Model comparison
Mistral Small 3.1 vs Phi 3 Medium 4k Instruct
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 31.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 17 benchmarks with published results for both. Mistral Small 3.1 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 math, where Phi 3 Medium 4k Instruct leads 33.4 to 14.7.
Side by side
| Mistral Small 3.1 | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.7 | 33.0 |
| Released | 2025-03-17 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 102K | — |
| Input $ / M tokens | $0.35 | — |
| Output $ / M tokens | $0.56 | — |
| Results tracked | 28 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Mistral Small 3.1: 38.3 (#179), Phi 3 Medium 4k Instruct: 32.9 (#268)
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1309 | 1130 |
Reasoning Phi 3 Medium 4k Instruct leads
Mistral Small 3.1: 19.7 (#254), Phi 3 Medium 4k Instruct: 21.7 (#214)
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1278 | 1127 |
| Chess Puzzles | 1% | — |
| Epoch Capabilities Index | 127.48 | — |
Math Phi 3 Medium 4k Instruct leads
Mistral Small 3.1: 14.7 (#301), Phi 3 Medium 4k Instruct: 33.4 (#202)
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1262 | 1173 |
| OTIS Mock AIME 2024-2025 | 3.9% | — |
| Omni-MATH | 24.8% | — |
Knowledge Phi 3 Medium 4k Instruct leads
Mistral Small 3.1: 22.6 (#271), Phi 3 Medium 4k Instruct: 30.2 (#229)
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1257 | 1108 |
| GPQA Diamond | 41.9% | — |
| MMLU-Pro | 61% | — |
| GPQA (HELM) | 39.2% | — |
Multimodal Not comparable
Mistral Small 3.1: 33.2 (#99), Phi 3 Medium 4k Instruct: —
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Vision | 1136 | — |
Multilingual Mistral Small 3.1 leads
Mistral Small 3.1: 41.2 (#209), Phi 3 Medium 4k Instruct: 30.6 (#263)
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1255 | 1094 |
| LMArena Chinese | 1253 | 1108 |
| LMArena French | 1273 | 1110 |
| LMArena German | 1266 | 1101 |
| LMArena Japanese | 1208 | 1042 |
| LMArena Korean | 1206 | 954 |
| LMArena Russian | 1263 | 1145 |
| LMArena Spanish | 1283 | 1095 |
Instruction Following Mistral Small 3.1 leads
Mistral Small 3.1: 63.6 (#230), Phi 3 Medium 4k Instruct: 57.6 (#268)
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1264 | 1113 |
| IFEval | 75% | — |
Long Context Mistral Small 3.1 leads
Mistral Small 3.1: 39.5 (#178), Phi 3 Medium 4k Instruct: 34.0 (#255)
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1299 | 1120 |
Writing & Preference Mistral Small 3.1 leads
Mistral Small 3.1: 37.0 (#259), Phi 3 Medium 4k Instruct: 34.1 (#272)
| Benchmark | Mistral Small 3.1 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1277 | 1138 |
| LMArena Creative Writing | 1253 | 1107 |
| LMArena Multi-Turn | 1270 | 1088 |
| EQ-Bench Creative Writing | 761 | — |
| WildBench | 78.8% | — |
Frequently asked questions
Is Mistral Small 3.1 better than Phi 3 Medium 4k Instruct?
Phi 3 Medium 4k Instruct is the stronger model overall, scoring 33.0 to 31.7 on the Noometry Index.
Is Mistral Small 3.1 or Phi 3 Medium 4k Instruct better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 32.9 in the Noometry coding category.
How many benchmarks do Mistral Small 3.1 and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. Mistral Small 3.1 has 28 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.