Model comparison
Mercury vs Phi-4 Mini
Mercury is the stronger model overall, scoring 37.3 to 30.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in coding, where Mercury leads 38.1 to 27.6.
- Phi-4 Mini has downloadable open weights; the other is API-only.
Side by side
| Mercury | Phi-4 Mini | |
|---|---|---|
| Provider | Inception | Microsoft |
| Noometry Index | 37.3 | 30.4 |
| Released | — | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 9 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
Mercury: 38.1 (#164), Phi-4 Mini: 27.6 (#312)
| Benchmark | Mercury | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| LMArena Coding | 1323 | — |
Reasoning Phi-4 Mini leads
Mercury: 16.8 (#288), Phi-4 Mini: 21.7 (#190)
| Benchmark | Mercury | Phi-4 Mini |
|---|---|---|
| Kagi LLM Benchmark | 21.6% | — |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1284 | — |
Knowledge Not comparable
Mercury: —, Phi-4 Mini: 24.8 (#261)
| Benchmark | Mercury | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
Multilingual Not comparable
Mercury: 41.7 (#201), Phi-4 Mini: —
| Benchmark | Mercury | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1259 | — |
Instruction Following Not comparable
Mercury: 65.3 (#220), Phi-4 Mini: —
| Benchmark | Mercury | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1238 | — |
Long Context Not comparable
Mercury: 38.3 (#193), Phi-4 Mini: —
| Benchmark | Mercury | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1264 | — |
Writing & Preference Not comparable
Mercury: 46.2 (#216), Phi-4 Mini: —
| Benchmark | Mercury | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1282 | — |
| LMArena Creative Writing | 1186 | — |
| LMArena Multi-Turn | 1283 | — |
Frequently asked questions
Is Mercury better than Phi-4 Mini?
Mercury is the stronger model overall, scoring 37.3 to 30.4 on the Noometry Index.
Is Mercury or Phi-4 Mini better for coding?
Mercury scores higher on coding benchmarks: 38.1 versus 27.6 in the Noometry coding category.
How many benchmarks do Mercury and Phi-4 Mini share?
0 benchmarks have published results for both models. Mercury has 9 scored results on Noometry and Phi-4 Mini has 3.