Compare / DeepSeek-V4-Flash (0423) vs Kimi K2.5
DeepSeek-V4-Flash (0423) vs Kimi K2.5
Which is cheaper, which is more capable, and which does better at each kind of work, from 20 results on 3 sources that measured both models.
Of the 20 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). See also DeepSeek vs Moonshot AI, every model from both labs.
DeepSeek-V4-Flash (0423) or Kimi K2.5? The short answer
They score about the same, so pick DeepSeek-V4-Flash (0423): it costs 7.6 times less per token.
- DeepSeek-V4-Flash (0423) is cheaper: $0.15 against $1.14 per million tokens, 7.6 times less.
- They score about the same on the Artificial Analysis Intelligence Index (24.4 and 23.5).
- DeepSeek-V4-Flash (0423) is newer: released 24 Apr 2026, against 27 Jan 2026 for Kimi K2.5.
- On third-party benchmarks, on the results both models have: DeepSeek-V4-Flash (0423) does better for agents and tool use and reasoning and knowledge; Kimi K2.5 for writing.
Head to head
Every fact side by side
| DeepSeek-V4-Flash (0423) | Kimi K2.5 | |
|---|---|---|
| Price per million tokens | $0.050 in · $0.45 out | $0.57 in · $2.85 out |
| Blended (3 in : 1 out) | $0.15 | $1.14 |
| Cheapest host, blended | $0.10 (StreamLake, FP8) | $0.99 (AtlasCloud, INT4) |
| Intelligence Index | 24.4 | 23.5 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 1,048,576 tokens | 262,144 tokens |
| Released | 24 Apr 2026 (newer) | 27 Jan 2026 |
| 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.
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 | DeepSeek-V4-Flash (0423) | Kimi K2.5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 85 · 67 of 387 measured | 1,438high reasoning | 1,450thinking reasoning |
| Overall · Text factualityArena rating, higher is better 81 · 69 of 163 measured | 1,439 | 1,445thinking reasoning |
| Business, management and finance · TextArena rating, higher is better 91 · 86 of 380 measured | 1,439 | 1,440thinking reasoning |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 85 · 88 of 249 measured | 24.4high reasoning | 23.5 |
| GPQA Diamond% of questions, higher is better 52 · 60 of 232 measured | 89.4%max reasoning | 87.9% |
| Humanity's Last Exam% of questions, higher is better 67 · 78 of 250 measured | 34.8%max reasoning | 30.7% |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 60 · 38 of 230 measured | 54.6no reasoning | 62.4thinking reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 54 · 43 of 230 measured | 12.0%thinking reasoning | 10.0%thinking reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 55 · 126 of 230 measured | 0.37thinking reasoning | 0.34no reasoning |
Show all 20 results (11 more)
| Measure | DeepSeek-V4-Flash (0423) | Kimi K2.5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better 78 · 67 of 385 measured | 1,410high reasoning | 1,423thinking reasoning |
| Expert prompts · TextArena rating, higher is better 83 · 58 of 338 measured | 1,466high reasoning | 1,483thinking reasoning |
| Instruction following · TextArena rating, higher is better 79 · 69 of 387 measured | 1,433high reasoning | 1,439thinking reasoning |
| Writing, literature and language · TextArena rating, higher is better 78 · 70 of 386 measured | 1,422high reasoning | 1,428thinking reasoning |
| Artificial Analysis reported by Artificial Analysis · 7 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 46 · 67 of 131 measured | 61.8%max reasoning | 45.7% |
| τ-bench banking% of tasks, higher is better 34 · 62 of 121 measured | 30.9%max reasoning | 14.2% |
| Artificial Analysis Coding Indexindex score, higher is better 45 · 62 of 130 measured | 56.2max reasoning | 46.8 |
| IFBench% of instructions, higher is better 7 · 54 of 195 measured | 79.2%max reasoning | 70.2% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 89 · 65 of 241 measured | 74.3%max reasoning | 78.0% |
| Terminal-Bench Hard% of tasks, higher is better 37 · 49 of 190 measured | 38.6%high reasoning | 34.8% |
| τ²-bench telecom% of tasks, higher is better 16 · 12 of 193 measured | 95.6%high reasoning | 95.9% |
Compare them with other models
Quick answers
Is DeepSeek-V4-Flash (0423) better than Kimi K2.5?
They score about the same, so pick DeepSeek-V4-Flash (0423): it costs 7.6 times less per token.
Which is cheaper, DeepSeek-V4-Flash (0423) or Kimi K2.5?
DeepSeek-V4-Flash (0423) is cheaper: $0.15 against $1.14 per million tokens, 7.6 times less.
Which is better for agents and tool use, DeepSeek-V4-Flash (0423) or Kimi K2.5?
DeepSeek-V4-Flash (0423) ranks 59 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, DeepSeek-V4-Flash (0423) or Kimi K2.5?
DeepSeek-V4-Flash (0423) ranks 69 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, DeepSeek-V4-Flash (0423) or Kimi K2.5?
Kimi K2.5 ranks 47 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 63 for DeepSeek-V4-Flash (0423).
Which is better for sticking to the facts, DeepSeek-V4-Flash (0423) or Kimi K2.5?
DeepSeek-V4-Flash (0423) ranks 81 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, DeepSeek-V4-Flash (0423) or Kimi K2.5?
DeepSeek-V4-Flash (0423): 1,048,576 tokens, against 262,144 for Kimi K2.5.
Run DeepSeek-V4-Flash (0423) and Kimi K2.5 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.