Qwen2.5-Coder-14B-Instruct
Qwen2.5-Coder-14B-Instruct ranks first on Ko-IFEval (Upstage).
Released November 6th, 2024 Compare with others
9
Benchmarks with a score
1
Ranked first, out of five or more models
2
In the top three
Unknown lab Nov 2024
Qwen2.5-Coder-14B-Instruct
No Epoch Capabilities Index score yet
- BigCodeBench-Hard 26.6% #35 /96
- Open Arabic LLM Leaderboard v1 46.1% #22 /55
- Ko-IFEval (Upstage) 64% #1 /21
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
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Ko-IFEval (Upstage) | 64% | #1 of 21 | Official leaderboard | |
| Open Arabic LLM Leaderboard v1 | 46.1% | #22 of 55 | Official leaderboard | |
| MuSR | 39.1% | #67 of 98 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 94.2% | #2 of 70 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 52.5% | #11 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 26.6% | #35 of 96 | Official leaderboard | |
| Aider-Edit | 69.2% | #14 of 34 | Official leaderboard | |
| FullStackBench | 55.3% | #7 of 10 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Open LLM Leaderboard v2 | 32.1 | #19 of 99 | Official leaderboard |