Model comparison
Phi-4 vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 31.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
MicrosoftSummary
- They share 12 benchmarks with published results for both. Phi-4 scores higher in 5 categories and Wizardlm 70b in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Wizardlm 70b leads 32.2 to 20.8.
Side by side
| Phi-4 | Wizardlm 70b | |
|---|---|---|
| Provider | Microsoft | Microsoft |
| Noometry Index | 31.2 | 33.0 |
| Released | 2024-12-11 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.07 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 37 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-4 leads
Phi-4: 34.4 (#239), Wizardlm 70b: 31.4 (#285)
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1231 | 1081 |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 30.7% | — |
| BigCodeBench Complete | 55.4% | — |
Agentic & Tool Use Not comparable
Phi-4: 22.8 (#128), Wizardlm 70b: —
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | — |
| BALROG | 11.6% | — |
Reasoning Wizardlm 70b leads
Phi-4: 17.7 (#291), Wizardlm 70b: 20.7 (#234)
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1079 |
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | 47.8% | — |
| LiveBench Data Analysis | 45.2% | — |
| Epoch Capabilities Index | 130.42 | — |
| LiveBench | 41.6% | — |
Math Wizardlm 70b leads
Phi-4: 20.8 (#285), Wizardlm 70b: 32.2 (#218)
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1246 | 1116 |
| OTIS Mock AIME 2024-2025 | 13.8% | — |
| LiveBench Math | 42% | — |
| MATH Level 5 | 64.9% | — |
Knowledge Not comparable
Phi-4: 32.6 (#209), Wizardlm 70b: —
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| Confabulations | 29.4% | — |
| Vectara Hallucination Rate | 3.7% | — |
| LMArena Expert | 1203 | — |
| MMLU | 84.8% | — |
Multilingual Phi-4 leads
Phi-4: 37.2 (#237), Wizardlm 70b: 29.6 (#265)
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1197 | 1078 |
| LMArena Chinese | 1212 | 1052 |
| LMArena German | 1222 | 1083 |
| LMArena Russian | 1209 | 1155 |
| LMArena French | 1224 | — |
| LMArena Japanese | 1158 | — |
| LMArena Korean | 1151 | — |
| LMArena Spanish | 1234 | — |
Instruction Following Phi-4 leads
Phi-4: 60.4 (#251), Wizardlm 70b: 56.3 (#273)
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1201 | 1093 |
| LiveBench Instruction Following | 58.4% | — |
Long Context Phi-4 leads
Phi-4: 36.9 (#226), Wizardlm 70b: 33.3 (#263)
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1217 | 1097 |
Writing & Preference Phi-4 leads
Phi-4: 40.5 (#244), Wizardlm 70b: 34.8 (#269)
| Benchmark | Phi-4 | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1217 | 1120 |
| LMArena Creative Writing | 1182 | 1149 |
| LMArena Multi-Turn | 1206 | 1108 |
| Short-Story Creative Writing | 62.6% | — |
| LiveBench Language | 25.6% | — |
Frequently asked questions
Is Phi-4 better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 31.2 on the Noometry Index.
Is Phi-4 or Wizardlm 70b better for coding?
Phi-4 scores higher on coding benchmarks: 34.4 versus 31.4 in the Noometry coding category.
How many benchmarks do Phi-4 and Wizardlm 70b share?
12 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Wizardlm 70b has 12.