Model comparison
Mistral Large 4 vs Phi-4
Mistral Large 4 is the stronger model overall, scoring 43.1 to 31.2 on the Noometry Index. Phi-4 costs 12× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 12 benchmarks with published results for both. Mistral Large 4 scores higher in 8 categories and Phi-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 4 leads 60.4 to 40.5.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.68 / $2.09 for Mistral Large 4.
- Mistral Large 4 accepts more context: 1.05M tokens versus 128K.
- Phi-4 has downloadable open weights; the other is API-only.
Side by side
| Mistral Large 4 | Phi-4 | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 43.1 | 31.2 |
| Released | 2026-10-06 | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 128K |
| Max output | 262K | 4K |
| Input $ / M tokens | $0.68 | $0.07 |
| Output $ / M tokens | $2.09 | $0.14 |
| Results tracked | 15 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large 4 leads
Mistral Large 4: 48.6 (#57), Phi-4: 34.4 (#239)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| LMArena Coding | 1475 | 1231 |
| LMArena WebDev | 1541 | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
Agentic & Tool Use Not comparable
Mistral Large 4: —, Phi-4: 22.8 (#128)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Mistral Large 4 leads
Mistral Large 4: 22.5 (#192), Phi-4: 17.7 (#291)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1220 |
| NYT Connections (extended) | 27.4% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |
Math Mistral Large 4 leads
Mistral Large 4: 40.4 (#91), Phi-4: 20.8 (#285)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| LMArena Math | 1488 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge Mistral Large 4 leads
Mistral Large 4: 36.6 (#166), Phi-4: 32.6 (#209)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| LMArena Expert | 1447 | 1203 |
| GPQA Diamond | — | 56.1% |
| SimpleQA Verified | 20% | — |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |
Multilingual Mistral Large 4 leads
Mistral Large 4: 52.6 (#82), Phi-4: 37.2 (#237)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| LMArena Non-English | 1415 | 1197 |
| LMArena Chinese | 1491 | 1212 |
| LMArena Russian | 1414 | 1209 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Spanish | — | 1234 |
Instruction Following Mistral Large 4 leads
Mistral Large 4: 75.0 (#76), Phi-4: 60.4 (#251)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1424 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Mistral Large 4 leads
Mistral Large 4: 43.6 (#89), Phi-4: 36.9 (#226)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1429 | 1217 |
Writing & Preference Mistral Large 4 leads
Mistral Large 4: 60.4 (#97), Phi-4: 40.5 (#244)
| Benchmark | Mistral Large 4 | Phi-4 |
|---|---|---|
| LMArena Text | 1427 | 1217 |
| LMArena Creative Writing | 1361 | 1182 |
| LMArena Multi-Turn | 1424 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Mistral Large 4 better than Phi-4?
Mistral Large 4 is the stronger model overall, scoring 43.1 to 31.2 on the Noometry Index. Phi-4 costs 12× less per token, which makes it the better buy when Mistral Large 4's lead doesn't matter for your workload.
Which is cheaper, Mistral Large 4 or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Mistral Large 4 lists at $0.68 and $2.09.
Is Mistral Large 4 or Phi-4 better for coding?
Mistral Large 4 scores higher on coding benchmarks: 48.6 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Mistral Large 4 does, with 1.05M tokens against 128K.
How many benchmarks do Mistral Large 4 and Phi-4 share?
12 benchmarks have published results for both models. Mistral Large 4 has 15 scored results on Noometry and Phi-4 has 37.