Model comparison
DeepSeek LLM 67B vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Olmo 3 32b Think in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Olmo 3 32b Think leads 35.0 to 7.0.
Side by side
| DeepSeek LLM 67B | Olmo 3 32b Think | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 24.9 | 38.7 |
| Released | 2023-11-29 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
DeepSeek LLM 67B: 31.9 (#278), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | DeepSeek LLM 67B | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1096 | 1319 |
Reasoning Olmo 3 32b Think leads
DeepSeek LLM 67B: 16.5 (#304), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | DeepSeek LLM 67B | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1302 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.5 | — |
Math Olmo 3 32b Think leads
DeepSeek LLM 67B: 8.7 (#324), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | DeepSeek LLM 67B | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1108 | 1316 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| MATH Level 5 | 6.4% | — |
Knowledge Olmo 3 32b Think leads
DeepSeek LLM 67B: 7.0 (#313), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | DeepSeek LLM 67B | Olmo 3 32b Think |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1273 |
Multilingual Olmo 3 32b Think leads
DeepSeek LLM 67B: 29.4 (#267), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | DeepSeek LLM 67B | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1073 | 1255 |
| LMArena Chinese | 1132 | 1300 |
| LMArena French | — | 1291 |
| LMArena German | — | 1290 |
| LMArena Russian | — | 1254 |
Instruction Following Olmo 3 32b Think leads
DeepSeek LLM 67B: 55.4 (#277), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | DeepSeek LLM 67B | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1079 | 1275 |
Long Context Olmo 3 32b Think leads
DeepSeek LLM 67B: 33.1 (#265), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | DeepSeek LLM 67B | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1092 | 1296 |
Writing & Preference Olmo 3 32b Think leads
DeepSeek LLM 67B: 31.6 (#282), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | DeepSeek LLM 67B | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1105 | 1300 |
| LMArena Creative Writing | 1067 | 1256 |
| LMArena Multi-Turn | 1082 | 1290 |
Frequently asked questions
Is DeepSeek LLM 67B better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Olmo 3 32b Think better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Olmo 3 32b Think share?
10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Olmo 3 32b Think has 14.