Mistral Large 3 vs Kimi K2.5
Benchmark Performance
Available Benchmarks
| Benchmark | Mistral Large 3 | Kimi-K2.5 |
|---|---|---|
| LMArena Text Arenatext-2026-09-01-011508720696 · arena_rating · leader | 1,427.6299% of row best · rating · mistral-large-3; 95% CI [1424.57601414, 1430.66670291]; votes 65336; rank 85 | 1,445.75100% of row best · rating · kimi-k2.5-thinking; 95% CI [1442.41231565, 1449.09515875]; votes 70620; rank 50 |
| LMArena Vision Arenavision-2026-08-27-011508720696 · arena_rating · leader | 1,226.8497% of row best · rating · mistral-large-3; 95% CI [1216.90651393, 1236.78308197]; votes 4751; rank 66 | 1,266.74100% of row best · rating · kimi-k2.5-thinking; 95% CI [1260.83834046, 1272.64651923]; votes 26728; rank 36 |
| Overall ResultCounted from the protocol-matched rows above | 0 benchmark wins | 2 benchmark winsOverall lead |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Technical Differences
Side-by-Side Facts
| Field | Mistral Large 3 | Kimi-K2.5 |
|---|---|---|
| Developer | Mistral AI | Moonshot AI |
| Family | Mistral Large 3 | Kimi K2 5 |
| Model | Mistral Large 3 | Kimi-K2.5 |
| Version | Mistral Large 3 | Kimi-K2.5 |
| Lifecycle | active | active |
| Released | 2025-12-02 | 2026-01-27 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image, Document | Text, Image |
| Output modalities | Text | Text |
| Context window | 262K | 262K |
| Total parameters | 675B | 1T |
| Active parameters | 41B | 32B |
| License | Apache-2.0 | other |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Mistral AI (Standard), Openrouter (Standard) | Deepinfra (Standard), Hugging Face (Standard), Openrouter (Standard) |
| Capabilities | agents, chat, generation, structured_outputs, tools, vision | chat, generation, reasoning, tools |
17 comparable fields · 11 material differences · Pair passes the primary-source comparison gate
Mistral Large 3 Capabilities
Kimi K2.5 Capabilities
Internal Comparison Graph
Related Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Mistral Large 3Mistral AI | vs |  GPT-6 AstraOpenAI | cross-developer peersimage, text |
Claude Fable 5.1Anthropic | vs | Mistral Large 3Mistral AI | cross-developer peersimage, text |
 Gemini 3.1 ProGoogle DeepMind | vs | Mistral Large 3Mistral AI | cross-developer peerstext |
 DeepSeek-V4-ProDeepSeek | vs | Mistral Large 3Mistral AI | cross-developer peerstext |
Mistral Large 3Mistral AI | vs | Grok 4.6xAI | cross-developer peersimage, text |
Mistral Large 3Mistral AI | vs |  Qwen3.8-MaxQwen | cross-developer peersimage, text |
Mistral Large 3Mistral AI | vs | Kimi-K3Moonshot AI | cross-developer peersimage, text |
 MiniMax-M3MiniMax | vs | Mistral Large 3Mistral AI | cross-developer peersimage, text |
Mistral Large 3Mistral AI | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Mistral Large 3Mistral AI | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Mistral Large 3Mistral AI | cross-developer peersimage, text |
| vs | Mistral Large 3Mistral AI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
Mistral Large 3 vs Kimi K2.5 FAQs
Is Mistral Large 3 or Kimi K2.5 better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Mistral Large 3 and Kimi K2.5, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Mistral Large 3 or Kimi K2.5?+
Mistral Large 3 is $0.50 and Kimi K2.5 is $0.45 per million tokens, so Kimi K2.5 is cheaper on this metric. Mistral Large 3 is $1.50 and Kimi K2.5 is $2.25 per million tokens, so Mistral Large 3 is cheaper on this metric.
Which has a larger context window, Mistral Large 3 or Kimi K2.5?+
Neither model has a larger sourced context window in this comparison. Mistral Large 3 is 262K and Kimi K2.5 is 262K.
Which performs better in benchmarks, Mistral Large 3 or Kimi K2.5?+
There is no overall benchmark winner: An overall winner requires at least two decisive benchmarks from at least two original publishers.
Can Mistral Large 3 or Kimi K2.5 be self-hosted?+
Both models have the same recorded self-hosting status: supported. Mistral Large 3 is open weight; Kimi K2.5 is open weight.
Can Mistral Large 3 and Kimi K2.5 understand images?+
Mistral Large 3 is documented with image input; Kimi K2.5 is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Mistral Large 3 or Kimi K2.5?+
Neither has a larger sourced maximum output. Mistral Large 3 is — and Kimi K2.5 is —.
Do Mistral Large 3 and Kimi K2.5 support reasoning and tool use?+
Mistral Large 3: tool calling and image input. Kimi K2.5: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Mistral Large 3 or Kimi K2.5?+
Mistral Large 3 has 2 sourced provider routes; Kimi K2.5 has 3, so Kimi K2.5 has broader tracked availability.
Which offers better value, Mistral Large 3 or Kimi K2.5?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.