Model comparison
Llama 2-13B vs Olmo 3.1 32b Instruct
Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 29.1 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 2-13B 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 writing & preference, where Olmo 3.1 32b Instruct leads 50.4 to 30.0.
Side by side
| Llama 2-13B | Olmo 3.1 32b Instruct | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 29.1 | 38.8 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3.1 32b Instruct leads
Llama 2-13B: 30.4 (#287), Olmo 3.1 32b Instruct: 38.9 (#154)
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Coding | 1062 | 1346 |
Reasoning Olmo 3.1 32b Instruct leads
Llama 2-13B: 12.3 (#333), Olmo 3.1 32b Instruct: 25.4 (#131)
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1322 |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 105.8 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Olmo 3.1 32b Instruct leads
Llama 2-13B: 28.7 (#226), Olmo 3.1 32b Instruct: 33.6 (#169)
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Math | 1065 | 1305 |
| GSM8K | 36.9% | — |
Knowledge Olmo 3.1 32b Instruct leads
Llama 2-13B: 27.5 (#244), Olmo 3.1 32b Instruct: 35.4 (#175)
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Expert | 1030 | 1307 |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Olmo 3.1 32b Instruct: —
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Olmo 3.1 32b Instruct leads
Llama 2-13B: 26.7 (#274), Olmo 3.1 32b Instruct: 42.8 (#185)
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Non-English | 1024 | 1275 |
| LMArena Chinese | 1001 | 1304 |
| LMArena French | 1043 | 1328 |
| LMArena German | 1009 | 1283 |
| LMArena Korean | 953 | 1206 |
| LMArena Russian | 1055 | 1268 |
| LMArena Spanish | 1086 | 1337 |
| LMArena Japanese | 894 | — |
Instruction Following Olmo 3.1 32b Instruct leads
Llama 2-13B: 53.5 (#282), Olmo 3.1 32b Instruct: 68.8 (#182)
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1046 | 1298 |
Long Context Olmo 3.1 32b Instruct leads
Llama 2-13B: 32.3 (#264), Olmo 3.1 32b Instruct: 39.9 (#161)
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1064 | 1312 |
Writing & Preference Olmo 3.1 32b Instruct leads
Llama 2-13B: 30.0 (#284), Olmo 3.1 32b Instruct: 50.4 (#179)
| Benchmark | Llama 2-13B | Olmo 3.1 32b Instruct |
|---|---|---|
| LMArena Text | 1085 | 1311 |
| LMArena Creative Writing | 1047 | 1264 |
| LMArena Multi-Turn | 1050 | 1309 |
Frequently asked questions
Is Llama 2-13B better than Olmo 3.1 32b Instruct?
Olmo 3.1 32b Instruct is the stronger model overall, scoring 38.8 to 29.1 on the Noometry Index.
Is Llama 2-13B or Olmo 3.1 32b Instruct better for coding?
Olmo 3.1 32b Instruct scores higher on coding benchmarks: 38.9 versus 30.4 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Olmo 3.1 32b Instruct share?
16 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Olmo 3.1 32b Instruct has 16.