Model comparison
Mercury 2 vs Phi-3.5-mini
Mercury 2 has enough public results to be ranked (#167); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- Phi-3.5-mini has downloadable open weights; the other is API-only.
Side by side
| Mercury 2 | Phi-3.5-mini | |
|---|---|---|
| Provider | Inception | Microsoft |
| Noometry Index | 38.8 | 36.4 |
| Released | 2026-02-20 | 2024-08-16 |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 50K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.75 | — |
| Results tracked | 17 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Mercury 2: 33.2 (#250), Phi-3.5-mini: 34.0 (#231)
| Benchmark | Mercury 2 | Phi-3.5-mini |
|---|---|---|
| LMArena WebDev | 1170 | — |
| SciCode | 38.7% | — |
| WeirdML | 43.2% | — |
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1391 | — |
| BigCodeBench Complete | — | 38.5% |
| ALE-Bench | 785.58 | — |
Reasoning Not comparable
Mercury 2: 23.0 (#170), Phi-3.5-mini: —
| Benchmark | Mercury 2 | Phi-3.5-mini |
|---|---|---|
| CritPt | 0.8% | — |
| LMArena Hard Prompts | 1362 | — |
| PIQA | — | 81% |
Math Not comparable
Mercury 2: —, Phi-3.5-mini: —
| Benchmark | Mercury 2 | Phi-3.5-mini |
|---|---|---|
| GSM8K | — | 86.2% |
Knowledge Not comparable
Mercury 2: 35.6 (#170), Phi-3.5-mini: —
| Benchmark | Mercury 2 | Phi-3.5-mini |
|---|---|---|
| Vectara Hallucination Rate | 12.3% | — |
| LMArena Expert | 1358 | — |
| BoolQ | — | 78% |
Multilingual Not comparable
Mercury 2: 46.8 (#153), Phi-3.5-mini: —
| Benchmark | Mercury 2 | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1331 | — |
| LMArena Chinese | 1416 | — |
| LMArena Russian | 1303 | — |
Instruction Following Not comparable
Mercury 2: 70.4 (#161), Phi-3.5-mini: —
| Benchmark | Mercury 2 | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1328 | — |
Long Context Not comparable
Mercury 2: 40.4 (#149), Phi-3.5-mini: —
| Benchmark | Mercury 2 | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1329 | — |
Writing & Preference Not comparable
Mercury 2: 54.0 (#151), Phi-3.5-mini: —
| Benchmark | Mercury 2 | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1355 | — |
| LMArena Creative Writing | 1289 | — |
| LMArena Multi-Turn | 1358 | — |
Frequently asked questions
Is Mercury 2 better than Phi-3.5-mini?
Mercury 2 has enough public results to be ranked (#167); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Mercury 2 or Phi-3.5-mini better for coding?
They score almost the same on coding (33.2 vs 34.0); test both on your own repository before choosing.
How many benchmarks do Mercury 2 and Phi-3.5-mini share?
0 benchmarks have published results for both models. Mercury 2 has 17 scored results on Noometry and Phi-3.5-mini has 5.