Model comparison
DeepSeek-V3.1 vs Olmo 3 32b Think
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.7 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-V3.1 scores higher in 7 categories and Olmo 3 32b Think in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 49.1.
Side by side
| DeepSeek-V3.1 | Olmo 3 32b Think | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 42.8 | 38.7 |
| 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 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | DeepSeek-V3.1 | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1417 | 1319 |
| WeirdML | 38.4% | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | DeepSeek-V3.1 | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1302 |
| 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: 38.9 (#122), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | DeepSeek-V3.1 | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1420 | 1316 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | DeepSeek-V3.1 | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1405 | 1273 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | DeepSeek-V3.1 | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1400 | 1255 |
| LMArena Chinese | 1469 | 1300 |
| LMArena French | 1447 | 1291 |
| LMArena German | 1411 | 1290 |
| LMArena Russian | 1405 | 1254 |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Spanish | 1431 | — |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | DeepSeek-V3.1 | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1400 | 1275 |
Long Context Olmo 3 32b Think leads
DeepSeek-V3.1: 36.3 (#232), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | DeepSeek-V3.1 | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1422 | 1296 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | DeepSeek-V3.1 | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1420 | 1300 |
| LMArena Creative Writing | 1401 | 1256 |
| LMArena Multi-Turn | 1408 | 1290 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Olmo 3 32b Think?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.7 on the Noometry Index.
Is DeepSeek-V3.1 or Olmo 3 32b Think better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 38.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and Olmo 3 32b Think share?
14 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Olmo 3 32b Think has 14.