Model comparison
Olmo 2 0325 32b Instruct vs Qwen1.5-72B
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 30.3 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Olmo 2 0325 32b Instruct scores higher in 7 categories and Qwen1.5-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Olmo 2 0325 32b Instruct leads 19.2 to 11.5.
Side by side
| Olmo 2 0325 32b Instruct | Qwen1.5-72B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 32.2 | 30.3 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 22 |
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), Qwen1.5-72B: 31.4 (#272)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1210 | 1166 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 22.6 (#174), Qwen1.5-72B: 21.2 (#201)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1208 | 1148 |
Math Qwen1.5-72B leads
Olmo 2 0325 32b Instruct: 24.8 (#255), Qwen1.5-72B: 30.7 (#205)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1208 | 1164 |
| Omni-MATH | 16.1% | — |
Knowledge Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 19.2 (#274), Qwen1.5-72B: 11.5 (#295)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | — | 28.8% |
| MMLU-Pro | 41.4% | — |
| GPQA (HELM) | 28.7% | — |
| LMArena Expert | — | 1136 |
Multilingual Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 35.0 (#243), Qwen1.5-72B: 33.4 (#248)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1160 | 1135 |
| LMArena Chinese | 1192 | 1186 |
| LMArena Russian | 1187 | 1104 |
| LMArena French | — | 1158 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1049 |
| LMArena Spanish | — | 1110 |
Instruction Following Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 61.8 (#238), Qwen1.5-72B: 59.6 (#251)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1186 | 1142 |
| IFEval | 78% | — |
Long Context Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 36.2 (#229), Qwen1.5-72B: 35.0 (#238)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1194 | 1157 |
Writing & Preference Olmo 2 0325 32b Instruct leads
Olmo 2 0325 32b Instruct: 42.3 (#231), Qwen1.5-72B: 37.4 (#253)
| Benchmark | Olmo 2 0325 32b Instruct | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1218 | 1166 |
| LMArena Creative Writing | 1199 | 1137 |
| LMArena Multi-Turn | 1221 | 1160 |
| WildBench | 73.4% | — |
Frequently asked questions
Is Olmo 2 0325 32b Instruct better than Qwen1.5-72B?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 30.3 on the Noometry Index.
Is Olmo 2 0325 32b Instruct or Qwen1.5-72B better for coding?
Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 34.6 versus 31.4 in the Noometry coding category.
How many benchmarks do Olmo 2 0325 32b Instruct and Qwen1.5-72B share?
11 benchmarks have published results for both models. Olmo 2 0325 32b Instruct has 16 scored results on Noometry and Qwen1.5-72B has 22.