Mercury 2 vs Phi 4
Updated October 21, 2026. 26 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Mercury 2 has the edge where the context window is larger, 128K against 16K tokens.
- Shared results
- 26
- Mercury 2 only
- 16
- Phi 4 only
- 19
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Mercury 2
Mercury 2 leads, 10.8 against 5.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Mercury 2 has a AA Agentic Index result, 1.6.
Directional only
Web design
Design Arena: websites
No call
Only Mercury 2 has a Design Arena: websites result, 1036.
Directional only
Long documents
Listed context window
Mercury 2
Mercury 2 takes 128K tokens against 16K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Phi 4
Mercury 2 $0.0006, Phi 4 $0.0001 per turn.
List prices
At a glance
- Coding index
- Mercury 2 not benchmarked, Phi 4 not benchmarked.
- Widest category
- Agentic work, 70.8 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Mercury 2 70.8% against Phi 4 0.0%, 70.8 points apart on a 0 to 100 scale.
- Output price
- Mercury 2 $0.75 against Phi 4 $0.14 per million output tokens, 5.4x apart.
- Context window
- Mercury 2 takes 128K tokens, Phi 4 16K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Mercury 2 | Bars | Phi 4 | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 0 | ||
| Knowledge | 3 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 26 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| LMArena WebDev | 1171 | Not measured | Only Mercury 2 measured |
| AA Coding Index | 31.1 | Not measured | Only Mercury 2 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 23.1% | Only Phi 4 measured |
| SciCode | 37.7% | Not measured | Only Mercury 2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 26.5% | 3.8% | Mercury 2 |
| WeirdML | 43.2% | Not measured | Only Mercury 2 measured |
| ALE-Bench | 785.6 | Not measured | Only Mercury 2 measured |
| LMArena Text: coding | 1390 | 1231 | Mercury 2 |
| LMArena Text: software and IT | 1385 | 1228 | Mercury 2 |
| LMArena WebDev: React | 1160 | Not measured | Only Mercury 2 measured |
| LMArena WebDev: HTML | 1199 | Not measured | Only Mercury 2 measured |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 5.9 | Mercury 2 |
| Epoch Capabilities Index | Not measured | 130.5 | Only Phi 4 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| AA Agentic Index | 1.6 | Not measured | Only Mercury 2 measured |
| τ²-Bench Telecom | 70.8% | 0.0% | Mercury 2 |
| BALROG | Not measured | 11.6% | Only Phi 4 measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 77.0% | 57.5% | Mercury 2 |
| Humanity's Last Exam (Artificial Analysis run) | 17.1% | 3.8% | Mercury 2 |
| GPQA Diamond (Epoch AI run) | Not measured | 56.1% | Only Phi 4 measured |
| LMArena Text: hard prompts | 1362 | 1220 | Mercury 2 |
| LMArena Text: expert | 1358 | 1203 | Mercury 2 |
| LMArena Text: hard prompts in English | 1374 | 1230 | Mercury 2 |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 18.0 | Only Phi 4 measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 18.0% | Only Phi 4 measured |
| OTIS Mock AIME | Not measured | 13.8% | Only Phi 4 measured |
| MATH level 5 | Not measured | 64.9% | Only Phi 4 measured |
| LMArena Text: math | Not measured | 1246 | Only Phi 4 measured |
| LMArena Text: mathematical work | Not measured | 1254 | Only Phi 4 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 71.4% | Only Phi 4 measured |
| MMLU | Not measured | 84.8% | Only Phi 4 measured |
| LMArena Text: science | 1343 | 1206 | Mercury 2 |
| LMArena Text: medicine and healthcare | 1363 | 1202 | Mercury 2 |
| LMArena Text: legal and government | Not measured | 1241 | Only Phi 4 measured |
| LMArena Text: business and finance | 1349 | 1199 | Mercury 2 |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1036 | Not measured | Only Mercury 2 measured |
| Design Arena: UI components | 998 | Not measured | Only Mercury 2 measured |
| Design Arena: game dev | 985 | Not measured | Only Mercury 2 measured |
| Design Arena: data viz | 1009 | Not measured | Only Mercury 2 measured |
| Design Arena: 3D | 983 | Not measured | Only Mercury 2 measured |
| Design Arena: all code categories | 1022 | Not measured | Only Mercury 2 measured |
| Design Arena: SVG | 998 | Not measured | Only Mercury 2 measured |
| Design Arena: ASCII art | 990 | Not measured | Only Mercury 2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| IFBench | 69.8% | 23.5% | Mercury 2 |
| Long context reasoning (AA-LCR) | 43.7% | 0.0% | Mercury 2 |
| Creative writing (Lech Mazur) | Not measured | 62.6% | Only Phi 4 measured |
| LMArena Text | 1354 | 1217 | Mercury 2 |
| LMArena Text: instruction following | 1328 | 1201 | Mercury 2 |
| LMArena Text: creative writing | 1286 | 1181 | Mercury 2 |
| LMArena Text: English | 1378 | 1231 | Mercury 2 |
| LMArena Text: non-English | 1330 | 1197 | Mercury 2 |
| LMArena Text: Chinese | 1414 | 1212 | Mercury 2 |
| LMArena Text: German | Not measured | 1222 | Only Phi 4 measured |
| LMArena Text: Japanese | Not measured | 1158 | Only Phi 4 measured |
| LMArena Text: Korean | Not measured | 1151 | Only Phi 4 measured |
| LMArena Text: French | Not measured | 1224 | Only Phi 4 measured |
| LMArena Text: Spanish | Not measured | 1234 | Only Phi 4 measured |
| LMArena Text: Russian | 1304 | 1209 | Mercury 2 |
| LMArena Text: multi-turn | 1357 | 1206 | Mercury 2 |
| LMArena Text: longer queries | 1329 | 1217 | Mercury 2 |
| LMArena Text: writing and language | 1300 | 1198 | Mercury 2 |
| LMArena Text: entertainment and media | 1314 | 1162 | Mercury 2 |
| Neither model has a result on the other 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2 | Phi 4 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Phi 4 costs less
Repository review
50K input + 3K output tokens
Phi 4 costs less
Agent loop
200K input + 10K output tokens
Phi 4 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Inception Mercury 2 | Microsoft Phi 4 |
|---|---|---|
| Maker | Inception | Microsoft |
| Weights | No public weights listed | Open weights |
| Released | March 4, 2026 | January 10, 2025 |
| Context window | 128K | 16K |
| Input $/Mtok | $0.25 | $0.07 |
| Output $/Mtok | $0.75 | $0.14 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mercury 2 better than Phi 4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Mercury 2 has the edge where the context window is larger, 128K against 16K tokens.
Which is cheaper, Mercury 2 or Phi 4?
Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens; Phi 4 costs $0.07 and $0.14. Cost per solved task is known for neither of them.
Which has the bigger context window, Mercury 2 or Phi 4?
Mercury 2, with 128K tokens against 16K.
How many benchmarks is the Mercury 2 vs Phi 4 comparison based on?
26 benchmarks have a result for both models as of October 21, 2026. Mercury 2's coding index rests on 1 independent benchmark and Phi 4's on 0. Where only one model has a result, the page says so instead of naming a winner.