Model comparison
DeepSeek-V3 vs Olmo 2 0325 32b Instruct
DeepSeek-V3 is the stronger model overall, scoring 39.5 to 32.7 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 16 benchmarks with published results for both. DeepSeek-V3 scores higher in 6 categories and Olmo 2 0325 32b Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3 leads 37.5 to 19.5.
- The biggest single-benchmark swing is MMLU-Pro: 72.3% for DeepSeek-V3 and 41.4% for Olmo 2 0325 32b Instruct.
Side by side
| DeepSeek-V3 | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 39.5 | 32.7 |
| Released | 2024-12-26 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 164K | — |
| Input $ / M tokens | $0.24 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 60 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3 leads
DeepSeek-V3: 42.3 (#106), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1368 | 1210 |
| Aider Polyglot | 55.1% | — |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, Olmo 2 0325 32b Instruct: —
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| METR Time Horizons | 49.6% | — |
Reasoning Olmo 2 0325 32b Instruct leads
DeepSeek-V3: 20.5 (#236), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1365 | 1208 |
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 65.8% | — |
| DTBench | 64.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 15.5% | — |
| BIG-Bench Hard | 87.5% | — |
| Epoch Capabilities Index | 135.94 | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math DeepSeek-V3 leads
DeepSeek-V3: 32.1 (#219), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| Omni-MATH | 40.3% | 16.1% |
| LMArena Math | 1373 | 1208 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge DeepSeek-V3 leads
DeepSeek-V3: 37.5 (#155), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | 72.3% | 41.4% |
| GPQA (HELM) | 53.8% | 28.7% |
| GPQA Diamond | 67.6% | — |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| LMArena Expert | 1351 | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multilingual DeepSeek-V3 leads
DeepSeek-V3: 48.5 (#143), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1358 | 1160 |
| LMArena Chinese | 1391 | 1192 |
| LMArena Russian | 1373 | 1187 |
| LMArena French | 1385 | — |
| LMArena German | 1374 | — |
| LMArena Japanese | 1333 | — |
| LMArena Korean | 1319 | — |
| LMArena Spanish | 1358 | — |
Instruction Following DeepSeek-V3 leads
DeepSeek-V3: 72.8 (#130), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| IFEval | 83.2% | 78% |
| LMArena Instruction Following | 1345 | 1186 |
| LiveBench Instruction Following | 81.5% | — |
Long Context Olmo 2 0325 32b Instruct leads
DeepSeek-V3: 34.0 (#253), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1352 | 1194 |
| Fiction.LiveBench | 50% | — |
Writing & Preference DeepSeek-V3 leads
DeepSeek-V3: 57.4 (#130), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | DeepSeek-V3 | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1375 | 1218 |
| LMArena Creative Writing | 1364 | 1199 |
| WildBench | 83% | 73.4% |
| LMArena Multi-Turn | 1389 | 1221 |
| Short-Story Creative Writing | 77% | — |
| EQ-Bench Creative Writing | 1472 | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than Olmo 2 0325 32b Instruct?
DeepSeek-V3 is the stronger model overall, scoring 39.5 to 32.7 on the Noometry Index.
Is DeepSeek-V3 or Olmo 2 0325 32b Instruct better for coding?
DeepSeek-V3 scores higher on coding benchmarks: 42.3 versus 35.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V3 and Olmo 2 0325 32b Instruct share?
16 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.