy review for autonomous agents about to publish or send ad, landing-page, email, CTA, campaign or GTM copy. Returns a fast PASS/WARN/BLOCK verdict, claim-risk flags and prioritized fixes before release. Standard machine terms: https://nexuseval.vercel.app/terms.json 2026-08-29-v2.

Research PoC: catalog-timing comparison w/ live URL (rsrcheval_live_fs_t1791706212)