Compare / Kimi K2.5 vs Kimi K3
Kimi K2.5 vs Kimi K3
Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 4 sources that measured both models.
Of the 16 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee).
Kimi K2.5 or Kimi K3? The short answer
Pick Kimi K3 if quality matters most: it scores higher (Intelligence Index 43.6 against 23.5). Pick Kimi K2.5 if cost matters more: it costs 5.3 times less per token.
- Kimi K2.5 is cheaper: $1.14 against $6.00 per million tokens, 5.3 times less.
- Kimi K3 scores higher on the Artificial Analysis Intelligence Index: 43.6 against 23.5.
- Kimi K3 is newer: released 16 Jul 2026, against 27 Jan 2026 for Kimi K2.5.
- On third-party benchmarks, on the results both models have: Kimi K3 does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| Kimi K2.5 | Kimi K3 | |
|---|---|---|
| Price per million tokens | $0.57 in · $2.85 out | $3.00 in · $15.00 out |
| Blended (3 in : 1 out) | $1.14 | $6.00 |
| Cheapest host, blended | $0.99 (AtlasCloud, INT4) | $2.47 (Relace, FP4) |
| Cached input, per million | – | $0.30 cached input |
| Intelligence Index | 23.5 | 43.6 |
| Spring Prompt overall | – | 47 |
| Output speed, tokens a second | – | 41 |
| Context window | 262,144 tokens | 1,048,576 tokens |
| Released | 27 Jan 2026 | 16 Jul 2026 (newer) |
| Weights | Open | Open |
| Developer based in | China | 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 the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
From our research
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Kimi K2.5 | Kimi K3 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 67 · 13 of 387 measured | 1,450thinking reasoning | 1,488max reasoning |
| Overall · Text factualityArena rating, higher is better 69 · 20 of 163 measured | 1,445thinking reasoning | 1,472max reasoning |
| Business, management and finance · TextArena rating, higher is better 86 · 12 of 380 measured | 1,440thinking reasoning | 1,487max reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 88 · 19 of 249 measured | 23.5 | 43.6max reasoning |
| GPQA Diamond% of questions, higher is better 60 · 10 of 232 measured | 87.9% | 93.5%max reasoning |
| Humanity's Last Exam% of questions, higher is better 78 · 20 of 250 measured | 30.7% | 46.9%max reasoning |
| SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result | ||
| Correct answers% of questions, higher is better 50 · 23 of 76 measured | 34.3% | 50.6%max reasoning |
| Vending-Bench 2 reported by Vending-Bench 2 · 1 result | ||
| Money after a yearUS dollars, higher is better 42 · 24 of 58 measured | $1,198 | $5,165 |
Show all 16 results (8 more)
| Measure | Kimi K2.5 | Kimi K3 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better 67 · 20 of 385 measured | 1,423thinking reasoning | 1,460max reasoning |
| Expert prompts · TextArena rating, higher is better 58 · 10 of 338 measured | 1,483thinking reasoning | 1,533max reasoning |
| Instruction following · TextArena rating, higher is better 69 · 11 of 387 measured | 1,439thinking reasoning | 1,488max reasoning |
| Writing, literature and language · TextArena rating, higher is better 70 · 13 of 386 measured | 1,428thinking reasoning | 1,476max reasoning |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 67 · 12 of 131 measured | 45.7% | 85.0%max reasoning |
| τ-bench banking% of tasks, higher is better 62 · 10 of 121 measured | 14.2% | 46.0%max reasoning |
| Artificial Analysis Coding Indexindex score, higher is better 62 · 10 of 130 measured | 46.8 | 76.2max reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 65 · 1 of 241 measured | 78.0% | 88.7%max reasoning |
Quick answers
Is Kimi K2.5 better than Kimi K3?
Pick Kimi K3 if quality matters most: it scores higher (Intelligence Index 43.6 against 23.5). Pick Kimi K2.5 if cost matters more: it costs 5.3 times less per token.
Which is cheaper, Kimi K2.5 or Kimi K3?
Kimi K2.5 is cheaper: $1.14 against $6.00 per million tokens, 5.3 times less.
Which is better for agents and tool use, Kimi K2.5 or Kimi K3?
Kimi K3 ranks 40 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 95 for Kimi K2.5.
Which is better for reasoning and knowledge, Kimi K2.5 or Kimi K3?
Kimi K3 ranks 18 of 187 models on sale for hard questions across science, maths and general knowledge, against 77 for Kimi K2.5.
Which is better for writing, Kimi K2.5 or Kimi K3?
Kimi K3 ranks 12 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 47 for Kimi K2.5.
Which is better for sticking to the facts, Kimi K2.5 or Kimi K3?
Kimi K3 ranks 27 of 139 models on sale for summarising without inventing things, and factual answers, against 100 for Kimi K2.5.
Which has the bigger context window, Kimi K2.5 or Kimi K3?
Kimi K3: 1,048,576 tokens, against 262,144 for Kimi K2.5.
Run Kimi K2.5 and Kimi K3 on your own prompt.
Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.