Compare / Qwen3 235B A22B vs Kimi K2.5
Qwen3 235B A22B vs Kimi K2.5
Which is cheaper, which is more capable, and which does better at each kind of work, from 15 results on 3 sources that measured both models.
Qwen3 235B A22B or Kimi K2.5? The short answer
- Qwen3 235B A22B is cheaper: $0.80 against $1.14 per million tokens, 30% less.
- Kimi K2.5 scores higher on the Artificial Analysis Intelligence Index: 23.5 against 9.5.
- On our business benchmarks, Qwen3 235B A22B ranks higher for sticking to the facts.
- On our business benchmarks, Kimi K2.5 ranks higher for reasoning and knowledge and writing.
At a glance
| Qwen3 235B A22B | Kimi K2.5 | |
|---|---|---|
| Price per million tokens | $0.46 in · $1.82 out | $0.57 in · $2.85 out |
| Blended (3 in : 1 out) | $0.80 | $1.14 |
| Cheapest host, blended | – | $0.90 (SiliconFlow, INT4) |
| Intelligence Index | 9.5 | 23.5 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 131,072 tokens | 262,144 tokens |
| 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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Qwen3 235B A22B | Kimi K2.5 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | not measured | 85 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 137 of 195 | 65 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 102 of 187 | 46 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 64 of 153 | 106 of 153 |
Every shared result
| Benchmark | Metric | Qwen3 235B A22B | Kimi K2.5 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,414 | 1,441 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,366 | 1,423 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,395 | 1,483 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,381 | 1,439 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,403 | 1,450 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,378 | 1,428 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 9.50 | 23.5 |
| Artificial Analysisreported | GPQA Diamond% of questions | 70.0% | 87.9% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 11.0% | 30.7% |
| Artificial Analysisreported | IFBench% of instructions | 38.7% | 70.2% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 0.0% | 78.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 6.1% | 34.8% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 27.2% | 95.9% |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 94.9% | 92.2% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 9.3% | 14.2% |
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 Qwen3 235B A22B better than Kimi K2.5?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Qwen3 235B A22B ranks higher for sticking to the facts; Kimi K2.5 ranks higher for reasoning and knowledge and writing.
Which is cheaper, Qwen3 235B A22B or Kimi K2.5?
Qwen3 235B A22B costs $0.80 per million tokens (three input to one output), against $1.14 for Kimi K2.5.
Run Qwen3 235B A22B and Kimi K2.5 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.