Model comparison
OLMo 2 Furious 13B vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.7 on the Noometry Index.
Last verified . 7 shared benchmarks.
Allen Institute for AI (Ai2)
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. OLMo 2 Furious 13B scores higher in 2 categories and Qwen2.5-Coder-32B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2.5-Coder-32B leads 33.4 to 18.3.
- The biggest single-benchmark swing is LiveBench Coding: 10.4% for OLMo 2 Furious 13B and 56.9% for Qwen2.5-Coder-32B.
Side by side
| OLMo 2 Furious 13B | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Alibaba (Qwen) |
| Noometry Index | 29.7 | 33.4 |
| Released | 2024-12-31 | 2024-09-18 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 12 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding OLMo 2 Furious 13B leads
OLMo 2 Furious 13B: 28.6 (#313), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | OLMo 2 Furious 13B | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Coding | 10.4% | 56.9% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LMArena Coding | — | 1276 |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Qwen2.5-Coder-32B leads
OLMo 2 Furious 13B: 15.5 (#314), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | OLMo 2 Furious 13B | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Reasoning | 16.3% | 42.1% |
| LiveBench Data Analysis | 20.6% | 49.9% |
| LiveBench | 22.1% | 46.2% |
| LMArena Hard Prompts | — | 1251 |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| WinoGrande | — | 80.8% |
Math Qwen2.5-Coder-32B leads
OLMo 2 Furious 13B: 23.1 (#273), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | OLMo 2 Furious 13B | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | 13.6% | 46.6% |
| Omni-MATH | 15.6% | — |
| LMArena Math | — | 1251 |
| GSM8K | — | 93% |
Knowledge Qwen2.5-Coder-32B leads
OLMo 2 Furious 13B: 18.3 (#283), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | OLMo 2 Furious 13B | Qwen2.5-Coder-32B |
|---|---|---|
| MMLU-Pro | 31% | — |
| GPQA (HELM) | 31.6% | — |
| LMArena Expert | — | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual Not comparable
OLMo 2 Furious 13B: —, Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | OLMo 2 Furious 13B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | — | 1205 |
| LMArena Chinese | — | 1222 |
| LMArena Russian | — | 1228 |
Instruction Following Too close to call
OLMo 2 Furious 13B: 60.9 (#248), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | OLMo 2 Furious 13B | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Instruction Following | 60.6% | 58.7% |
| IFEval | 73% | — |
| LMArena Instruction Following | — | 1223 |
Long Context Not comparable
OLMo 2 Furious 13B: —, Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | OLMo 2 Furious 13B | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | — | 1251 |
Writing & Preference OLMo 2 Furious 13B leads
OLMo 2 Furious 13B: 42.9 (#230), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | OLMo 2 Furious 13B | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Language | 11.2% | 23.3% |
| LMArena Text | — | 1230 |
| LMArena Creative Writing | — | 1174 |
| WildBench | 68.9% | — |
| LMArena Multi-Turn | — | 1222 |
Frequently asked questions
Is OLMo 2 Furious 13B better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 29.7 on the Noometry Index.
Is OLMo 2 Furious 13B or Qwen2.5-Coder-32B better for coding?
OLMo 2 Furious 13B scores higher on coding benchmarks: 28.6 versus 22.6 in the Noometry coding category.
How many benchmarks do OLMo 2 Furious 13B and Qwen2.5-Coder-32B share?
7 benchmarks have published results for both models. OLMo 2 Furious 13B has 12 scored results on Noometry and Qwen2.5-Coder-32B has 31.