Model comparison
Llama 3-70B vs Olmo 2 0325 32b Instruct
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 28.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Llama 3-70B scores higher in 4 categories and Olmo 2 0325 32b Instruct in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 2 0325 32b Instruct leads 24.8 to 12.0.
Side by side
| Llama 3-70B | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 28.5 | 32.2 |
| Released | 2024-04-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-70B: 35.3 (#215), Olmo 2 0325 32b Instruct: 34.6 (#222)
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1206 | 1210 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 20.9 (#132), Olmo 2 0325 32b Instruct: —
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| Cybench | 5% | — |
Reasoning Olmo 2 0325 32b Instruct leads
Llama 3-70B: 17.4 (#284), Olmo 2 0325 32b Instruct: 22.6 (#174)
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1208 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.91 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Olmo 2 0325 32b Instruct leads
Llama 3-70B: 12.0 (#299), Olmo 2 0325 32b Instruct: 24.8 (#255)
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1218 | 1208 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | — | 16.1% |
| MATH Level 5 | 22.6% | — |
Knowledge Llama 3-70B leads
Llama 3-70B: 20.8 (#272), Olmo 2 0325 32b Instruct: 19.2 (#274)
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| GPQA Diamond | 40.6% | — |
| MMLU-Pro | — | 41.4% |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1149 | — |
| MMLU | 79.3% | — |
Multilingual Olmo 2 0325 32b Instruct leads
Llama 3-70B: 33.8 (#246), Olmo 2 0325 32b Instruct: 35.0 (#243)
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1142 | 1160 |
| LMArena Chinese | 1114 | 1192 |
| LMArena Russian | 1159 | 1187 |
| LMArena French | 1231 | — |
| LMArena German | 1169 | — |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Too close to call
Llama 3-70B: 62.8 (#233), Olmo 2 0325 32b Instruct: 61.8 (#238)
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1194 | 1186 |
| IFEval | — | 78% |
Long Context Too close to call
Llama 3-70B: 35.6 (#235), Olmo 2 0325 32b Instruct: 36.2 (#229)
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1174 | 1194 |
Writing & Preference Too close to call
Llama 3-70B: 43.0 (#225), Olmo 2 0325 32b Instruct: 42.3 (#231)
| Benchmark | Llama 3-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1221 | 1218 |
| LMArena Creative Writing | 1210 | 1199 |
| LMArena Multi-Turn | 1223 | 1221 |
| WildBench | — | 73.4% |
Frequently asked questions
Is Llama 3-70B better than Olmo 2 0325 32b Instruct?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 28.5 on the Noometry Index.
Is Llama 3-70B or Olmo 2 0325 32b Instruct better for coding?
They score almost the same on coding (35.3 vs 34.6); test both on your own repository before choosing.
How many benchmarks do Llama 3-70B and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.