Benchmark Almanac

Falcon-Arabic-7B

Falcon-Arabic-7B.

Technology Innovation Institute Released May 21st, 2025 Family Falcon Arabic The lab's model card Compare with others
14
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Technology Innovation Institute May 2025

Falcon-Arabic-7B

Open weights Small

99.3 #394 of 404
Self-Reported Index, from the lab's own numbers. No Epoch Capabilities Index score yet.
  • IFEval 57.6% #131 /135
  • MMLU 63.3% #114 /131
  • GSM8K 67.7% #76 /92

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
ARC-Challenge 53.5% #42 of 49 Lab model card
MMLU 63.3% #114 of 131 Lab model card
WinoGrande 68.4% #42 of 47 Lab model card
HellaSwag 71.4% #48 of 53 Lab model card
IFEval 57.6% #131 of 135 Lab model card
TruthfulQA 31.5% #30 of 30 Lab model card
AlGhafa 72.4% #1 of 1 Lab model card
ALRAGE 72.3% #1 of 1 Lab model card
ArabCulture 65.2% #1 of 1 Lab model card
ArabicMMLU 68.3% #1 of 1 Lab model card
MadinahQA 73.6% #1 of 1 Lab model card
Open Arabic LLM Leaderboard v2 68.3% #1 of 1 Lab model card

Math and science

BenchmarkScoreRankSource
GSM8K 67.7% #76 of 92 Lab model card

Safety and security

BenchmarkScoreRankSource
AraTrust 82.6% #1 of 1 Lab model card

Its lab's numbers put it at 99.3, number 394 of 404

The Self-Reported Index fits one score to the 7 capability results Technology Innovation Institute reported for this model, on the scale of the Epoch Capabilities Index. Labs choose which benchmarks to show and how to run them, so read it as the lab's claim, not an independent measurement. The 90% interval runs from 95.7 to 102.8. How we compute it.

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 12 of them aren't in the launch post.