Model comparison
Llama 3.1-70B vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 29.4 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 3.1-70B 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 33.8 to 12.7.
Side by side
| Llama 3.1-70B | Olmo 3 32b Think | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 29.4 | 38.1 |
| Released | 2024-07-23 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 35 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
Llama 3.1-70B: 29.8 (#292), Olmo 3 32b Think: 38.0 (#169)
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1260 | 1318 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 24.9 (#104), Olmo 3 32b Think: —
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Olmo 3 32b Think leads
Llama 3.1-70B: 20.8 (#215), Olmo 3 32b Think: 24.9 (#138)
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1302 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.91 | — |
Math Olmo 3 32b Think leads
Llama 3.1-70B: 12.7 (#298), Olmo 3 32b Think: 33.8 (#165)
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1252 | 1315 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Olmo 3 32b Think leads
Llama 3.1-70B: 24.1 (#264), Olmo 3 32b Think: 34.4 (#189)
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1209 | 1272 |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual Olmo 3 32b Think leads
Llama 3.1-70B: 38.9 (#220), Olmo 3 32b Think: 41.4 (#205)
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1219 | 1255 |
| LMArena Chinese | 1215 | 1300 |
| LMArena French | 1260 | 1291 |
| LMArena German | 1222 | 1290 |
| LMArena Russian | 1234 | 1255 |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
| LMArena Spanish | 1253 | — |
Instruction Following Olmo 3 32b Think leads
Llama 3.1-70B: 65.5 (#218), Olmo 3 32b Think: 67.4 (#193)
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1231 | 1275 |
| IFEval | 82.1% | — |
Long Context Olmo 3 32b Think leads
Llama 3.1-70B: 37.6 (#208), Olmo 3 32b Think: 39.4 (#177)
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1241 | 1296 |
Writing & Preference Olmo 3 32b Think leads
Llama 3.1-70B: 35.6 (#262), Olmo 3 32b Think: 49.2 (#188)
| Benchmark | Llama 3.1-70B | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1261 | 1300 |
| LMArena Creative Writing | 1232 | 1256 |
| LMArena Multi-Turn | 1256 | 1289 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 29.4 on the Noometry Index.
Is Llama 3.1-70B or Olmo 3 32b Think better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.0 versus 29.8 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Olmo 3 32b Think share?
14 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Olmo 3 32b Think has 14.