Model comparison
Llama 3.1 Tulu 3 8b vs Phi-2
Llama 3.1 Tulu 3 8b has enough public results to be ranked (#220); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Allen Institute for AI (Ai2)
MicrosoftSide by side
| Llama 3.1 Tulu 3 8b | Phi-2 | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Microsoft |
| Noometry Index | 35.1 | — |
| Released | — | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.1 Tulu 3 8b: 33.9 (#235), Phi-2: —
| Benchmark | Llama 3.1 Tulu 3 8b | Phi-2 |
|---|---|---|
| LMArena Coding | 1184 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
Llama 3.1 Tulu 3 8b: 21.8 (#188), Phi-2: —
| Benchmark | Llama 3.1 Tulu 3 8b | Phi-2 |
|---|---|---|
| LMArena Hard Prompts | 1174 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.62 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
Llama 3.1 Tulu 3 8b: 31.3 (#196), Phi-2: —
| Benchmark | Llama 3.1 Tulu 3 8b | Phi-2 |
|---|---|---|
| LMArena Math | 1195 | — |
Knowledge Not comparable
Llama 3.1 Tulu 3 8b: —, Phi-2: —
| Benchmark | Llama 3.1 Tulu 3 8b | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
Llama 3.1 Tulu 3 8b: 35.6 (#241), Phi-2: —
| Benchmark | Llama 3.1 Tulu 3 8b | Phi-2 |
|---|---|---|
| LMArena Non-English | 1169 | — |
| LMArena Chinese | 1175 | — |
| LMArena Russian | 1193 | — |
Instruction Following Not comparable
Llama 3.1 Tulu 3 8b: 61.6 (#241), Phi-2: —
| Benchmark | Llama 3.1 Tulu 3 8b | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1174 | — |
Long Context Not comparable
Llama 3.1 Tulu 3 8b: 35.8 (#234), Phi-2: —
| Benchmark | Llama 3.1 Tulu 3 8b | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1181 | — |
Writing & Preference Not comparable
Llama 3.1 Tulu 3 8b: 39.9 (#240), Phi-2: —
| Benchmark | Llama 3.1 Tulu 3 8b | Phi-2 |
|---|---|---|
| LMArena Text | 1193 | — |
| LMArena Creative Writing | 1182 | — |
| LMArena Multi-Turn | 1154 | — |
Frequently asked questions
Is Llama 3.1 Tulu 3 8b better than Phi-2?
Llama 3.1 Tulu 3 8b has enough public results to be ranked (#220); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Llama 3.1 Tulu 3 8b and Phi-2 share?
0 benchmarks have published results for both models. Llama 3.1 Tulu 3 8b has 11 scored results on Noometry and Phi-2 has 11.