Model comparison
Llama 3-70B vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 28.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Llama 3-70B 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 math, where Olmo 3 32b Think leads 36.5 to 12.8.
Side by side
| Llama 3-70B | Olmo 3 32b Think | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 28.8 | 38.7 |
| Released | 2024-04-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
Llama 3-70B: 35.8 (#218), Olmo 3 32b Think: 38.6 (#172)
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1206 | 1319 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Olmo 3 32b Think: —
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| Cybench | 5% | — |
Reasoning Olmo 3 32b Think leads
Llama 3-70B: 18.0 (#288), Olmo 3 32b Think: 25.9 (#140)
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1302 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Olmo 3 32b Think leads
Llama 3-70B: 12.8 (#305), Olmo 3 32b Think: 36.5 (#165)
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1218 | 1316 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |
Knowledge Olmo 3 32b Think leads
Llama 3-70B: 20.8 (#277), Olmo 3 32b Think: 35.0 (#190)
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1149 | 1273 |
| GPQA Diamond | 40.6% | — |
| MMLU | 79.3% | — |
Multilingual Olmo 3 32b Think leads
Llama 3-70B: 33.6 (#251), Olmo 3 32b Think: 41.2 (#210)
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1142 | 1255 |
| LMArena Chinese | 1114 | 1300 |
| LMArena French | 1232 | 1291 |
| LMArena German | 1169 | 1290 |
| LMArena Russian | 1159 | 1254 |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Olmo 3 32b Think leads
Llama 3-70B: 62.5 (#238), Olmo 3 32b Think: 67.2 (#198)
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1194 | 1275 |
Long Context Olmo 3 32b Think leads
Llama 3-70B: 35.6 (#240), Olmo 3 32b Think: 39.4 (#182)
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1174 | 1296 |
Writing & Preference Olmo 3 32b Think leads
Llama 3-70B: 42.8 (#231), Olmo 3 32b Think: 49.1 (#193)
| Benchmark | Llama 3-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1221 | 1300 |
| LMArena Creative Writing | 1210 | 1256 |
| LMArena Multi-Turn | 1223 | 1290 |
Frequently asked questions
Is Llama 3-70B better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.7 to 28.8 on the Noometry Index.
Is Llama 3-70B or Olmo 3 32b Think better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.6 versus 35.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Olmo 3 32b Think share?
14 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Olmo 3 32b Think has 14.