Model comparison
Kimi K2 (Jul 2025) vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 1.7× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 1 category and Kimi K2.6 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 40.5 to 23.3.
- The biggest single-benchmark swing is WeirdML: 42.8% for Kimi K2 (Jul 2025) and 55.9% for Kimi K2.6.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
Side by side
| Kimi K2 (Jul 2025) | Kimi K2.6 | |
|---|---|---|
| Provider | Moonshot AI | Moonshot AI |
| Noometry Index | 41.2 | 47.7 |
| Released | 2025-07-12 | 2026-04-20 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 262K | 262K |
| Input $ / M tokens | $0.57 | $0.95 |
| Output $ / M tokens | $2.30 | $4 |
| Results tracked | 42 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Kimi K2 (Jul 2025): 42.4 (#102), Kimi K2.6: 50.7 (#43)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| WeirdML | 42.8% | 55.9% |
| LMArena Coding | 1399 | 1488 |
| ALE-Bench | 597.5 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| GSO | 4.9% | — |
Agentic & Tool Use Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 32.4 (#64), Kimi K2.6: 21.9 (#137)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| METR Time Horizons | 59.2% | — |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Kimi K2 (Jul 2025): 23.3 (#179), Kimi K2.6: 40.5 (#55)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1470 |
| Epoch Capabilities Index | 146.01 | 151.05 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| NYT Connections (extended) | — | 87.2% |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
| ForecastBench | 60.2 | — |
Math Kimi K2.6 leads
Kimi K2 (Jul 2025): 42.7 (#83), Kimi K2.6: 57.0 (#41)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| LMArena Math | 1397 | 1475 |
| FrontierMath (Feb 2025 set) | 21.4% | 39% |
| FrontierMath Tier 4 (v1) | 0% | 14.6% |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| OTIS Mock AIME 2024-2025 | — | 96.1% |
| ProofBench | — | 16% |
| Omni-MATH | 65.4% | — |
Knowledge Kimi K2.6 leads
Kimi K2 (Jul 2025): 37.3 (#157), Kimi K2.6: 54.0 (#54)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| Vectara Hallucination Rate | 17.9% | 10.8% |
| LMArena Expert | 1365 | 1491 |
| GPQA Diamond | — | 90.8% |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| GPQA (HELM) | 65.3% | — |
Multimodal Not comparable
Kimi K2 (Jul 2025): —, Kimi K2.6: 31.6 (#103)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Kimi K2 (Jul 2025): 49.6 (#130), Kimi K2.6: 54.9 (#37)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1372 | 1446 |
| LMArena Chinese | 1415 | 1521 |
| LMArena French | 1379 | 1471 |
| LMArena German | 1387 | 1450 |
| LMArena Japanese | 1349 | 1443 |
| LMArena Korean | 1325 | 1427 |
| LMArena Russian | 1385 | 1446 |
| LMArena Spanish | 1386 | 1464 |
Instruction Following Kimi K2.6 leads
Kimi K2 (Jul 2025): 71.1 (#156), Kimi K2.6: 76.3 (#43)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1348 | 1451 |
| IFEval | 85% | — |
Long Context Kimi K2.6 leads
Kimi K2 (Jul 2025): 41.2 (#145), Kimi K2.6: 44.9 (#52)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1353 | 1468 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2.6 leads
Kimi K2 (Jul 2025): 62.3 (#78), Kimi K2.6: 68.5 (#26)
| Benchmark | Kimi K2 (Jul 2025) | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1380 | 1455 |
| LMArena Creative Writing | 1350 | 1434 |
| EQ-Bench Creative Writing | 1666 | 1725 |
| LMArena Multi-Turn | 1371 | 1453 |
| Short-Story Creative Writing | 85.6% | — |
| WildBench | 86.2% | — |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 1.7× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.
Which is cheaper, Kimi K2 (Jul 2025) or Kimi K2.6?
Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Kimi K2.6 lists at $0.95 and $4.
Is Kimi K2 (Jul 2025) or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Kimi K2 (Jul 2025) and Kimi K2.6 share?
24 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Kimi K2.6 has 51.