Compare / Mercury 2 vs Kimi K2.6
Mercury 2 vs Kimi K2.6
Which is cheaper, which is more capable, and which does better at each kind of work, from 21 results on 3 sources that measured both models.
Mercury 2 or Kimi K2.6? The short answer
- Mercury 2 is cheaper: $0.38 against $1.71 per million tokens, 4.6 times less.
- Kimi K2.6 scores higher on the Artificial Analysis Intelligence Index: 27.0 against 13.8.
- On our business benchmarks, Kimi K2.6 ranks higher for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
At a glance
| Mercury 2 | Kimi K2.6 | |
|---|---|---|
| Price per million tokens | $0.25 in · $0.75 out | $0.95 in · $4.00 out |
| Blended (3 in : 1 out) | $0.38 | $1.71 |
| Cheapest host, blended | – | $0.96 (Inceptron, INT4) |
| Intelligence Index | 13.8 | 27.0 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 128,000 tokens | 262,144 tokens |
| Weights | Closed | Open |
| Developer based in | the US | China |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Mercury 2 | Kimi K2.6 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 107 of 161 | 63 of 161 |
| Professional workReal tasks from banking, consulting and law, business documents and freelance projects | not measured | 43 of 51 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 109 of 195 | 48 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 146 of 187 | 33 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 136 of 153 | 85 of 153 |
Every shared result
| Benchmark | Metric | Mercury 2 | Kimi K2.6 |
|---|---|---|---|
| Arena (formerly LMArena)reported | OverallArena rating | 1,368 | 1,456 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,340 | 1,455 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,292 | 1,433 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,348 | 1,503 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,327 | 1,456 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,343 | 1,461 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,307 | 1,441 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 31.1 | 61.8 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 13.8 | 27.0 |
| Artificial Analysisreported | GPQA Diamond% of questions | 77.0% | 91.1% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 17.1% | 37.5% |
| Artificial Analysisreported | IFBench% of instructions | 69.8% | 76.0% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 43.7% | 81.0% |
| Artificial Analysisreported | SciCode% of problems | 37.7% | 51.5% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 27.3% | 65.9% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 0.5% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 26.5% | 43.9% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 9.5% | 23.3% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 70.8% | 95.9% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 100.0% | 99.7% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 12.3% | 10.8% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is Mercury 2 better than Kimi K2.6?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Kimi K2.6 ranks higher for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Which is cheaper, Mercury 2 or Kimi K2.6?
Mercury 2 costs $0.38 per million tokens (three input to one output), against $1.71 for Kimi K2.6.
Run Mercury 2 and Kimi K2.6 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.