Model comparison
Llama 13b vs Olmo 7b Instruct
Olmo 7b Instruct is the stronger model overall, scoring 30.3 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 8 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Olmo 7b Instruct in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Olmo 7b Instruct leads 49.0 to 36.7.
Side by side
| Llama 13b | Olmo 7b Instruct | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 24.4 | 30.3 |
| Released | 2023-02-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 7b Instruct leads
Llama 13b: 21.4 (#337), Olmo 7b Instruct: 29.6 (#303)
| Benchmark | Llama 13b | Olmo 7b Instruct |
|---|---|---|
| LMArena Coding | 683 | 1016 |
Reasoning Olmo 7b Instruct leads
Llama 13b: 14.0 (#329), Olmo 7b Instruct: 18.8 (#274)
| Benchmark | Llama 13b | Olmo 7b Instruct |
|---|---|---|
| LMArena Hard Prompts | 728 | 993 |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Olmo 7b Instruct leads
Llama 13b: 26.7 (#256), Olmo 7b Instruct: 30.2 (#237)
| Benchmark | Llama 13b | Olmo 7b Instruct |
|---|---|---|
| LMArena Math | 838 | 1018 |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Olmo 7b Instruct: —
| Benchmark | Llama 13b | Olmo 7b Instruct |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Olmo 7b Instruct: —
| Benchmark | Llama 13b | Olmo 7b Instruct |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Olmo 7b Instruct leads
Llama 13b: 16.6 (#297), Olmo 7b Instruct: 24.0 (#291)
| Benchmark | Llama 13b | Olmo 7b Instruct |
|---|---|---|
| LMArena Non-English | 819 | 977 |
| LMArena Chinese | — | 1014 |
| LMArena Russian | — | 947 |
Instruction Following Olmo 7b Instruct leads
Llama 13b: 36.7 (#305), Olmo 7b Instruct: 49.0 (#301)
| Benchmark | Llama 13b | Olmo 7b Instruct |
|---|---|---|
| LMArena Instruction Following | 781 | 978 |
Writing & Preference Olmo 7b Instruct leads
Llama 13b: 13.8 (#312), Olmo 7b Instruct: 25.8 (#303)
| Benchmark | Llama 13b | Olmo 7b Instruct |
|---|---|---|
| LMArena Text | 834 | 1032 |
| LMArena Creative Writing | 794 | 990 |
| LMArena Multi-Turn | 753 | 1007 |
Frequently asked questions
Is Llama 13b better than Olmo 7b Instruct?
Olmo 7b Instruct is the stronger model overall, scoring 30.3 to 24.4 on the Noometry Index.
Is Llama 13b or Olmo 7b Instruct better for coding?
Olmo 7b Instruct scores higher on coding benchmarks: 29.6 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Olmo 7b Instruct share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Olmo 7b Instruct has 10.