Model comparison
Mistral Nemo vs phi-3-medium 14B
phi-3-medium 14B is the stronger model overall, scoring 29.7 to 26.4 on the Noometry Index.
Last verified . 3 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 3 benchmarks with published results for both. Mistral Nemo scores higher in 1 category and phi-3-medium 14B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Nemo leads 12.3 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 10.8% for Mistral Nemo and 17.6% for phi-3-medium 14B.
Side by side
| Mistral Nemo | phi-3-medium 14B | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 26.4 | 29.7 |
| Released | 2024-07-01 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 10 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, phi-3-medium 14B: 36.8 (#201)
| Benchmark | Mistral Nemo | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 48.7% |
Agentic & Tool Use Not comparable
Mistral Nemo: 23.5 (#125), phi-3-medium 14B: —
| Benchmark | Mistral Nemo | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| BALROG | 17.6% | — |
Reasoning Not comparable
Mistral Nemo: 20.7 (#232), phi-3-medium 14B: —
| Benchmark | Mistral Nemo | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 118.68 | 121.23 |
| DTBench | 48.6% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| PIQA | 83.5% | — |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Mistral Nemo: 25.5 (#268), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Mistral Nemo | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 10.8% | 17.6% |
| GSM8K | 84.2% | — |
Knowledge Mistral Nemo leads
Mistral Nemo: 12.3 (#298), phi-3-medium 14B: 9.1 (#306)
| Benchmark | Mistral Nemo | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 29.9% | 27.6% |
| ARC (AI2) Challenge | — | 91.6% |
| BoolQ | 82.5% | — |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Writing & Preference Not comparable
Mistral Nemo: 28.5 (#296), phi-3-medium 14B: —
| Benchmark | Mistral Nemo | phi-3-medium 14B |
|---|---|---|
| EQ-Bench Creative Writing | 881 | — |
Frequently asked questions
Is Mistral Nemo better than phi-3-medium 14B?
phi-3-medium 14B is the stronger model overall, scoring 29.7 to 26.4 on the Noometry Index.
How many benchmarks do Mistral Nemo and phi-3-medium 14B share?
3 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and phi-3-medium 14B has 13.