Model comparison
Mistral Large vs Phi-4 Mini
Mistral Large is the stronger model overall, scoring 31.9 to 30.9 on the Noometry Index. Phi-4 Mini costs 23× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 3 benchmarks with published results for both. Mistral Large scores higher in 2 categories and Phi-4 Mini in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Phi-4 Mini leads 22.4 to 15.8.
- The biggest single-benchmark swing is SciCode: 36.2% for Mistral Large and 10.8% for Phi-4 Mini.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $2 / $6 for Mistral Large.
- Mistral Large accepts more context: 131K tokens versus 128K.
Side by side
| Mistral Large | Phi-4 Mini | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 31.9 | 30.9 |
| Released | 2024-02-26 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 131K | 128K |
| Max output | 16K | 4K |
| Input $ / M tokens | $2 | $0.075 |
| Output $ / M tokens | $6 | $0.30 |
| Results tracked | 51 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Mistral Large: 34.3 (#240), Phi-4 Mini: 28.1 (#317)
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| SciCode | 36.2% | 10.8% |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| LMArena Coding | 1277 | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Phi-4 Mini: —
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Phi-4 Mini leads
Mistral Large: 15.8 (#310), Phi-4 Mini: 22.4 (#195)
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| CritPt | 0% | 0% |
| SimpleBench | 22.5% | — |
| LiveBench Reasoning | 43.5% | — |
| LMArena Hard Prompts | 1257 | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Not comparable
Mistral Large: 18.2 (#291), Phi-4 Mini: —
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | — |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| LMArena Math | 1262 | — |
| MATH Level 5 | 50.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Large leads
Mistral Large: 30.1 (#230), Phi-4 Mini: 25.3 (#262)
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | 4.5% | 23.5% |
| GPQA Diamond | 51.3% | — |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| GPQA (HELM) | 43.5% | — |
| LMArena Expert | 1232 | — |
| MMLU | 80% | — |
Multilingual Not comparable
Mistral Large: 40.0 (#219), Phi-4 Mini: —
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1237 | — |
| LMArena Chinese | 1240 | — |
| LMArena French | 1325 | — |
| LMArena German | 1254 | — |
| LMArena Japanese | 1188 | — |
| LMArena Korean | 1202 | — |
| LMArena Russian | 1257 | — |
| LMArena Spanish | 1268 | — |
Instruction Following Not comparable
Mistral Large: 67.9 (#191), Phi-4 Mini: —
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
| LMArena Instruction Following | 1249 | — |
Long Context Not comparable
Mistral Large: 38.3 (#199), Phi-4 Mini: —
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1261 | — |
Writing & Preference Not comparable
Mistral Large: 40.7 (#242), Phi-4 Mini: —
| Benchmark | Mistral Large | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1266 | — |
| LMArena Creative Writing | 1243 | — |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LMArena Multi-Turn | 1260 | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Phi-4 Mini?
Mistral Large is the stronger model overall, scoring 31.9 to 30.9 on the Noometry Index. Phi-4 Mini costs 23× less per token, which makes it the better buy when Mistral Large's lead doesn't matter for your workload.
Which is cheaper, Mistral Large or Phi-4 Mini?
Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Mistral Large lists at $2 and $6.
Is Mistral Large or Phi-4 Mini better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 28.1 in the Noometry coding category.
Which has the bigger context window?
Mistral Large does, with 131K tokens against 128K.
How many benchmarks do Mistral Large and Phi-4 Mini share?
3 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Phi-4 Mini has 3.