Mercury 2 vs Kimi K2 Thinking
Kimi K2 Thinking leads Mercury 2 on the Artificial Analysis Intelligence Index, 22.0 to 10.8, and Mercury 2 costs 3.3x less per output token ($0.75 vs $2.50 per million). Updated October 22, 2026; 10 benchmarks have a result for both.
Mercury 2 or Kimi K2 Thinking: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Mercury 2 for output tokens 3.3x cheaper ($0.75 vs $2.50 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 10
- Mercury 2 only
- 32
- Kimi K2 Thinking only
- 20
- Like-for-like categories
- 6 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
Kimi K2 Thinking
Kimi K2 Thinking leads, 22.0 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
Reasoning
GPQA Diamond
No call
Only Kimi K2 Thinking has a GPQA Diamond result, 78.5%.
Directional only
Math
AIME
No call
Only Kimi K2 Thinking has a AIME result, 85.4%.
Directional only
Knowledge
MMLU Pro
No call
Only Kimi K2 Thinking has a MMLU Pro result, 81.1%.
Directional only
Web design
Design Arena: websites
Kimi K2 Thinking
Kimi K2 Thinking leads, 1113 against 1036.
Same board, both measured
Long documents
Listed context window
Kimi K2 Thinking
Kimi K2 Thinking takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Mercury 2
Mercury 2 $0.0006, Kimi K2 Thinking $0.0019 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Kimi K2 Thinking has the number, $0.61.
Directional only
At a glance
- Coding index
- Mercury 2 not benchmarked, Kimi K2 Thinking not benchmarked.
- Widest category
- Agentic work, 22.2 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Mercury 2 43.7% against Kimi K2 Thinking 72.0%, 28.3 points apart on a 0 to 100 scale.
- Output price
- Mercury 2 $0.75 against Kimi K2 Thinking $2.50 per million output tokens, 3.3x apart.
- Context window
- Mercury 2 takes 128K tokens, Kimi K2 Thinking 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 | Kimi K2 Thinking | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| Web design | 0 | 1 | ||
| General | 1 | 1 | ||
| All shared boards | 3 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | Mercury 2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 63.4% | Only Kimi K2 Thinking measured |
| LMArena WebDev | 1171 | Not measured | Only Mercury 2 measured |
| AA Coding Index | 31.1 | Not measured | Only Mercury 2 measured |
| LiveCodeBench (Vals AI) | Not measured | 63.1% | Only Kimi K2 Thinking measured |
| SWE-bench Verified (Vals AI) | Not measured | 60.2% | Only Kimi K2 Thinking measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 85.3% | Only Kimi K2 Thinking measured |
| SciCode | 37.7% | Not measured | Only Mercury 2 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 26.5% | 31.1% | Kimi K2 Thinking |
| Terminal-Bench | Not measured | 35.7% | Only Kimi K2 Thinking measured |
| WeirdML | 43.2% | 42.8% | Mercury 2 |
| ALE-Bench | 785.6 | 597.5 | 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 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mercury 2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.8 | 22.0 | Kimi K2 Thinking |
| Epoch Capabilities Index | Not measured | 145.8 | Only Kimi K2 Thinking measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mercury 2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Agentic Index | 1.6 | Not measured | Only Mercury 2 measured |
| τ²-Bench Telecom | 70.8% | 93.0% | Kimi K2 Thinking |
| METR time horizons | Not measured | 59.2% | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Mercury 2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| GPQA Diamond | Not measured | 78.5% | Only Kimi K2 Thinking measured |
| GPQA Diamond (Artificial Analysis run) | 77.0% | 83.8% | Kimi K2 Thinking |
| Humanity's Last Exam (Artificial Analysis run) | 17.1% | 23.8% | Kimi K2 Thinking |
| 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 | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Mercury 2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AIME | Not measured | 85.4% | Only Kimi K2 Thinking measured |
| MGSM (Vals AI) | Not measured | 90.2% | Only Kimi K2 Thinking measured |
| AA Math Index | Not measured | 94.7 | Only Kimi K2 Thinking measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 94.7% | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | Mercury 2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 81.1% | Only Kimi K2 Thinking measured |
| LegalBench (Vals AI) | Not measured | 80.2% | Only Kimi K2 Thinking measured |
| CaseLaw (Vals AI) | Not measured | 65.7% | Only Kimi K2 Thinking measured |
| CorpFin (Vals AI) | Not measured | 60.6% | Only Kimi K2 Thinking measured |
| TaxEval (Vals AI) | Not measured | 71.7% | Only Kimi K2 Thinking measured |
| MedQA (Vals AI) | Not measured | 92.6% | Only Kimi K2 Thinking measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 84.8% | Only Kimi K2 Thinking measured |
| 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 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Mercury 2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| Design Arena: websites | 1036 | 1113 | Kimi K2 Thinking |
| Design Arena: UI components | 996 | Not measured | Only Mercury 2 measured |
| Design Arena: game dev | 984 | Not measured | Only Mercury 2 measured |
| Design Arena: data viz | 1009 | 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 | 998 | 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 index11
| Benchmark | Mercury 2 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| IFBench | 69.8% | 68.1% | Mercury 2 |
| Long context reasoning (AA-LCR) | 43.7% | 72.0% | Kimi K2 Thinking |
| CL-bench | Not measured | 17.6% | Only Kimi K2 Thinking measured |
| 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 32 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Mercury 2 | Kimi K2 Thinking | 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 | MoonshotAI Kimi K2 Thinking |
|---|---|---|
| Maker | Inception | Moonshot AI |
| Weights | No public weights listed | Open weights |
| Released | March 4, 2026 | November 6, 2025 |
| Context window | 128K | 262K |
| Input $/Mtok | $0.25 | $0.60 |
| Output $/Mtok | $0.75 | $2.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | $0.61 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Mercury 2 better than Kimi K2 Thinking for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Mercury 2 for output tokens 3.3x cheaper ($0.75 vs $2.50 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Mercury 2 or Kimi K2 Thinking?
Mercury 2 costs $0.25 per million input tokens and $0.75 per million output tokens; Kimi K2 Thinking costs $0.60 and $2.50. Cost per solved task is known for Kimi K2 Thinking only.
Which has the bigger context window, Mercury 2 or Kimi K2 Thinking?
Kimi K2 Thinking, with 262K tokens against 128K.
How many benchmarks is the Mercury 2 vs Kimi K2 Thinking comparison based on?
10 benchmarks have a result for both models as of October 22, 2026. Mercury 2's coding index rests on 1 independent benchmark and Kimi K2 Thinking's on 1. Where only one model has a result, the page says so instead of naming a winner.