Mercury 2.5 vs Hy4 preview
Hy4 preview leads Mercury 2.5 on coding, 44.3 to 1.6 on the Vibe Coding Index, and Mercury 2.5 costs 16.7x less per output token ($0.15 vs $2.501 per million). Updated October 22, 2026; 16 benchmarks have a result for both.
Mercury 2.5 or Hy4 preview: which to pick
Pick Hy4 preview for coding: it scores 44.3 on the Vibe Coding Index against 1.6 for Mercury 2.5.
Pick Mercury 2.5 for output tokens 16.7x cheaper ($0.15 vs $2.501 per million).
- Shared results
- 16
- Mercury 2.5 only
- 6
- Hy4 preview only
- 8
- Like-for-like categories
- 5 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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
Hy4 preview
Hy4 preview scores 44.3 against 1.6.
2 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Mercury 2.5 has a AA Intelligence Index result, 12.3.
Directional only
General
Vals Index
No call
Only Hy4 preview has a Vals Index result, 53.2%.
Directional only
Long documents
Listed context window
Hy4 preview
Hy4 preview takes 1.05M tokens against 260K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2.5
Mercury 2.5 $0.0001, Hy4 preview $0.0021 per turn.
List prices
At a glance
- Coding index
- Mercury 2.5 1.6 from 2 benchmarks, Hy4 preview 44.3 from 3 benchmarks.
- Widest category
- Math, 72.0 points apart on average over 1 shared benchmark.
- Widest single gap
- Vibe Code Bench (Vals AI): Mercury 2.5 3.7% against Hy4 preview 77.5%, 73.8 points apart on a 0 to 100 scale.
- Output price
- Mercury 2.5 $0.15 against Hy4 preview $2.501 per million output tokens, 16.7x apart.
- Context window
- Mercury 2.5 takes 260K tokens, Hy4 preview 1.05M.
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 2.5 | Bars | Hy4 preview | Ties |
|---|---|---|---|---|
| Coding | 0 | 6 | ||
| Agentic work | 0 | 5 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 2 | ||
| General | 0 | 2 | ||
| All shared boards | 0 | 16 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index06
| Benchmark | Mercury 2.5 | Hy4 preview | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1631 | Only Hy4 preview measured |
| Terminal-Bench 4 (Vals AI) | 0.0% | 8.1% | Hy4 preview |
| Vibe Code Bench (Vals AI) | 3.7% | 77.5% | Hy4 preview |
| Code migration (Vals AI) | 4.5% | 47.4% | Hy4 preview |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Hy4 preview measured |
| IOI (Vals AI) | 2.4% | 59.3% | Hy4 preview |
| Terminal-Bench 2.1 (Vals AI) | 34.5% | 55.1% | Hy4 preview |
| SkillsBench (Vals AI) | 18.1% | Not measured | Only Mercury 2.5 measured |
| CyberBench (Vals AI) | 45.5% | 65.4% | Hy4 preview |
| SciCode | 38.5% | Not measured | Only Mercury 2.5 measured |
| ALE-Bench | 301.6 | Not measured | Only Mercury 2.5 measured |
| LMArena WebDev: React | Not measured | 1653 | Only Hy4 preview measured |
| LMArena WebDev: HTML | Not measured | 1620 | Only Hy4 preview measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Mercury 2.5 | Hy4 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.3 | Not measured | Only Mercury 2.5 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | Mercury 2.5 | Hy4 preview | Leader |
|---|---|---|---|
| SREBench (Vals AI) | Not measured | 2.3% | Only Hy4 preview measured |
| Finance Agent (Vals AI) | 18.9% | 55.1% | Hy4 preview |
| Tax Agent Bench (Vals AI) | 2.5% | 32.6% | Hy4 preview |
| Legal Research Bench (Vals AI) | 4.3% | 45.2% | Hy4 preview |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 8.8% | Only Hy4 preview measured |
| Excel Modeling Benchmark (Vals AI) | 8.8% | 58.1% | Hy4 preview |
| BioMysteryBench (Vals AI) | Not measured | 69.3% | Only Hy4 preview measured |
| Terminal-Bench-Science (Vals AI) | 0.0% | 1.4% | Hy4 preview |
| Neither model has a result on the other 33 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Mercury 2.5 | Hy4 preview | Leader |
|---|---|---|---|
| Humanity's Last Exam (Artificial Analysis run) | 11.8% | Not measured | Only Mercury 2.5 measured |
| Neither model has a result on the other 21 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mercury 2.5 | Hy4 preview | Leader |
|---|---|---|---|
| ProofBench | 3.0% | 75.0% | Hy4 preview |
| Neither model has a result on the other 12 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mercury 2.5 | Hy4 preview | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | 83.1% | 83.8% | Hy4 preview |
| MedCode (Vals AI) | 31.3% | 43.3% | Hy4 preview |
| Neither model has a result on the other 16 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2.5 | Hy4 preview | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mercury 2.5 | Hy4 preview | Leader |
|---|---|---|---|
| Vals Index | Not measured | 53.2% | Only Hy4 preview measured |
| Public Benefits Bench (Vals AI) | 45.3% | 68.6% | Hy4 preview |
| MedScribe (Vals AI) | 55.1% | 83.6% | Hy4 preview |
| Long context reasoning (AA-LCR) | 71.7% | Not measured | Only Mercury 2.5 measured |
| Neither model has a result on the other 42 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2.5 | Hy4 preview | 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
Mercury 2.5 costs less
Repository review
50K input + 3K output tokens
Mercury 2.5 costs less
Agent loop
200K input + 10K output tokens
Mercury 2.5 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 2.5 | Tencent Hy4 preview |
|---|---|---|
| Maker | Inception | Tencent |
| Weights | No public weights listed | Open weights |
| Released | September 8, 2026 | August 28, 2026 |
| Context window | 260K | 1.05M |
| Input $/Mtok | $0.04 | $0.834 |
| Output $/Mtok | $0.15 | $2.501 |
| Coding index | 1.6 | 44.3 |
| Independent measurements behind it | 2 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mercury 2.5 better than Hy4 preview for coding?
Pick Hy4 preview for coding: it scores 44.3 on the Vibe Coding Index against 1.6 for Mercury 2.5. Pick Mercury 2.5 for output tokens 16.7x cheaper ($0.15 vs $2.501 per million).
Which is cheaper, Mercury 2.5 or Hy4 preview?
Mercury 2.5 costs $0.04 per million input tokens and $0.15 per million output tokens; Hy4 preview costs $0.834 and $2.501. Cost per solved task is known for neither of them.
Which has the bigger context window, Mercury 2.5 or Hy4 preview?
Hy4 preview, with 1.05M tokens against 260K.
How many benchmarks is the Mercury 2.5 vs Hy4 preview comparison based on?
16 benchmarks have a result for both models as of October 22, 2026. Mercury 2.5's coding index rests on 2 independent benchmarks and Hy4 preview's on 3. Where only one model has a result, the page says so instead of naming a winner.