Model comparison
Mistral Small vs Phi 3 Small 8k Instruct
Mistral Small is the stronger model overall, scoring 33.4 to 29.3 on the Noometry Index.
Last verified . 25 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 25 benchmarks with published results for both. Mistral Small scores higher in 7 categories and Phi 3 Small 8k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 31.1.
- The biggest single-benchmark swing is LiveBench Reasoning: 44.8% for Mistral Small and 15.9% for Phi 3 Small 8k Instruct.
Side by side
| Mistral Small | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 33.4 | 29.3 |
| Released | 2024-02-26 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 256K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 39 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Mistral Small: 34.0 (#247), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Coding | 36.2% | 20.3% |
| LMArena Coding | 1362 | 1101 |
| SciCode | 26.5% | — |
| BigCodeBench Instruct | 36.1% | — |
| BigCodeBench Complete | 46.6% | — |
| ALE-Bench | 497.62 | — |
Agentic & Tool Use Not comparable
Mistral Small: 28.1 (#93), Phi 3 Small 8k Instruct: —
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.1% | — |
Reasoning Mistral Small leads
Mistral Small: 19.8 (#250), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Reasoning | 44.8% | 15.9% |
| LMArena Hard Prompts | 1335 | 1100 |
| LiveBench Data Analysis | 53.7% | 30.3% |
| LiveBench | 44% | 24% |
| Kagi LLM Benchmark | 37.8% | — |
| CritPt | 0% | — |
| DTBench | 70.9% | — |
| LMCA | 20.6% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| HellaSwag | — | 77% |
| WinoGrande | — | 81.5% |
Math Phi 3 Small 8k Instruct leads
Mistral Small: 16.4 (#293), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Math | 39.9% | 17.6% |
| LMArena Math | 1341 | 1151 |
| OTIS Mock AIME 2024-2025 | 5.8% | — |
| MATH Level 5 | 46.8% | — |
Knowledge Mistral Small leads
Mistral Small: 31.0 (#222), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1291 | 1067 |
| MMLU | 68.7% | 75.7% |
| GPQA Diamond | 47.5% | — |
| Vectara Hallucination Rate | 5.1% | — |
| ARC (AI2) Challenge | — | 90.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multimodal Not comparable
Mistral Small: 33.5 (#96), Phi 3 Small 8k Instruct: —
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Vision | 1142 | — |
Multilingual Mistral Small leads
Mistral Small: 45.5 (#169), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1315 | 1058 |
| LMArena Chinese | 1340 | 1061 |
| LMArena French | 1337 | 1135 |
| LMArena German | 1340 | 1080 |
| LMArena Japanese | 1275 | 966 |
| LMArena Korean | 1259 | 894 |
| LMArena Russian | 1324 | 1111 |
| LMArena Spanish | 1346 | 1111 |
Instruction Following Mistral Small leads
Mistral Small: 66.4 (#209), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LiveBench Instruction Following | 63.7% | 47.2% |
| LMArena Instruction Following | 1310 | 1087 |
Long Context Mistral Small leads
Mistral Small: 40.4 (#156), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1327 | 1088 |
Writing & Preference Mistral Small leads
Mistral Small: 52.5 (#171), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | Mistral Small | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1338 | 1110 |
| LMArena Creative Writing | 1305 | 1083 |
| LMArena Multi-Turn | 1344 | 1068 |
| LiveBench Language | 30.5% | 12.9% |
Frequently asked questions
Is Mistral Small better than Phi 3 Small 8k Instruct?
Mistral Small is the stronger model overall, scoring 33.4 to 29.3 on the Noometry Index.
Is Mistral Small or Phi 3 Small 8k Instruct better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 27.9 in the Noometry coding category.
How many benchmarks do Mistral Small and Phi 3 Small 8k Instruct share?
25 benchmarks have published results for both models. Mistral Small has 39 scored results on Noometry and Phi 3 Small 8k Instruct has 32.