Model comparison
Olmo 2 0325 32b Instruct vs Qwen-14B
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Olmo 2 0325 32b Instruct scores higher in 6 categories and Qwen-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 2 0325 32b Instruct leads 42.3 to 27.8.
Side by side
| Olmo 2 0325 32b Instruct | Qwen-14B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 32.2 | 30.8 |
| Released | — | 2023-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 34.6 (#222), Qwen-14B: 30.6 (#283)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen-14B |
|---|---|---|
| LMArena Coding | 1210 | 1072 |
Reasoning Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 22.6 (#174), Qwen-14B: 18.7 (#255)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1208 | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 112.8 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Olmo 2 0325 32b Instruct: 24.8 (#255), Qwen-14B: 28.7 (#224)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen-14B |
|---|---|---|
| LMArena Math | 1208 | 1068 |
| Omni-MATH | 16.1% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Olmo 2 0325 32b Instruct: 19.2 (#274), Qwen-14B: —
| Benchmark | Olmo 2 0325 32b Instruct | Qwen-14B |
|---|---|---|
| MMLU-Pro | 41.4% | — |
| GPQA (HELM) | 28.7% | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 35.0 (#243), Qwen-14B: 27.7 (#270)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1160 | 1042 |
| LMArena Chinese | 1192 | 1077 |
| LMArena Russian | 1187 | — |
Instruction Following Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 61.8 (#238), Qwen-14B: 52.6 (#284)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1186 | 1031 |
| IFEval | 78% | — |
Long Context Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 36.2 (#229), Qwen-14B: 31.3 (#276)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1194 | 1029 |
Writing & Preference Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 42.3 (#231), Qwen-14B: 27.8 (#294)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen-14B |
|---|---|---|
| LMArena Text | 1218 | 1051 |
| LMArena Creative Writing | 1199 | 1028 |
| LMArena Multi-Turn | 1221 | 1022 |
| WildBench | 73.4% | — |
Frequently asked questions
Is Olmo 2 0325 32b Instruct better than Qwen-14B?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 30.8 on the Noometry Index.
Is Olmo 2 0325 32b Instruct or Qwen-14B better for coding?
Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 34.6 versus 30.6 in the Noometry coding category.
How many benchmarks do Olmo 2 0325 32b Instruct and Qwen-14B share?
10 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Qwen-14B has 18.