Mercury 2 vs Step 3.7 Flash
Updated October 21, 2026. 18 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 output tokens cost 1.5x less, and where what matters is AA Coding Index or SciCode, where it leads.
- Shared results
- 18
- Mercury 2 only
- 24
- Step 3.7 Flash only
- 0
- 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
Step 3.7 Flash
Step 3.7 Flash leads, 19.5 against 10.8.
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
Step 3.7 Flash
Step 3.7 Flash leads, 1196 against 1036.
Same board, both measured
Long documents
Listed context window
Step 3.7 Flash
Step 3.7 Flash takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2
Mercury 2 $0.0006, Step 3.7 Flash $0.0008 per turn.
List prices
At a glance
- Coding index
- Mercury 2 not benchmarked, Step 3.7 Flash not benchmarked.
- Widest category
- Agentic work, 27.8 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Mercury 2 43.7% against Step 3.7 Flash 73.7%, 30.0 points apart on a 0 to 100 scale.
- Output price
- Mercury 2 $0.75 against Step 3.7 Flash $1.15 per million output tokens, 1.5x apart.
- Context window
- Mercury 2 takes 128K tokens, Step 3.7 Flash 262K.
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 | Step 3.7 Flash | Ties |
|---|---|---|---|---|
| Coding | 1 | 3 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| Web design | 0 | 8 | ||
| General | 1 | 1 | ||
| All shared boards | 2 | 16 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index13
| Benchmark | Mercury 2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| LMArena WebDev | 1171 | Not measured | Only Mercury 2 measured |
| AA Coding Index | 31.1 | 39.6 | Step 3.7 Flash |
| SciCode | 37.7% | 43.9% | Step 3.7 Flash |
| Terminal-Bench Hard (Artificial Analysis run) | 26.5% | 35.6% | Step 3.7 Flash |
| WeirdML | 43.2% | Not measured | Only Mercury 2 measured |
| ALE-Bench | 785.6 | 694.1 | Mercury 2 |
| LMArena Text: coding | 1390 | Not measured | Only Mercury 2 measured |
| LMArena Text: software and IT | 1385 | Not measured | Only Mercury 2 measured |
| 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 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mercury 2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 19.5 | Step 3.7 Flash |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mercury 2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| AA Agentic Index | 1.6 | Not measured | Only Mercury 2 measured |
| τ²-Bench Telecom | 70.8% | 98.5% | Step 3.7 Flash |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mercury 2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 77.0% | 80.9% | Step 3.7 Flash |
| Humanity's Last Exam (Artificial Analysis run) | 17.1% | 21.4% | Step 3.7 Flash |
| LMArena Text: hard prompts | 1362 | Not measured | Only Mercury 2 measured |
| LMArena Text: expert | 1358 | Not measured | Only Mercury 2 measured |
| LMArena Text: hard prompts in English | 1374 | Not measured | Only Mercury 2 measured |
| Neither model has a result on the other 16 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| Neither model has a result on 13 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Mercury 2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| LMArena Text: science | 1343 | Not measured | Only Mercury 2 measured |
| LMArena Text: medicine and healthcare | 1363 | Not measured | Only Mercury 2 measured |
| LMArena Text: business and finance | 1349 | Not measured | Only Mercury 2 measured |
| Neither model has a result on the other 14 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | Mercury 2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1036 | 1196 | Step 3.7 Flash |
| Design Arena: UI components | 998 | 1179 | Step 3.7 Flash |
| Design Arena: game dev | 985 | 1158 | Step 3.7 Flash |
| Design Arena: data viz | 1009 | 1172 | Step 3.7 Flash |
| Design Arena: 3D | 983 | 1129 | Step 3.7 Flash |
| Design Arena: all code categories | 1022 | 1182 | Step 3.7 Flash |
| Design Arena: SVG | 998 | 1085 | Step 3.7 Flash |
| Design Arena: ASCII art | 990 | 1152 | Step 3.7 Flash |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Mercury 2 | Step 3.7 Flash | Leader |
|---|---|---|---|
| IFBench | 69.8% | 67.3% | Mercury 2 |
| Long context reasoning (AA-LCR) | 43.7% | 73.7% | Step 3.7 Flash |
| LMArena Text | 1354 | Not measured | Only Mercury 2 measured |
| LMArena Text: instruction following | 1328 | Not measured | Only Mercury 2 measured |
| LMArena Text: creative writing | 1286 | Not measured | Only Mercury 2 measured |
| LMArena Text: English | 1378 | Not measured | Only Mercury 2 measured |
| LMArena Text: non-English | 1330 | Not measured | Only Mercury 2 measured |
| LMArena Text: Chinese | 1414 | Not measured | Only Mercury 2 measured |
| LMArena Text: Russian | 1304 | Not measured | Only Mercury 2 measured |
| LMArena Text: multi-turn | 1357 | Not measured | Only Mercury 2 measured |
| LMArena Text: longer queries | 1329 | Not measured | Only Mercury 2 measured |
| LMArena Text: writing and language | 1300 | Not measured | Only Mercury 2 measured |
| LMArena Text: entertainment and media | 1314 | Not measured | Only Mercury 2 measured |
| Neither model has a result on the other 33 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2 | Step 3.7 Flash | 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 costs less
Repository review
50K input + 3K output tokens
Step 3.7 Flash costs less
Agent loop
200K input + 10K output tokens
Step 3.7 Flash 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 | StepFun Step 3.7 Flash |
|---|---|---|
| Maker | Inception | StepFun |
| Weights | No public weights listed | Open weights |
| Released | March 4, 2026 | May 28, 2026 |
| Context window | 128K | 262K |
| Input $/Mtok | $0.25 | $0.20 |
| Output $/Mtok | $0.75 | $1.15 |
| 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 Step 3.7 Flash for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Mercury 2 has the edge where output tokens cost 1.5x less, and where what matters is AA Coding Index or SciCode, where it leads.
Which is cheaper, Mercury 2 or Step 3.7 Flash?
Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens; Step 3.7 Flash costs $0.20 and $1.15. Cost per solved task is known for neither of them.
Which has the bigger context window, Mercury 2 or Step 3.7 Flash?
Step 3.7 Flash, with 262K tokens against 128K.
How many benchmarks is the Mercury 2 vs Step 3.7 Flash comparison based on?
18 benchmarks have a result for both models as of October 21, 2026. Mercury 2's coding index rests on 1 independent benchmark and Step 3.7 Flash's on 0. Where only one model has a result, the page says so instead of naming a winner.