Model comparison
Llama 3.1-70B vs Olmo 2 0325 32b Instruct
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 29.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 16 benchmarks with published results for both. Llama 3.1-70B scores higher in 4 categories and Olmo 2 0325 32b Instruct in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 2 0325 32b Instruct leads 24.8 to 12.7.
- The biggest single-benchmark swing is MMLU-Pro: 65.3% for Llama 3.1-70B and 41.4% for Olmo 2 0325 32b Instruct.
Side by side
| Llama 3.1-70B | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 29.4 | 32.2 |
| 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 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 2 0325 32b Instruct leads
Llama 3.1-70B: 29.8 (#292), Olmo 2 0325 32b Instruct: 34.6 (#222)
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1260 | 1210 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 24.9 (#104), Olmo 2 0325 32b Instruct: —
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Olmo 2 0325 32b Instruct leads
Llama 3.1-70B: 20.8 (#215), Olmo 2 0325 32b Instruct: 22.6 (#174)
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1208 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.91 | — |
Math Olmo 2 0325 32b Instruct leads
Llama 3.1-70B: 12.7 (#298), Olmo 2 0325 32b Instruct: 24.8 (#255)
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| Omni-MATH | 21% | 16.1% |
| LMArena Math | 1252 | 1208 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Llama 3.1-70B leads
Llama 3.1-70B: 24.1 (#264), Olmo 2 0325 32b Instruct: 19.2 (#274)
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| MMLU-Pro | 65.3% | 41.4% |
| GPQA (HELM) | 42.6% | 28.7% |
| GPQA Diamond | 44.2% | — |
| LMArena Expert | 1209 | — |
| MMLU | 80.1% | — |
Multilingual Llama 3.1-70B leads
Llama 3.1-70B: 38.9 (#220), Olmo 2 0325 32b Instruct: 35.0 (#243)
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1219 | 1160 |
| LMArena Chinese | 1215 | 1192 |
| LMArena Russian | 1234 | 1187 |
| LMArena French | 1260 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
| LMArena Spanish | 1253 | — |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.5 (#218), Olmo 2 0325 32b Instruct: 61.8 (#238)
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| IFEval | 82.1% | 78% |
| LMArena Instruction Following | 1231 | 1186 |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#208), Olmo 2 0325 32b Instruct: 36.2 (#229)
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1241 | 1194 |
Writing & Preference Olmo 2 0325 32b Instruct leads
Llama 3.1-70B: 35.6 (#262), Olmo 2 0325 32b Instruct: 42.3 (#231)
| Benchmark | Llama 3.1-70B | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1261 | 1218 |
| LMArena Creative Writing | 1232 | 1199 |
| WildBench | 75.8% | 73.4% |
| LMArena Multi-Turn | 1256 | 1221 |
| EQ-Bench Creative Writing | 784 | — |
Frequently asked questions
Is Llama 3.1-70B better than Olmo 2 0325 32b Instruct?
Olmo 2 0325 32b Instruct is the stronger model overall, scoring 32.2 to 29.4 on the Noometry Index.
Is Llama 3.1-70B or Olmo 2 0325 32b Instruct better for coding?
Olmo 2 0325 32b Instruct scores higher on coding benchmarks: 34.6 versus 29.8 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Olmo 2 0325 32b Instruct share?
16 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.