Model comparison
Phi 3 Mini 4k Instruct vs Wizardlm 13b
Wizardlm 13b is the stronger model overall, scoring 30.8 to 27.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
MicrosoftSummary
- They share 10 benchmarks with published results for both. Phi 3 Mini 4k Instruct scores higher in 0 categories and Wizardlm 13b in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Wizardlm 13b leads 53.7 to 48.0.
Side by side
| Phi 3 Mini 4k Instruct | Wizardlm 13b | |
|---|---|---|
| Provider | Microsoft | Microsoft |
| Noometry Index | 27.4 | 30.8 |
| Released | 2024-04-23 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Wizardlm 13b leads
Phi 3 Mini 4k Instruct: 26.1 (#319), Wizardlm 13b: 29.6 (#293)
| Benchmark | Phi 3 Mini 4k Instruct | Wizardlm 13b |
|---|---|---|
| LMArena Coding | 1093 | 1035 |
| LiveBench Coding | 15.5% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 54.2% | — |
Reasoning Wizardlm 13b leads
Phi 3 Mini 4k Instruct: 13.6 (#326), Wizardlm 13b: 18.5 (#265)
| Benchmark | Phi 3 Mini 4k Instruct | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | 1072 | 1018 |
| 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 Wizardlm 13b leads
Phi 3 Mini 4k Instruct: 24.5 (#258), Wizardlm 13b: 27.8 (#235)
| Benchmark | Phi 3 Mini 4k Instruct | Wizardlm 13b |
|---|---|---|
| LMArena Math | 1111 | 1017 |
| LiveBench Math | 15.7% | — |
Knowledge Not comparable
Phi 3 Mini 4k Instruct: 27.9 (#241), Wizardlm 13b: —
| Benchmark | Phi 3 Mini 4k Instruct | Wizardlm 13b |
|---|---|---|
| LMArena Expert | 1045 | — |
| ARC (AI2) Challenge | 84.9% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 88% | — |
| TriviaQA | 64% | — |
Multilingual Too close to call
Phi 3 Mini 4k Instruct: 26.5 (#275), Wizardlm 13b: 27.3 (#272)
| Benchmark | Phi 3 Mini 4k Instruct | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | 1021 | 1034 |
| LMArena Chinese | 1021 | 1023 |
| LMArena French | 1075 | — |
| LMArena German | 1044 | — |
| LMArena Japanese | 935 | — |
| LMArena Korean | 905 | — |
| LMArena Russian | 1022 | — |
| LMArena Spanish | 1084 | — |
Instruction Following Wizardlm 13b leads
Phi 3 Mini 4k Instruct: 48.0 (#298), Wizardlm 13b: 53.7 (#280)
| Benchmark | Phi 3 Mini 4k Instruct | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | 1053 | 1049 |
| LiveBench Instruction Following | 39.1% | — |
Long Context Too close to call
Phi 3 Mini 4k Instruct: 31.7 (#271), Wizardlm 13b: 32.0 (#268)
| Benchmark | Phi 3 Mini 4k Instruct | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | 1044 | 1054 |
Writing & Preference Wizardlm 13b leads
Phi 3 Mini 4k Instruct: 27.7 (#295), Wizardlm 13b: 30.7 (#282)
| Benchmark | Phi 3 Mini 4k Instruct | Wizardlm 13b |
|---|---|---|
| LMArena Text | 1073 | 1077 |
| LMArena Creative Writing | 1037 | 1090 |
| LMArena Multi-Turn | 1018 | 1047 |
| LiveBench Language | 9.2% | — |
Frequently asked questions
Is Phi 3 Mini 4k Instruct better than Wizardlm 13b?
Wizardlm 13b is the stronger model overall, scoring 30.8 to 27.4 on the Noometry Index.
Is Phi 3 Mini 4k Instruct or Wizardlm 13b better for coding?
Wizardlm 13b scores higher on coding benchmarks: 29.6 versus 26.1 in the Noometry coding category.
How many benchmarks do Phi 3 Mini 4k Instruct and Wizardlm 13b share?
10 benchmarks have published results for both models. Phi 3 Mini 4k Instruct has 35 scored results on Noometry and Wizardlm 13b has 10.