HumanEval.org

Models

Claude Fable 5.1

Compare with…

HumanEval ratings

Not rated yet — ratings appear with the next official snapshot once this model has eligible votes.

External benchmarks

Curated third-party results, shown as context with provenance — the HumanEval rating from blind human votes remains the verdict.

General Intelligence

LMArena Text Arena (overall)15041493 15152026-09-02LMArena
LiveBench — Overall83.42026-09-07LiveBench

Reasoning

LiveBench — Reasoning91.72026-09-07LiveBench
Humanity's Last Exam46.5%42.6% 50.4%2026-09-08Scale AI SEAL — Humanity's Last Exam

Coding

LiveBench — Coding86.42026-09-07LiveBench

Mathematics

LiveBench — Mathematics97.02026-09-07LiveBench
OTIS Mock AIME 2024–2025100.0%100.0% 100.0%2026-09-01Epoch AI Benchmarking Hub

Agentic

LiveBench — Agentic Coding66.12026-09-07LiveBench
Terminal-Bench 4.057.9%54.1% 61.6%2026-09-01Terminal-Bench

Language

LiveBench — Language89.52026-09-07LiveBench

Data analytics

LiveBench — Data Analysis80.32026-09-07LiveBench

Instruction following

LiveBench — Instruction Following73.02026-09-07LiveBench

Benchmark percentile by metric group

Percentile of this model within the 19 listed LLM models per metric group (100 = best, averaged across the group's external benchmarks), against the roster median. External data only — not the HumanEval rating.

Win rate by opponent

No eligible head-to-head votes yet. Ties count as half a win for each side.

Sample battles

Curated prompts only, with vote tallies — voter identities are never published.

No published sample battles yet — battles appear here once this model has eligible votes on curated prompts.