Model comparison
Deepseek Coder v2 vs Olmo 3.1 32b Think
Olmo 3.1 32b Think is the stronger model overall, scoring 37.3 to 35.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 15 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Olmo 3.1 32b Think in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Olmo 3.1 32b Think leads 46.4 to 38.4.
Side by side
| Deepseek Coder v2 | Olmo 3.1 32b Think | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 35.3 | 37.3 |
| Released | 2024-06-17 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Deepseek Coder v2: 37.5 (#178), Olmo 3.1 32b Think: 37.1 (#186)
| Benchmark | Deepseek Coder v2 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Coding | 1251 | 1292 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Olmo 3.1 32b Think leads
Deepseek Coder v2: 22.6 (#175), Olmo 3.1 32b Think: 24.1 (#151)
| Benchmark | Deepseek Coder v2 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1272 |
| WinoGrande | 83.7% | — |
Math Olmo 3.1 32b Think leads
Deepseek Coder v2: 32.3 (#188), Olmo 3.1 32b Think: 33.6 (#170)
| Benchmark | Deepseek Coder v2 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Math | 1241 | 1305 |
| GSM8K | 94.5% | — |
Knowledge Olmo 3.1 32b Think leads
Deepseek Coder v2: 31.7 (#209), Olmo 3.1 32b Think: 35.0 (#178)
| Benchmark | Deepseek Coder v2 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Expert | 1181 | 1294 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Olmo 3.1 32b Think leads
Deepseek Coder v2: 36.4 (#235), Olmo 3.1 32b Think: 38.3 (#226)
| Benchmark | Deepseek Coder v2 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Non-English | 1182 | 1210 |
| LMArena Chinese | 1201 | 1241 |
| LMArena French | 1184 | 1262 |
| LMArena German | 1164 | 1260 |
| LMArena Russian | 1188 | 1193 |
| LMArena Spanish | 1153 | 1288 |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
Instruction Following Olmo 3.1 32b Think leads
Deepseek Coder v2: 61.9 (#237), Olmo 3.1 32b Think: 65.8 (#213)
| Benchmark | Deepseek Coder v2 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Instruction Following | 1180 | 1246 |
Long Context Olmo 3.1 32b Think leads
Deepseek Coder v2: 37.0 (#219), Olmo 3.1 32b Think: 38.6 (#190)
| Benchmark | Deepseek Coder v2 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Longer Query | 1219 | 1272 |
Writing & Preference Olmo 3.1 32b Think leads
Deepseek Coder v2: 38.4 (#249), Olmo 3.1 32b Think: 46.4 (#215)
| Benchmark | Deepseek Coder v2 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Text | 1191 | 1271 |
| LMArena Creative Writing | 1120 | 1226 |
| LMArena Multi-Turn | 1176 | 1252 |
Frequently asked questions
Is Deepseek Coder v2 better than Olmo 3.1 32b Think?
Olmo 3.1 32b Think is the stronger model overall, scoring 37.3 to 35.3 on the Noometry Index.
Is Deepseek Coder v2 or Olmo 3.1 32b Think better for coding?
They score almost the same on coding (37.5 vs 37.1); test both on your own repository before choosing.
How many benchmarks do Deepseek Coder v2 and Olmo 3.1 32b Think share?
15 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Olmo 3.1 32b Think has 15.