Model comparison
Qwen-14B vs Qwen2.5 7B Instruct
Qwen-14B is the stronger model overall, scoring 30.8 to 28.6 on the Noometry Index.
Last verified . 2 shared benchmarks.
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Qwen-14B scores higher in 2 categories and Qwen2.5 7B Instruct in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 7B Instruct leads 48.8 to 27.8.
Side by side
| Qwen-14B | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | 28.6 |
| Released | 2023-09-24 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 18 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Qwen-14B: 30.6 (#283), Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1072 | — |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
Qwen-14B: —, Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Qwen-14B leads
Qwen-14B: 18.7 (#255), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| Epoch Capabilities Index | 112.8 | 118.44 |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1027 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| BIG-Bench Hard | 55% | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Qwen-14B leads
Qwen-14B: 28.7 (#224), Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1068 | — |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| MMLU | 66.3% | 72.9% |
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
Multilingual Not comparable
Qwen-14B: 27.7 (#270), Qwen2.5 7B Instruct: —
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1042 | — |
| LMArena Chinese | 1077 | — |
Instruction Following Qwen2.5 7B Instruct leads
Qwen-14B: 52.6 (#284), Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1031 | — |
Long Context Not comparable
Qwen-14B: 31.3 (#276), Qwen2.5 7B Instruct: —
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1029 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Qwen-14B: 27.8 (#294), Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | Qwen-14B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1051 | — |
| LMArena Creative Writing | 1028 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1022 | — |
Frequently asked questions
Is Qwen-14B better than Qwen2.5 7B Instruct?
Qwen-14B is the stronger model overall, scoring 30.8 to 28.6 on the Noometry Index.
Is Qwen-14B or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 30.6 in the Noometry coding category.
How many benchmarks do Qwen-14B and Qwen2.5 7B Instruct share?
2 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen2.5 7B Instruct has 15.