Model comparison
Llama 3.1-405B vs Olmo 3.1 32b Instruct
Olmo 3.1 32b Instruct is the stronger model overall, scoring 39.4 to 30.7 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 3.1-405B scores higher in 0 categories and Olmo 3.1 32b Instruct in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Olmo 3.1 32b Instruct leads 36.3 to 18.4.
Side by side
| Llama 3.1-405B | Olmo 3.1 32b Instruct | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 30.7 | 39.4 |
| Released | 2024-07-23 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3.1 32b Instruct leads
Llama 3.1-405B: 33.1 (#262), Olmo 3.1 32b Instruct: 39.5 (#157)
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Coding | 1291 | 1347 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Olmo 3.1 32b Instruct: —
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Olmo 3.1 32b Instruct leads
Llama 3.1-405B: 16.8 (#300), Olmo 3.1 32b Instruct: 26.4 (#132)
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1322 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Olmo 3.1 32b Instruct leads
Llama 3.1-405B: 18.4 (#290), Olmo 3.1 32b Instruct: 36.3 (#167)
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Math | 1281 | 1305 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Olmo 3.1 32b Instruct leads
Llama 3.1-405B: 30.4 (#227), Olmo 3.1 32b Instruct: 36.1 (#175)
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Expert | 1243 | 1308 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Olmo 3.1 32b Instruct leads
Llama 3.1-405B: 40.7 (#214), Olmo 3.1 32b Instruct: 42.6 (#191)
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | 1248 | 1275 |
| LMArena Chinese | 1242 | 1304 |
| LMArena French | 1279 | 1328 |
| LMArena German | 1252 | 1282 |
| LMArena Korean | 1184 | 1206 |
| LMArena Russian | 1265 | 1268 |
| LMArena Spanish | 1260 | 1336 |
| LMArena Japanese | 1208 | — |
Instruction Following Olmo 3.1 32b Instruct leads
Llama 3.1-405B: 65.9 (#214), Olmo 3.1 32b Instruct: 68.6 (#187)
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1259 | 1299 |
| IFEval | 81.1% | — |
Long Context Olmo 3.1 32b Instruct leads
Llama 3.1-405B: 38.4 (#197), Olmo 3.1 32b Instruct: 39.9 (#166)
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1266 | 1312 |
Writing & Preference Olmo 3.1 32b Instruct leads
Llama 3.1-405B: 38.9 (#251), Olmo 3.1 32b Instruct: 50.2 (#185)
| Benchmark | Llama 3.1-405B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | 1284 | 1311 |
| LMArena Creative Writing | 1262 | 1264 |
| LMArena Multi-Turn | 1297 | 1309 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Olmo 3.1 32b Instruct?
Olmo 3.1 32b Instruct is the stronger model overall, scoring 39.4 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Olmo 3.1 32b Instruct better for coding?
Olmo 3.1 32b Instruct scores higher on coding benchmarks: 39.5 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Olmo 3.1 32b Instruct share?
16 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Olmo 3.1 32b Instruct has 16.