Model comparison
phi-3-medium 14B vs Pixtral Large
Pixtral Large is the stronger model overall, scoring 32.2 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
Microsoft
Mistral AISide by side
| phi-3-medium 14B | Pixtral Large | |
|---|---|---|
| Provider | Microsoft | Mistral AI |
| Noometry Index | 29.7 | 32.2 |
| Released | 2024-04-23 | 2024-11-01 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 13 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
phi-3-medium 14B: 36.8 (#201), Pixtral Large: —
| Benchmark | phi-3-medium 14B | Pixtral Large |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| BigCodeBench Complete | 48.7% | — |
Reasoning Not comparable
phi-3-medium 14B: —, Pixtral Large: 21.7 (#218)
| Benchmark | phi-3-medium 14B | Pixtral Large |
|---|---|---|
| EnigmaEval | — | 0.8% |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.23 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |
Math Not comparable
phi-3-medium 14B: 27.3 (#250), Pixtral Large: —
| Benchmark | phi-3-medium 14B | Pixtral Large |
|---|---|---|
| MATH Level 5 | 17.6% | — |
Knowledge Not comparable
phi-3-medium 14B: 9.1 (#306), Pixtral Large: —
| Benchmark | phi-3-medium 14B | Pixtral Large |
|---|---|---|
| GPQA Diamond | 27.6% | — |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |
Multimodal Not comparable
phi-3-medium 14B: —, Pixtral Large: 30.6 (#111)
| Benchmark | phi-3-medium 14B | Pixtral Large |
|---|---|---|
| LMArena Vision | — | 1089 |
Writing & Preference Not comparable
phi-3-medium 14B: —, Pixtral Large: 32.9 (#278)
| Benchmark | phi-3-medium 14B | Pixtral Large |
|---|---|---|
| EQ-Bench Creative Writing | — | 988 |
Frequently asked questions
Is phi-3-medium 14B better than Pixtral Large?
Pixtral Large is the stronger model overall, scoring 32.2 to 29.7 on the Noometry Index.
How many benchmarks do phi-3-medium 14B and Pixtral Large share?
0 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Pixtral Large has 3.