Model comparison
Deepseek Coder v2 vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 35.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Olmo 3 32b Think in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 3 32b Think leads 49.1 to 38.2.
Side by side
| Deepseek Coder v2 | Olmo 3 32b Think | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 35.9 | 38.7 |
| Released | 2024-06-17 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Deepseek Coder v2: 38.1 (#183), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | Deepseek Coder v2 | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1251 | 1319 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Olmo 3 32b Think leads
Deepseek Coder v2: 23.6 (#176), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | Deepseek Coder v2 | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1302 |
| WinoGrande | 83.7% | — |
Math Olmo 3 32b Think leads
Deepseek Coder v2: 34.9 (#190), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | Deepseek Coder v2 | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1241 | 1316 |
| GSM8K | 94.5% | — |
Knowledge Olmo 3 32b Think leads
Deepseek Coder v2: 32.3 (#212), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | Deepseek Coder v2 | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1181 | 1273 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Olmo 3 32b Think leads
Deepseek Coder v2: 36.3 (#240), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | Deepseek Coder v2 | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1182 | 1255 |
| LMArena Chinese | 1201 | 1300 |
| LMArena French | 1185 | 1291 |
| LMArena German | 1164 | 1290 |
| LMArena Russian | 1188 | 1254 |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Olmo 3 32b Think leads
Deepseek Coder v2: 61.7 (#242), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | Deepseek Coder v2 | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1180 | 1275 |
Long Context Olmo 3 32b Think leads
Deepseek Coder v2: 37.0 (#224), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | Deepseek Coder v2 | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1219 | 1296 |
Writing & Preference Olmo 3 32b Think leads
Deepseek Coder v2: 38.2 (#253), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | Deepseek Coder v2 | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1191 | 1300 |
| LMArena Creative Writing | 1120 | 1256 |
| LMArena Multi-Turn | 1177 | 1290 |
Frequently asked questions
Is Deepseek Coder v2 better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Olmo 3 32b Think better for coding?
They score almost the same on coding (38.1 vs 38.6); test both on your own repository before choosing.
How many benchmarks do Deepseek Coder v2 and Olmo 3 32b Think share?
14 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Olmo 3 32b Think has 14.