Model comparison
Llama 2-13B vs Molmo 2 8b
Molmo 2 8b is the stronger model overall, scoring 38.7 to 29.1 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Allen Institute for AI (Ai2)Summary
- They share 4 benchmarks with published results for both. Llama 2-13B scores higher in 0 categories and Molmo 2 8b in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Molmo 2 8b leads 49.5 to 30.0.
Side by side
| Llama 2-13B | Molmo 2 8b | |
|---|---|---|
| Provider | Meta | Allen Institute for AI (Ai2) |
| Noometry Index | 29.1 | 38.7 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 2-13B: 30.4 (#287), Molmo 2 8b: —
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Coding | 1062 | — |
Reasoning Molmo 2 8b leads
Llama 2-13B: 12.3 (#333), Molmo 2 8b: 24.5 (#146)
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1288 |
| 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 Not comparable
Llama 2-13B: 28.7 (#226), Molmo 2 8b: —
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Math | 1065 | — |
| GSM8K | 36.9% | — |
Knowledge Not comparable
Llama 2-13B: 27.5 (#244), Molmo 2 8b: —
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Expert | 1030 | — |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Molmo 2 8b: 29.5 (#106)
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Vision | — | 1081 |
| ScienceQA | 55.8% | — |
Multilingual Molmo 2 8b leads
Llama 2-13B: 26.7 (#274), Molmo 2 8b: 42.8 (#186)
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Non-English | 1024 | 1275 |
| LMArena Chinese | 1001 | — |
| LMArena French | 1043 | — |
| LMArena German | 1009 | — |
| LMArena Japanese | 894 | — |
| LMArena Korean | 953 | — |
| LMArena Russian | 1055 | — |
| LMArena Spanish | 1086 | — |
Instruction Following Molmo 2 8b leads
Llama 2-13B: 53.5 (#282), Molmo 2 8b: 67.2 (#196)
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Instruction Following | 1046 | 1270 |
Long Context Not comparable
Llama 2-13B: 32.3 (#264), Molmo 2 8b: —
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Longer Query | 1064 | — |
Writing & Preference Molmo 2 8b leads
Llama 2-13B: 30.0 (#284), Molmo 2 8b: 49.5 (#187)
| Benchmark | Llama 2-13B | Molmo 2 8b |
|---|---|---|
| LMArena Text | 1085 | 1288 |
| LMArena Creative Writing | 1047 | — |
| LMArena Multi-Turn | 1050 | — |
Frequently asked questions
Is Llama 2-13B better than Molmo 2 8b?
Molmo 2 8b is the stronger model overall, scoring 38.7 to 29.1 on the Noometry Index.
How many benchmarks do Llama 2-13B and Molmo 2 8b share?
4 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Molmo 2 8b has 5.