Model comparison
Ministral 8B vs Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 27.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 12 benchmarks with published results for both. Ministral 8B scores higher in 5 categories and Phi 3 Medium 4k Instruct in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Medium 4k Instruct leads 29.6 to 12.5.
Side by side
| Ministral 8B | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 27.8 | 32.4 |
| Released | 2024-10-01 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.10 | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Ministral 8B: 34.4 (#226), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1202 | 1130 |
Agentic & Tool Use Not comparable
Ministral 8B: 16.2 (#140), Phi 3 Medium 4k Instruct: —
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Phi 3 Medium 4k Instruct leads
Ministral 8B: 17.7 (#279), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1127 |
| DTBench | 45.7% | — |
Math Phi 3 Medium 4k Instruct leads
Ministral 8B: 23.7 (#262), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1188 | 1173 |
| MATH Level 5 | 14.9% | — |
Knowledge Phi 3 Medium 4k Instruct leads
Ministral 8B: 12.5 (#292), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1170 | 1108 |
| GPQA Diamond | 27.1% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multilingual Ministral 8B leads
Ministral 8B: 35.3 (#242), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1165 | 1094 |
| LMArena Chinese | 1193 | 1108 |
| LMArena Russian | 1195 | 1145 |
| LMArena French | — | 1109 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Spanish | — | 1095 |
Instruction Following Ministral 8B leads
Ministral 8B: 60.7 (#245), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1161 | 1114 |
Long Context Ministral 8B leads
Ministral 8B: 36.7 (#222), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1212 | 1120 |
Writing & Preference Ministral 8B leads
Ministral 8B: 39.8 (#241), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | Ministral 8B | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1191 | 1138 |
| LMArena Creative Writing | 1175 | 1106 |
| LMArena Multi-Turn | 1166 | 1088 |
Frequently asked questions
Is Ministral 8B better than Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 27.8 on the Noometry Index.
Is Ministral 8B or Phi 3 Medium 4k Instruct better for coding?
Ministral 8B scores higher on coding benchmarks: 34.4 versus 32.3 in the Noometry coding category.
How many benchmarks do Ministral 8B and Phi 3 Medium 4k Instruct share?
12 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.