Model comparison
Mercury 2 vs Phi 3 Mini 128k Instruct
Mercury 2 is the stronger model overall, scoring 38.8 to 29.1 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 Mini 128k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury 2 leads 54.0 to 27.3.
- Phi 3 Mini 128k Instruct has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Phi 3 Mini 128k Instruct | |
|---|---|---|
| Provider | Inception | Microsoft |
| Noometry Index | 38.8 | 29.1 |
| Released | 2026-02-20 | 2024-04-23 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 50K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.75 | — |
| Results tracked | 17 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury 2 leads
Mercury 2: 33.2 (#250), Phi 3 Mini 128k Instruct: 28.3 (#307)
| Benchmark | Mercury 2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1391 | 1040 |
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 785.58 | — |
Reasoning Mercury 2 leads
Mercury 2: 23.0 (#170), Phi 3 Mini 128k Instruct: 18.7 (#254)
| Benchmark | Mercury 2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1362 | 1028 |
| CritPt | 0.8% | — |
Math Not comparable
Mercury 2: —, Phi 3 Mini 128k Instruct: 29.2 (#220)
| Benchmark | Mercury 2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | — | 1089 |
Knowledge Mercury 2 leads
Mercury 2: 35.6 (#170), Phi 3 Mini 128k Instruct: 26.3 (#251)
| Benchmark | Mercury 2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1358 | 984 |
| Vectara Hallucination Rate | 12.3% | — |
Multilingual Mercury 2 leads
Mercury 2: 46.8 (#153), Phi 3 Mini 128k Instruct: 25.4 (#280)
| Benchmark | Mercury 2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1331 | 1000 |
| LMArena Chinese | 1416 | 1016 |
| LMArena Russian | 1303 | 1004 |
| LMArena French | — | 1038 |
| LMArena German | — | 1006 |
| LMArena Japanese | — | 899 |
| LMArena Korean | — | 856 |
| LMArena Spanish | — | 1058 |
Instruction Following Mercury 2 leads
Mercury 2: 70.4 (#161), Phi 3 Mini 128k Instruct: 52.1 (#289)
| Benchmark | Mercury 2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1328 | 1023 |
Long Context Mercury 2 leads
Mercury 2: 40.4 (#149), Phi 3 Mini 128k Instruct: 30.3 (#284)
| Benchmark | Mercury 2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1329 | 996 |
Writing & Preference Mercury 2 leads
Mercury 2: 54.0 (#151), Phi 3 Mini 128k Instruct: 27.3 (#296)
| Benchmark | Mercury 2 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1355 | 1050 |
| LMArena Creative Writing | 1289 | 1024 |
| LMArena Multi-Turn | 1358 | 989 |
Frequently asked questions
Is Mercury 2 better than Phi 3 Mini 128k Instruct?
Mercury 2 is the stronger model overall, scoring 38.8 to 29.1 on the Noometry Index.
Is Mercury 2 or Phi 3 Mini 128k Instruct better for coding?
Mercury 2 scores higher on coding benchmarks: 33.2 versus 28.3 in the Noometry coding category.
How many benchmarks do Mercury 2 and Phi 3 Mini 128k Instruct share?
11 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.