Model comparison
Kimi K2.6 vs Mistral Medium
Kimi K2.6 is the stronger model overall, scoring 47.7 to 36.3 on the Noometry Index.
Last verified . 29 shared benchmarks.
Mistral AISummary
- They share 29 benchmarks with published results for both. Kimi K2.6 scores higher in 8 categories and Mistral Medium in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.6 leads 54.0 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 96.1% for Kimi K2.6 and 32.2% for Mistral Medium.
- Kimi K2.6 is cheaper at $0.95 / $4 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
Side by side
| Kimi K2.6 | Mistral Medium | |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 47.7 | 36.3 |
| Released | 2026-04-20 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 262K |
| Input $ / M tokens | $0.95 | $1.50 |
| Output $ / M tokens | $4 | $7.50 |
| Results tracked | 51 | 36 |
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 Medium: 34.2 (#243)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| SciCode | 53.5% | 40.2% |
| WeirdML | 55.9% | 43.7% |
| LMArena Coding | 1488 | 1434 |
| ALE-Bench | 1,093 | 763.98 |
| SWE-bench Verified | 76.7% | — |
| FrontierCode | — | 8% |
| LMArena WebDev | 1509 | — |
Agentic & Tool Use Mistral Medium leads
Kimi K2.6: 21.9 (#137), Mistral Medium: 28.3 (#90)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| 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 Medium: 24.0 (#167)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| CritPt | 8% | 0% |
| LMArena Hard Prompts | 1470 | 1426 |
| DTBench | 90.9% | 75.5% |
| LMCA | 37.3% | 26.1% |
| Kagi LLM Benchmark | — | 50% |
| NYT Connections (extended) | 87.2% | — |
| Chess Puzzles | 26% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 18% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 151.05 | — |
Math Kimi K2.6 leads
Kimi K2.6: 57.0 (#41), Mistral Medium: 28.1 (#245)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 96.1% | 32.2% |
| ProofBench | 16% | 9% |
| LMArena Math | 1475 | 1408 |
| FrontierMath (Feb 2025 set) | 39% | 0.3% |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 25.6% | — |
| MathArena Final-Answer Competitions | 72.9% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Kimi K2.6 leads
Kimi K2.6: 54.0 (#54), Mistral Medium: 25.0 (#265)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 90.8% | 59.5% |
| Vectara Hallucination Rate | 10.8% | 22.7% |
| LMArena Expert | 1491 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 34.9% | — |
Multimodal Mistral Medium leads
Kimi K2.6: 31.6 (#103), Mistral Medium: 35.3 (#88)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1283 | 1172 |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |
Multilingual Kimi K2.6 leads
Kimi K2.6: 54.9 (#37), Mistral Medium: 52.1 (#91)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1446 | 1408 |
| LMArena Chinese | 1521 | 1447 |
| LMArena French | 1471 | 1459 |
| LMArena German | 1450 | 1432 |
| LMArena Japanese | 1443 | 1378 |
| LMArena Korean | 1427 | 1380 |
| LMArena Russian | 1446 | 1411 |
| LMArena Spanish | 1464 | 1433 |
Instruction Following Kimi K2.6 leads
Kimi K2.6: 76.3 (#43), Mistral Medium: 73.7 (#116)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1451 | 1398 |
Long Context Kimi K2.6 leads
Kimi K2.6: 44.9 (#52), Mistral Medium: 42.9 (#114)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1468 | 1406 |
Writing & Preference Kimi K2.6 leads
Kimi K2.6: 68.5 (#26), Mistral Medium: 60.0 (#103)
| Benchmark | Kimi K2.6 | Mistral Medium |
|---|---|---|
| LMArena Text | 1455 | 1424 |
| LMArena Creative Writing | 1434 | 1391 |
| LMArena Multi-Turn | 1453 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |
Frequently asked questions
Is Kimi K2.6 better than Mistral Medium?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 36.3 on the Noometry Index.
Which is cheaper, Kimi K2.6 or Mistral Medium?
Kimi K2.6 is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Kimi K2.6 or Mistral Medium better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2.6 and Mistral Medium share?
29 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Mistral Medium has 36.