Model comparison
Mercury vs Phi-4
Mercury is the stronger model overall, scoring 37.6 to 31.2 on the Noometry Index.
Last verified . 8 shared benchmarks.
MicrosoftSummary
- They share 8 benchmarks with published results for both. Mercury scores higher in 5 categories and Phi-4 in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mercury leads 46.2 to 40.5.
- Phi-4 has downloadable open weights; the other is API-only.
Side by side
| Mercury | Phi-4 | |
|---|---|---|
| Provider | Inception | Microsoft |
| Noometry Index | 37.6 | 31.2 |
| Released | — | 2024-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.07 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 9 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mercury leads
Mercury: 38.7 (#170), Phi-4: 34.4 (#239)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| LMArena Coding | 1322 | 1231 |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
Agentic & Tool Use Not comparable
Mercury: —, Phi-4: 22.8 (#128)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Too close to call
Mercury: 17.5 (#293), Phi-4: 17.7 (#291)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1285 | 1220 |
| Kagi LLM Benchmark | 21.6% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |
Math Not comparable
Mercury: —, Phi-4: 20.8 (#285)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| LMArena Math | — | 1246 |
| MATH Level 5 | — | 64.9% |
Knowledge Not comparable
Mercury: —, Phi-4: 32.6 (#209)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| LMArena Expert | — | 1203 |
| MMLU | — | 84.8% |
Multilingual Mercury leads
Mercury: 41.6 (#206), Phi-4: 37.2 (#237)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| LMArena Non-English | 1260 | 1197 |
| LMArena Chinese | — | 1212 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Russian | — | 1209 |
| LMArena Spanish | — | 1234 |
Instruction Following Mercury leads
Mercury: 65.2 (#224), Phi-4: 60.4 (#251)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1239 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Mercury leads
Mercury: 38.4 (#198), Phi-4: 36.9 (#226)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1266 | 1217 |
Writing & Preference Mercury leads
Mercury: 46.2 (#221), Phi-4: 40.5 (#244)
| Benchmark | Mercury | Phi-4 |
|---|---|---|
| LMArena Text | 1282 | 1217 |
| LMArena Creative Writing | 1191 | 1182 |
| LMArena Multi-Turn | 1282 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Mercury better than Phi-4?
Mercury is the stronger model overall, scoring 37.6 to 31.2 on the Noometry Index.
Is Mercury or Phi-4 better for coding?
Mercury scores higher on coding benchmarks: 38.7 versus 34.4 in the Noometry coding category.
How many benchmarks do Mercury and Phi-4 share?
8 benchmarks have published results for both models. Mercury has 9 scored results on Noometry and Phi-4 has 37.