Model comparison
DeepSeek-V3.1 vs Olmo 2 0325 32b Instruct
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 32.2 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and Olmo 2 0325 32b Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.0 to 19.2.
Side by side
| DeepSeek-V3.1 | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 42.2 | 32.2 |
| Released | 2025-08-21 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 39.8 (#140), Olmo 2 0325 32b Instruct: 34.6 (#222)
| Benchmark | DeepSeek-V3.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1417 | 1210 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.3 (#109), Olmo 2 0325 32b Instruct: 22.6 (#174)
| Benchmark | DeepSeek-V3.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1208 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 36.1 (#125), Olmo 2 0325 32b Instruct: 24.8 (#255)
| Benchmark | DeepSeek-V3.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1420 | 1208 |
| Omni-MATH | — | 16.1% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.0 (#86), Olmo 2 0325 32b Instruct: 19.2 (#274)
| Benchmark | DeepSeek-V3.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | — | 41.4% |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1403 | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.8 (#100), Olmo 2 0325 32b Instruct: 35.0 (#243)
| Benchmark | DeepSeek-V3.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1400 | 1160 |
| LMArena Chinese | 1470 | 1192 |
| LMArena Russian | 1405 | 1187 |
| LMArena French | 1447 | — |
| LMArena German | 1412 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1337 | — |
| LMArena Spanish | 1429 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 74.1 (#105), Olmo 2 0325 32b Instruct: 61.8 (#238)
| Benchmark | DeepSeek-V3.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1400 | 1186 |
| IFEval | — | 78% |
Long Context Too close to call
DeepSeek-V3.1: 36.3 (#227), Olmo 2 0325 32b Instruct: 36.2 (#229)
| Benchmark | DeepSeek-V3.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1422 | 1194 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.5 (#93), Olmo 2 0325 32b Instruct: 42.3 (#231)
| Benchmark | DeepSeek-V3.1 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1420 | 1218 |
| LMArena Creative Writing | 1401 | 1199 |
| LMArena Multi-Turn | 1408 | 1221 |
| EQ-Bench Creative Writing | 1436 | — |
| WildBench | — | 73.4% |
Frequently asked questions
Is DeepSeek-V3.1 better than Olmo 2 0325 32b Instruct?
DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 32.2 on the Noometry Index.
Is DeepSeek-V3.1 or Olmo 2 0325 32b Instruct better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 34.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.