Model comparison
Laguna M.1 vs Llama 2-70B
Laguna M.1 is the stronger model overall, scoring 31.9 to 24.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Poolside
MetaSummary
- The widest gap is in math, where Laguna M.1 leads 20.3 to 7.5.
Side by side
| Laguna M.1 | Llama 2-70B | |
|---|---|---|
| Provider | Poolside | Meta |
| Noometry Index | 31.9 | 24.1 |
| Released | 2026-04-28 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 33K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 3 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Laguna M.1 leads
Laguna M.1: 36.4 (#195), Llama 2-70B: 30.8 (#281)
| Benchmark | Laguna M.1 | Llama 2-70B |
|---|---|---|
| LMArena WebDev | 1348 | — |
| LMArena Coding | — | 1079 |
Reasoning Laguna M.1 leads
Laguna M.1: 21.9 (#187), Llama 2-70B: 13.7 (#324)
| Benchmark | Laguna M.1 | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | — | 1073 |
| DTBench | — | 41.6% |
| Surface Evolver Bench | 15.6% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.59 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Laguna M.1 leads
Laguna M.1: 20.3 (#276), Llama 2-70B: 7.5 (#320)
| Benchmark | Laguna M.1 | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0% |
| ProofBench | 0% | — |
| LMArena Math | — | 1091 |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Not comparable
Laguna M.1: —, Llama 2-70B: 7.4 (#305)
| Benchmark | Laguna M.1 | Llama 2-70B |
|---|---|---|
| GPQA Diamond | — | 26.3% |
| LMArena Expert | — | 1039 |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multilingual Not comparable
Laguna M.1: —, Llama 2-70B: 27.9 (#269)
| Benchmark | Laguna M.1 | Llama 2-70B |
|---|---|---|
| LMArena Non-English | — | 1045 |
| LMArena Chinese | — | 994 |
| LMArena French | — | 1089 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1142 |
Instruction Following Not comparable
Laguna M.1: —, Llama 2-70B: 55.1 (#273)
| Benchmark | Laguna M.1 | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | — | 1071 |
Long Context Not comparable
Laguna M.1: —, Llama 2-70B: 32.2 (#265)
| Benchmark | Laguna M.1 | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | — | 1062 |
Writing & Preference Not comparable
Laguna M.1: —, Llama 2-70B: 32.5 (#274)
| Benchmark | Laguna M.1 | Llama 2-70B |
|---|---|---|
| LMArena Text | — | 1115 |
| LMArena Creative Writing | — | 1075 |
| LMArena Multi-Turn | — | 1088 |
Frequently asked questions
Is Laguna M.1 better than Llama 2-70B?
Laguna M.1 is the stronger model overall, scoring 31.9 to 24.1 on the Noometry Index.
Is Laguna M.1 or Llama 2-70B better for coding?
Laguna M.1 scores higher on coding benchmarks: 36.4 versus 30.8 in the Noometry coding category.
How many benchmarks do Laguna M.1 and Llama 2-70B share?
0 benchmarks have published results for both models. Laguna M.1 has 3 scored results on Noometry and Llama 2-70B has 35.