Mercury 2 vs MiniMax M1
MiniMax M1 leads Mercury 2 on the Artificial Analysis Intelligence Index, 11.7 to 10.8, and Mercury 2 costs 2.9x less per output token ($0.75 vs $2.20 per million). Updated October 22, 2026; 20 benchmarks have a result for both.
Mercury 2 or MiniMax M1: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mercury 2 for output tokens 2.9x cheaper ($0.75 vs $2.20 per million) and work measured by AA Intelligence Index or LMArena Text: science, where it leads.
- Shared results
- 20
- Mercury 2 only
- 22
- MiniMax M1 only
- 9
- 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
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M1
MiniMax M1 leads, 11.7 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
No call
Only Mercury 2 has a Design Arena: websites result, 1035.
Directional only
Long documents
Listed context window
MiniMax M1
MiniMax M1 takes 1M tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2
Mercury 2 $0.0006, MiniMax M1 $0.0015 per turn.
List prices
At a glance
- Coding index
- Mercury 2 not benchmarked, MiniMax M1 not benchmarked.
- Widest category
- Coding, 4.8 points apart on average over 2 shared benchmarks.
- Widest single gap
- LMArena Text: Chinese: Mercury 2 1414 against MiniMax M1 1360, 9.0 points apart on a 0 to 100 scale.
- Output price
- Mercury 2 $0.75 against MiniMax M1 $2.20 per million output tokens, 2.9x apart.
- Context window
- Mercury 2 takes 128K tokens, MiniMax M1 1M.
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 | MiniMax M1 | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 3 | 0 | ||
| Knowledge | 2 | 1 | ||
| General | 8 | 3 | ||
| All shared boards | 15 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Mercury 2 | MiniMax M1 | Leader |
|---|---|---|---|
| LMArena WebDev | 1171 | Not measured | Only Mercury 2 measured |
| AA Coding Index | 31.1 | Not measured | Only Mercury 2 measured |
| SciCode | 37.7% | Not measured | Only Mercury 2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 26.5% | Not measured | Only Mercury 2 measured |
| WeirdML | 43.2% | Not measured | Only Mercury 2 measured |
| ALE-Bench | 785.6 | Not measured | Only Mercury 2 measured |
| LMArena Text: coding | 1390 | 1359 | Mercury 2 |
| LMArena Text: software and IT | 1385 | 1359 | 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 33 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mercury 2 | MiniMax M1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 11.7 | MiniMax M1 |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Mercury 2 | MiniMax M1 | Leader |
|---|---|---|---|
| AA Agentic Index | 1.6 | Not measured | Only Mercury 2 measured |
| τ²-Bench Telecom | 70.8% | Not measured | Only Mercury 2 measured |
| Neither model has a result on the other 40 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Mercury 2 | MiniMax M1 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 77.0% | Not measured | Only Mercury 2 measured |
| Humanity's Last Exam (Artificial Analysis run) | 17.1% | Not measured | Only Mercury 2 measured |
| LMArena Text: hard prompts | 1362 | 1339 | Mercury 2 |
| LMArena Text: expert | 1358 | 1317 | Mercury 2 |
| LMArena Text: hard prompts in English | 1374 | 1353 | Mercury 2 |
| Neither model has a result on the other 18 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Mercury 2 | MiniMax M1 | Leader |
|---|---|---|---|
| LMArena Text: math | Not measured | 1361 | Only MiniMax M1 measured |
| LMArena Text: mathematical work | Not measured | 1363 | Only MiniMax M1 measured |
| Neither model has a result on the other 12 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Mercury 2 | MiniMax M1 | Leader |
|---|---|---|---|
| LMArena Text: science | 1343 | 1354 | MiniMax M1 |
| LMArena Text: medicine and healthcare | 1363 | 1355 | Mercury 2 |
| LMArena Text: legal and government | Not measured | 1337 | Only MiniMax M1 measured |
| LMArena Text: business and finance | 1349 | 1319 | Mercury 2 |
| Neither model has a result on the other 16 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Mercury 2 | MiniMax M1 | Leader |
|---|---|---|---|
| Design Arena: websites | 1035 | Not measured | Only Mercury 2 measured |
| Design Arena: UI components | 996 | Not measured | Only Mercury 2 measured |
| Design Arena: game dev | 983 | Not measured | Only Mercury 2 measured |
| Design Arena: data viz | 1010 | Not measured | Only Mercury 2 measured |
| Design Arena: 3D | 982 | Not measured | Only Mercury 2 measured |
| Design Arena: all code categories | 1021 | Not measured | Only Mercury 2 measured |
| Design Arena: SVG | 997 | Not measured | Only Mercury 2 measured |
| Design Arena: ASCII art | 988 | 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 index83
| Benchmark | Mercury 2 | MiniMax M1 | Leader |
|---|---|---|---|
| IFBench | 69.8% | Not measured | Only Mercury 2 measured |
| Long context reasoning (AA-LCR) | 43.7% | Not measured | Only Mercury 2 measured |
| LMArena Text | 1354 | 1343 | Mercury 2 |
| LMArena Text: instruction following | 1328 | 1312 | Mercury 2 |
| LMArena Text: creative writing | 1286 | 1297 | MiniMax M1 |
| LMArena Text: English | 1378 | 1363 | Mercury 2 |
| LMArena Text: non-English | 1330 | 1319 | Mercury 2 |
| LMArena Text: Chinese | 1414 | 1360 | Mercury 2 |
| LMArena Text: German | Not measured | 1350 | Only MiniMax M1 measured |
| LMArena Text: Japanese | Not measured | 1217 | Only MiniMax M1 measured |
| LMArena Text: Korean | Not measured | 1266 | Only MiniMax M1 measured |
| LMArena Text: French | Not measured | 1370 | Only MiniMax M1 measured |
| LMArena Text: Spanish | Not measured | 1353 | Only MiniMax M1 measured |
| LMArena Text: Russian | 1304 | 1329 | MiniMax M1 |
| LMArena Text: Polish | Not measured | 1329 | Only MiniMax M1 measured |
| LMArena Text: multi-turn | 1357 | 1335 | Mercury 2 |
| LMArena Text: longer queries | 1329 | 1326 | Mercury 2 |
| LMArena Text: writing and language | 1300 | 1311 | MiniMax M1 |
| LMArena Text: entertainment and media | 1314 | 1303 | Mercury 2 |
| Neither model has a result on the other 29 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2 | MiniMax M1 | 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
Mercury 2 costs less
Agent loop
200K input + 10K output tokens
Mercury 2 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 | MiniMax M1 |
|---|---|---|
| Maker | Inception | MiniMax |
| Weights | No public weights listed | No public weights listed |
| Released | March 4, 2026 | June 17, 2025 |
| Context window | 128K | 1M |
| Input $/Mtok | $0.25 | $0.40 |
| Output $/Mtok | $0.75 | $2.20 |
| 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 MiniMax M1 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mercury 2 for output tokens 2.9x cheaper ($0.75 vs $2.20 per million) and work measured by AA Intelligence Index or LMArena Text: science, where it leads.
Which is cheaper, Mercury 2 or MiniMax M1?
Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens; MiniMax M1 costs $0.40 and $2.20. Cost per solved task is known for neither of them.
Which has the bigger context window, Mercury 2 or MiniMax M1?
MiniMax M1, with 1M tokens against 128K.
How many benchmarks is the Mercury 2 vs MiniMax M1 comparison based on?
20 benchmarks have a result for both models as of October 22, 2026. Mercury 2's coding index rests on 1 independent benchmark and MiniMax M1's on 0. Where only one model has a result, the page says so instead of naming a winner.