Model comparison
Mercury 2 vs Phi 3 Medium 4k Instruct
Mercury 2 is the stronger model overall, scoring 39.1 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
MicrosoftSummary
- They share 11 benchmarks with published results for both. Mercury 2 scores higher in 7 categories and Phi 3 Medium 4k Instruct in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 53.8 to 34.1.
- Phi 3 Medium 4k Instruct has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Inception | Microsoft |
| Noometry Index | 39.1 | 33.0 |
| Released | 2026-02-20 | — |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 50K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.75 | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mercury 2: 33.5 (#255), Phi 3 Medium 4k Instruct: 32.9 (#268)
| Benchmark | Mercury 2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1391 | 1130 |
| LMArena WebDev | 1171 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| ALE-Bench | 785.58 | — |
Reasoning Mercury 2 leads
Mercury 2: 23.8 (#170), Phi 3 Medium 4k Instruct: 21.7 (#214)
| Benchmark | Mercury 2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1127 |
| CritPt | 0.8% | — |
Math Not comparable
Mercury 2: —, Phi 3 Medium 4k Instruct: 33.4 (#202)
| Benchmark | Mercury 2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | — | 1173 |
Knowledge Mercury 2 leads
Mercury 2: 36.2 (#172), Phi 3 Medium 4k Instruct: 30.2 (#229)
| Benchmark | Mercury 2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1358 | 1108 |
| Vectara Hallucination Rate | 12.3% | — |
Multilingual Mercury 2 leads
Mercury 2: 46.6 (#157), Phi 3 Medium 4k Instruct: 30.6 (#263)
| Benchmark | Mercury 2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1331 | 1094 |
| LMArena Chinese | 1417 | 1108 |
| LMArena Russian | 1304 | 1145 |
| LMArena French | — | 1110 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Spanish | — | 1095 |
Instruction Following Mercury 2 leads
Mercury 2: 70.2 (#165), Phi 3 Medium 4k Instruct: 57.6 (#268)
| Benchmark | Mercury 2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1329 | 1113 |
Long Context Mercury 2 leads
Mercury 2: 40.5 (#154), Phi 3 Medium 4k Instruct: 34.0 (#255)
| Benchmark | Mercury 2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1330 | 1120 |
Writing & Preference Mercury 2 leads
Mercury 2: 53.8 (#155), Phi 3 Medium 4k Instruct: 34.1 (#272)
| Benchmark | Mercury 2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1355 | 1138 |
| LMArena Creative Writing | 1289 | 1107 |
| LMArena Multi-Turn | 1358 | 1088 |
Frequently asked questions
Is Mercury 2 better than Phi 3 Medium 4k Instruct?
Mercury 2 is the stronger model overall, scoring 39.1 to 33.0 on the Noometry Index.
Is Mercury 2 or Phi 3 Medium 4k Instruct better for coding?
They score almost the same on coding (33.5 vs 32.9); test both on your own repository before choosing.
How many benchmarks do Mercury 2 and Phi 3 Medium 4k Instruct share?
11 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.