Model comparison
Mercury 2.5 vs phi-3-medium 14B
Mercury 2.5 is the stronger model overall, scoring 33.5 to 29.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in math, where phi-3-medium 14B leads 27.3 to 23.3.
- phi-3-medium 14B has downloadable open weights; the other is API-only.
Side by side
| Mercury 2.5 | phi-3-medium 14B | |
|---|---|---|
| Provider | Inception | Microsoft |
| Noometry Index | 33.5 | 29.7 |
| Released | 2026-09-08 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 260K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 4 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2.5 leads
Mercury 2.5: 39.5 (#156), phi-3-medium 14B: 36.8 (#201)
| Benchmark | Mercury 2.5 | phi-3-medium 14B |
|---|---|---|
| SciCode | 38.5% | — |
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 301.65 | — |
Reasoning Not comparable
Mercury 2.5: 22.4 (#193), phi-3-medium 14B: —
| Benchmark | Mercury 2.5 | phi-3-medium 14B |
|---|---|---|
| CritPt | 0% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.23 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math phi-3-medium 14B leads
Mercury 2.5: 23.3 (#272), phi-3-medium 14B: 27.3 (#250)
| Benchmark | Mercury 2.5 | phi-3-medium 14B |
|---|---|---|
| ProofBench | 3% | — |
| MATH Level 5 | — | 17.6% |
Knowledge Not comparable
Mercury 2.5: —, phi-3-medium 14B: 9.1 (#306)
| Benchmark | Mercury 2.5 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Frequently asked questions
Is Mercury 2.5 better than phi-3-medium 14B?
Mercury 2.5 is the stronger model overall, scoring 33.5 to 29.7 on the Noometry Index.
Is Mercury 2.5 or phi-3-medium 14B better for coding?
Mercury 2.5 scores higher on coding benchmarks: 39.5 versus 36.8 in the Noometry coding category.
How many benchmarks do Mercury 2.5 and phi-3-medium 14B share?
0 benchmarks have published results for both models. Mercury 2.5 has 4 scored results on Noometry and phi-3-medium 14B has 13.