Model comparison
Llama2 70b Steerlm Chat vs Phi 3 Mini 4k Instruct
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 27.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
NVIDIA
MicrosoftSummary
- They share 9 benchmarks with published results for both. Llama2 70b Steerlm Chat scores higher in 6 categories and Phi 3 Mini 4k Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama2 70b Steerlm Chat leads 54.2 to 47.7.
Side by side
| Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 31.8 | 27.9 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 29.9 (#300), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1025 | 1093 |
| LiveBench Coding | — | 15.5% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 20.0 (#246), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1047 | 1072 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 31.3 (#226), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1072 | 1111 |
| LiveBench Math | — | 15.7% |
Knowledge Not comparable
Llama2 70b Steerlm Chat: —, Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 28.8 (#270), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1063 | 1021 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1085 |
Instruction Following Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 54.2 (#279), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1060 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Phi 3 Mini 4k Instruct leads
Llama2 70b Steerlm Chat: 30.4 (#288), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 998 | 1044 |
Writing & Preference Llama2 70b Steerlm Chat leads
Llama2 70b Steerlm Chat: 31.6 (#283), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Llama2 70b Steerlm Chat | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1098 | 1073 |
| LMArena Creative Writing | 1091 | 1037 |
| LMArena Multi-Turn | 1058 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Llama2 70b Steerlm Chat better than Phi 3 Mini 4k Instruct?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 27.9 on the Noometry Index.
Is Llama2 70b Steerlm Chat or Phi 3 Mini 4k Instruct better for coding?
Llama2 70b Steerlm Chat scores higher on coding benchmarks: 29.9 versus 26.6 in the Noometry coding category.
How many benchmarks do Llama2 70b Steerlm Chat and Phi 3 Mini 4k Instruct share?
9 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.