Model comparison
Llama 3.1-70B vs Olmo 3.1 32b Think
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 29.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 15 benchmarks with published results for both. Llama 3.1-70B scores higher in 1 category and Olmo 3.1 32b Think in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3.1 32b Think leads 36.3 to 13.5.
Side by side
| Llama 3.1-70B | Olmo 3.1 32b Think | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 29.6 | 37.9 |
| 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 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3.1 32b Think leads
Llama 3.1-70B: 30.3 (#296), Olmo 3.1 32b Think: 37.7 (#189)
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Coding | 1260 | 1291 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Olmo 3.1 32b Think: —
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Olmo 3.1 32b Think leads
Llama 3.1-70B: 21.6 (#220), Olmo 3.1 32b Think: 25.2 (#150)
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1272 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.92 | — |
Math Olmo 3.1 32b Think leads
Llama 3.1-70B: 13.5 (#304), Olmo 3.1 32b Think: 36.3 (#168)
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Math | 1252 | 1305 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Olmo 3.1 32b Think leads
Llama 3.1-70B: 24.2 (#269), Olmo 3.1 32b Think: 35.7 (#181)
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Expert | 1209 | 1295 |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| MMLU | 80.1% | — |
Multilingual Too close to call
Llama 3.1-70B: 38.8 (#225), Olmo 3.1 32b Think: 38.1 (#231)
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Non-English | 1219 | 1209 |
| LMArena Chinese | 1215 | 1242 |
| LMArena French | 1261 | 1260 |
| LMArena German | 1222 | 1262 |
| LMArena Russian | 1234 | 1193 |
| LMArena Spanish | 1253 | 1289 |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
Instruction Following Too close to call
Llama 3.1-70B: 65.3 (#223), Olmo 3.1 32b Think: 65.6 (#218)
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Instruction Following | 1231 | 1247 |
| IFEval | 82.1% | — |
Long Context Too close to call
Llama 3.1-70B: 37.6 (#214), Olmo 3.1 32b Think: 38.6 (#195)
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Longer Query | 1241 | 1272 |
Writing & Preference Olmo 3.1 32b Think leads
Llama 3.1-70B: 35.4 (#267), Olmo 3.1 32b Think: 46.2 (#220)
| Benchmark | Llama 3.1-70B | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Text | 1261 | 1272 |
| LMArena Creative Writing | 1232 | 1226 |
| LMArena Multi-Turn | 1256 | 1252 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Olmo 3.1 32b Think?
Olmo 3.1 32b Think is the stronger model overall, scoring 37.9 to 29.6 on the Noometry Index.
Is Llama 3.1-70B or Olmo 3.1 32b Think better for coding?
Olmo 3.1 32b Think scores higher on coding benchmarks: 37.7 versus 30.3 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Olmo 3.1 32b Think share?
15 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Olmo 3.1 32b Think has 15.