Falcon-H1-0.5B-Base: benchmark results

Provider: TII. Released 2025-05-20. Access: Open.

Aggregate Rating 1296 ± 38, rank #8672 of 10552 rated models, from 31 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Lara Mini Base Report (base-model protocol) - GSM8K (5-shot)63.4Exact match (strict extraction: first "#### N", else first \64.8
Lara Mini Base Report (base-model protocol) - MATH (4-shot)39.2Math-Verify equivalence, Minerva prompts, 5,000 problems ove61.1
Lara Mini Base Report (base-model protocol) - MMLU-Pro (5 (CoT)-shot)33Exact match (%), English benchmark55.6
Lara Mini Base Report (base-model protocol) - PAWS (English) (0-shot)65.2Accuracy (%), English benchmark51.9
Lara Mini Base Report (base-model protocol) - CRUXEval-I (2-shot)29.4pass@1, direct prediction, official answer parser (%)42.6
Lara Mini Base Report (base-model protocol) - MBPP (3-shot)36pass@1 (execution) (%)38.9
Lara Mini Base Report (base-model protocol) - MMLU (5-shot)55.1Accuracy (%), English benchmark38
Lara Mini Base Report (base-model protocol) - MBPP+ (3-shot)40.7pass@1; must pass MBPP's own and the EvalPlus tests (%)33.3
Lara Mini Base Report (base-model protocol) - XNLI (English) (0-shot)52.3Accuracy (%), English benchmark33.3
Lara Mini Base Report (base-model protocol) - Belebele (English) (0-shot)50.1Accuracy (%), English benchmark29.6
Open Portuguese LLM - OAB Exams31.44Accuracy (%)28.1
Lara Mini Base Report (base-model protocol) - ARC-Challenge (25-shot)47.1Accuracy normalized by answer length (%), English benchmark24.1

Interactive version: theaggregate.ai/model?slug=falcon-h1-0-5b-base · How It Works · Data refreshed daily, snapshot 2026-11-16.