Benchmark Almanac

Qwen2.5-1.5B

Qwen2.5-1.5B.

Qwen Released September 19th, 2024 Family Qwen2.5 The lab's model card Compare with others
21
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Sep 2024

Qwen2.5-1.5B

Open weights Small

No Epoch Capabilities Index score yet
  • BigCodeBench-Hard 3.00% #94 /96
  • Open Arabic LLM Leaderboard v1 39.6% #40 /55
  • AlGhafa 48.4% #26 /39

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
ArabicMMLU 43.5% #24 of 39 Official leaderboard
AlGhafa 48.4% #26 of 39 Official leaderboard
ArbMMLU-HT 35.9% #26 of 39 Official leaderboard
MadinahQA 38.2% #26 of 39 Official leaderboard
Open Arabic LLM Leaderboard v2 47.2% #26 of 39 Official leaderboard
ALRAGE 61.6% #27 of 39 Official leaderboard
Open Arabic LLM Leaderboard v1 39.6% #40 of 55 Official leaderboard
HELMET 12.9% #12 of 16 Official leaderboard
MMLU-CF 51.2% #30 of 37 Official leaderboard
MLogiQA 35.1% #14 of 17 Official leaderboard
MMLU-Pro 32.1% #177 of 212 Official leaderboard
MuSR 35.8% #85 of 98 Official leaderboard
SuperGPQA 18.8% #55 of 59 Official leaderboard
Vectara Hallucination Leaderboard (HHEM) 15.8% #140 of 148 Official leaderboard
FaithJudge 66.7% #35 of 37 Official leaderboard
Chinese SimpleQA 12% #27 of 27 Official leaderboard

Coding

BenchmarkScoreRankSource
BigCodeBench 23.7% #64 of 69 Official leaderboard
BigCodeBench-Hard 3.00% #94 of 96 Official leaderboard

Agents and tools

BenchmarkScoreRankSource
C3-Bench 3.91% #25 of 30 Official leaderboard

Safety and security

BenchmarkScoreRankSource
AraTrust 70.8% #23 of 39 Official leaderboard

Other

BenchmarkScoreRankSource
Open LLM Leaderboard v2 13.8 #78 of 99 Official leaderboard