Model comparison
Kimi K2.6 vs Mistral Large
Kimi K2.6 is the stronger model overall, scoring 47.7 to 31.9 on the Noometry Index.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Kimi K2.6 scores higher in 8 categories and Mistral Large in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 57.0 to 18.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 96.1% for Kimi K2.6 and 8.5% for Mistral Large.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $2 / $6 for Mistral Large.
- Kimi K2.6 accepts more context: 262K tokens versus 131K.
Side by side
| Kimi K2.6 | Mistral Large | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 47.7 | 31.9 |
| Released | 2026-04-20 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 16K |
| Input $ / M tokens | $0.95 | $2 |
| Output $ / M tokens | $4 | $6 |
| Results tracked | 51 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Kimi K2.6: 50.7 (#43), Mistral Large: 34.3 (#240)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| SciCode | 53.5% | 36.2% |
| LMArena Coding | 1488 | 1277 |
| ALE-Bench | 1,093 | 264.7 |
| SWE-bench Verified | 76.7% | — |
| LMArena WebDev | 1509 | — |
| WeirdML | 55.9% | — |
| BigCodeBench Instruct | — | 30% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |
Agentic & Tool Use Mistral Large leads
Kimi K2.6: 21.9 (#137), Mistral Large: 28.6 (#89)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| OSWorld 2.0 | 4.6% | — |
| ExploitBench | 18.4% | — |
| GBAEval | 0.9% | — |
| GDP.pdf | 12% | — |
| Vending-Bench 2 | 6,205 | — |
Reasoning Kimi K2.6 leads
Kimi K2.6: 40.5 (#55), Mistral Large: 15.8 (#310)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| CritPt | 8% | 0% |
| LMArena Hard Prompts | 1470 | 1257 |
| DTBench | 90.9% | 65.1% |
| LMCA | 37.3% | 16.7% |
| Epoch Capabilities Index | 151.05 | 128.52 |
| SimpleBench | — | 22.5% |
| NYT Connections (extended) | 87.2% | — |
| Chess Puzzles | 26% | — |
| EBR-Bench | 2.4% | — |
| LiveBench Reasoning | — | 43.5% |
| Mystery Game Puzzles | 18% | — |
| LiveBench Data Analysis | — | 50.1% |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |
Math Kimi K2.6 leads
Kimi K2.6: 57.0 (#41), Mistral Large: 18.2 (#291)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 96.1% | 8.5% |
| LMArena Math | 1475 | 1262 |
| FrontierMath (Feb 2025 set) | 39% | 0.3% |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 25.6% | — |
| MathArena Final-Answer Competitions | 72.9% | — |
| ProofBench | 16% | — |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Kimi K2.6 leads
Kimi K2.6: 54.0 (#54), Mistral Large: 30.1 (#230)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| GPQA Diamond | 90.8% | 51.3% |
| Vectara Hallucination Rate | 10.8% | 4.5% |
| LMArena Expert | 1491 | 1232 |
| SimpleQA Verified | 34.9% | — |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |
Multimodal Not comparable
Kimi K2.6: 31.6 (#103), Mistral Large: —
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |
Multilingual Kimi K2.6 leads
Kimi K2.6: 54.9 (#37), Mistral Large: 40.0 (#219)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| LMArena Non-English | 1446 | 1237 |
| LMArena Chinese | 1521 | 1240 |
| LMArena French | 1471 | 1325 |
| LMArena German | 1450 | 1254 |
| LMArena Japanese | 1443 | 1188 |
| LMArena Korean | 1427 | 1202 |
| LMArena Russian | 1446 | 1257 |
| LMArena Spanish | 1464 | 1268 |
Instruction Following Kimi K2.6 leads
Kimi K2.6: 76.3 (#43), Mistral Large: 67.9 (#191)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1451 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |
Long Context Kimi K2.6 leads
Kimi K2.6: 44.9 (#52), Mistral Large: 38.3 (#199)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1468 | 1261 |
Writing & Preference Kimi K2.6 leads
Kimi K2.6: 68.5 (#26), Mistral Large: 40.7 (#242)
| Benchmark | Kimi K2.6 | Mistral Large |
|---|---|---|
| LMArena Text | 1455 | 1266 |
| LMArena Creative Writing | 1434 | 1243 |
| EQ-Bench Creative Writing | 1725 | 985 |
| LMArena Multi-Turn | 1453 | 1260 |
| Short-Story Creative Writing | — | 69% |
| WildBench | — | 80.1% |
| EQ-Bench 4 | 1202 | — |
| LiveBench Language | — | 39.4% |
Frequently asked questions
Is Kimi K2.6 better than Mistral Large?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 31.9 on the Noometry Index.
Which is cheaper, Kimi K2.6 or Mistral Large?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Mistral Large lists at $2 and $6.
Is Kimi K2.6 or Mistral Large better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 34.3 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.6 does, with 262K tokens against 131K.
How many benchmarks do Kimi K2.6 and Mistral Large share?
28 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Mistral Large has 51.