Model comparison
Mistral Small 3 vs Phi 3 Mini 128k Instruct
Mistral Small 3 is the stronger model overall, scoring 30.9 to 29.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 18 benchmarks with published results for both. Mistral Small 3 scores higher in 5 categories and Phi 3 Mini 128k Instruct in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Mini 128k Instruct leads 29.2 to 15.3.
- The biggest single-benchmark swing is BigCodeBench Instruct: 45.3% for Mistral Small 3 and 29.6% for Phi 3 Mini 128k Instruct.
Side by side
| Mistral Small 3 | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 30.9 | 29.1 |
| Released | 2025-01-30 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Small 3: 36.0 (#203), Phi 3 Mini 128k Instruct: 28.3 (#307)
| Benchmark | Mistral Small 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| BigCodeBench Instruct | 45.3% | 29.6% |
| LMArena Coding | 1246 | 1040 |
| BigCodeBench Complete | 50.4% | 40.6% |
Reasoning Too close to call
Mistral Small 3: 18.2 (#269), Phi 3 Mini 128k Instruct: 18.7 (#254)
| Benchmark | Mistral Small 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1028 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.06 | — |
Math Phi 3 Mini 128k Instruct leads
Mistral Small 3: 15.3 (#290), Phi 3 Mini 128k Instruct: 29.2 (#220)
| Benchmark | Mistral Small 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1240 | 1089 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
Knowledge Phi 3 Mini 128k Instruct leads
Mistral Small 3: 25.0 (#258), Phi 3 Mini 128k Instruct: 26.3 (#251)
| Benchmark | Mistral Small 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1202 | 984 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
Multilingual Mistral Small 3 leads
Mistral Small 3: 37.5 (#231), Phi 3 Mini 128k Instruct: 25.4 (#280)
| Benchmark | Mistral Small 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1198 | 1000 |
| LMArena Chinese | 1204 | 1016 |
| LMArena French | 1202 | 1038 |
| LMArena German | 1211 | 1006 |
| LMArena Japanese | 1111 | 899 |
| LMArena Korean | 1188 | 856 |
| LMArena Russian | 1216 | 1004 |
| LMArena Spanish | — | 1058 |
Instruction Following Mistral Small 3 leads
Mistral Small 3: 63.9 (#224), Phi 3 Mini 128k Instruct: 52.1 (#289)
| Benchmark | Mistral Small 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1214 | 1023 |
Long Context Mistral Small 3 leads
Mistral Small 3: 37.8 (#206), Phi 3 Mini 128k Instruct: 30.3 (#284)
| Benchmark | Mistral Small 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1246 | 996 |
Writing & Preference Mistral Small 3 leads
Mistral Small 3: 32.4 (#275), Phi 3 Mini 128k Instruct: 27.3 (#296)
| Benchmark | Mistral Small 3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1234 | 1050 |
| LMArena Creative Writing | 1195 | 1024 |
| LMArena Multi-Turn | 1217 | 989 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Phi 3 Mini 128k Instruct?
Mistral Small 3 is the stronger model overall, scoring 30.9 to 29.1 on the Noometry Index.
Is Mistral Small 3 or Phi 3 Mini 128k Instruct better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.0 versus 28.3 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Phi 3 Mini 128k Instruct share?
18 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.