Kimi K2 Thinking vs Mistral Large
Updated October 21, 2026. 13 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
Kimi K2 Thinking has the edge where output tokens cost 2.4x less, and where the context window is larger, 262K against 128K tokens.
- Shared results
- 13
- Kimi K2 Thinking only
- 17
- Mistral Large only
- 31
- Like-for-like categories
- 5 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Kimi K2 Thinking
Kimi K2 Thinking leads, 22.0 against 5.8.
Same board, both measured
Reasoning
GPQA Diamond
Kimi K2 Thinking
Kimi K2 Thinking leads, 78.5% against 47.7%.
Same board, both measured
Math
AIME
Kimi K2 Thinking
Kimi K2 Thinking leads, 85.4% against 9.2%.
Same board, both measured
Knowledge
MMLU Pro
Kimi K2 Thinking
Kimi K2 Thinking leads, 81.1% against 69.7%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Kimi K2 Thinking has a Design Arena: websites result, 1113.
Directional only
Long documents
Listed context window
Kimi K2 Thinking
Kimi K2 Thinking takes 262K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Kimi K2 Thinking
Kimi K2 Thinking $0.0019, Mistral Large $0.0050 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Kimi K2 Thinking has the number, $0.61.
Directional only
At a glance
- Coding index
- Kimi K2 Thinking not benchmarked, Mistral Large not benchmarked.
- Widest category
- Coding, 46.8 points apart on average over 2 shared benchmarks.
- Widest single gap
- AIME: Kimi K2 Thinking 85.4% against Mistral Large 9.2%, 76.3 points apart on a 0 to 100 scale.
- Output price
- Kimi K2 Thinking $2.50 against Mistral Large $6.00 per million output tokens, 2.4x apart.
- Context window
- Kimi K2 Thinking takes 262K tokens, Mistral Large 128K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | Kimi K2 Thinking | Bars | Mistral Large | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 3 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| All shared boards | 13 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| SWE-bench Verified | 63.4% | Not measured | Only Kimi K2 Thinking measured |
| LiveCodeBench (Vals AI) | 63.1% | 37.1% | Kimi K2 Thinking |
| SWE-bench Verified (Vals AI) | 60.2% | Not measured | Only Kimi K2 Thinking measured |
| LiveCodeBench (Artificial Analysis run) | 85.3% | 17.8% | Kimi K2 Thinking |
| Terminal-Bench Hard (Artificial Analysis run) | 31.1% | Not measured | Only Kimi K2 Thinking measured |
| Terminal-Bench | 35.7% | Not measured | Only Kimi K2 Thinking measured |
| WeirdML | 42.8% | Not measured | Only Kimi K2 Thinking measured |
| ALE-Bench | 597.5 | Not measured | Only Kimi K2 Thinking measured |
| LMArena Text: coding | Not measured | 1275 | Only Mistral Large measured |
| LMArena Text: software and IT | Not measured | 1274 | Only Mistral Large measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.0 | 5.8 | Kimi K2 Thinking |
| Epoch Capabilities Index | 145.8 | 122.1 | Kimi K2 Thinking |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 93.0% | Not measured | Only Kimi K2 Thinking measured |
| METR time horizons | 59.2% | Not measured | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| GPQA Diamond | 78.5% | 47.7% | Kimi K2 Thinking |
| GPQA Diamond (Artificial Analysis run) | 83.8% | 35.1% | Kimi K2 Thinking |
| Humanity's Last Exam (Artificial Analysis run) | 23.8% | 3.5% | Kimi K2 Thinking |
| LMArena Text: hard prompts | Not measured | 1257 | Only Mistral Large measured |
| LMArena Text: expert | Not measured | 1208 | Only Mistral Large measured |
| LMArena Text: hard prompts in English | Not measured | 1268 | Only Mistral Large measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| AIME | 85.4% | 9.2% | Kimi K2 Thinking |
| MATH 500 (Vals AI) | Not measured | 74.4% | Only Mistral Large measured |
| MGSM (Vals AI) | 90.2% | 87.2% | Kimi K2 Thinking |
| AA Math Index | 94.7 | Not measured | Only Kimi K2 Thinking measured |
| AIME 2025 (Artificial Analysis run) | 94.7% | Not measured | Only Kimi K2 Thinking measured |
| LMArena Text: math | Not measured | 1261 | Only Mistral Large measured |
| LMArena Text: mathematical work | Not measured | 1257 | Only Mistral Large measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| MMLU Pro | 81.1% | 69.7% | Kimi K2 Thinking |
| LegalBench (Vals AI) | 80.2% | Not measured | Only Kimi K2 Thinking measured |
| CaseLaw (Vals AI) | 65.7% | Not measured | Only Kimi K2 Thinking measured |
| CorpFin (Vals AI) | 60.6% | Not measured | Only Kimi K2 Thinking measured |
| TaxEval (Vals AI) | 71.7% | 63.8% | Kimi K2 Thinking |
| MedQA (Vals AI) | 92.6% | 76.2% | Kimi K2 Thinking |
| MMLU Pro (Artificial Analysis run) | 84.8% | 51.5% | Kimi K2 Thinking |
| MMLU | Not measured | 68.8% | Only Mistral Large measured |
| LMArena Text: science | Not measured | 1260 | Only Mistral Large measured |
| LMArena Text: medicine and healthcare | Not measured | 1255 | Only Mistral Large measured |
| LMArena Text: legal and government | Not measured | 1275 | Only Mistral Large measured |
| LMArena Text: business and finance | Not measured | 1238 | Only Mistral Large measured |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| Design Arena: websites | 1113 | Not measured | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 8 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index21 boards, none shared
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| IFBench | 68.1% | Not measured | Only Kimi K2 Thinking measured |
| Long context reasoning (AA-LCR) | 72.0% | Not measured | Only Kimi K2 Thinking measured |
| DTBench | Not measured | 60.8% | Only Mistral Large measured |
| CL-bench | 17.6% | Not measured | Only Kimi K2 Thinking measured |
| LMArena Text | Not measured | 1265 | Only Mistral Large measured |
| LMArena Text: instruction following | Not measured | 1249 | Only Mistral Large measured |
| LMArena Text: creative writing | Not measured | 1242 | Only Mistral Large measured |
| LMArena Text: English | Not measured | 1284 | Only Mistral Large measured |
| LMArena Text: non-English | Not measured | 1235 | Only Mistral Large measured |
| LMArena Text: Chinese | Not measured | 1239 | Only Mistral Large measured |
| LMArena Text: German | Not measured | 1242 | Only Mistral Large measured |
| LMArena Text: Japanese | Not measured | 1170 | Only Mistral Large measured |
| LMArena Text: Korean | Not measured | 1202 | Only Mistral Large measured |
| LMArena Text: French | Not measured | 1325 | Only Mistral Large measured |
| LMArena Text: Spanish | Not measured | 1268 | Only Mistral Large measured |
| LMArena Text: Russian | Not measured | 1252 | Only Mistral Large measured |
| LMArena Text: Polish | Not measured | 1157 | Only Mistral Large measured |
| LMArena Text: multi-turn | Not measured | 1260 | Only Mistral Large measured |
| LMArena Text: longer queries | Not measured | 1261 | Only Mistral Large measured |
| LMArena Text: writing and language | Not measured | 1261 | Only Mistral Large measured |
| LMArena Text: entertainment and media | Not measured | 1230 | Only Mistral Large measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Kimi K2 Thinking | Mistral Large | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Kimi K2 Thinking costs less
Repository review
50K input + 3K output tokens
Kimi K2 Thinking costs less
Agent loop
200K input + 10K output tokens
Kimi K2 Thinking costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | MoonshotAI Kimi K2 Thinking | Mistral Large |
|---|---|---|
| Maker | Moonshot AI | Mistral AI |
| Weights | Open weights | No public weights listed |
| Released | November 6, 2025 | February 26, 2024 |
| Context window | 262K | 128K |
| Input $/Mtok | $0.60 | $2.00 |
| Output $/Mtok | $2.50 | $6.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | $0.61 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Kimi K2 Thinking better than Mistral Large for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Kimi K2 Thinking has the edge where output tokens cost 2.4x less, and where the context window is larger, 262K against 128K tokens.
Which is cheaper, Kimi K2 Thinking or Mistral Large?
Kimi K2 Thinking costs $0.60 per million input tokens and $2.50 per million output tokens; Mistral Large costs $2.00 and $6.00. Cost per solved task is known for Kimi K2 Thinking only.
Which has the bigger context window, Kimi K2 Thinking or Mistral Large?
Kimi K2 Thinking, with 262K tokens against 128K.
How many benchmarks is the Kimi K2 Thinking vs Mistral Large comparison based on?
13 benchmarks have a result for both models as of October 21, 2026. Kimi K2 Thinking's coding index rests on 1 independent benchmark and Mistral Large's on 0. Where only one model has a result, the page says so instead of naming a winner.