Model comparison
Grok 3 vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.5 to 39.6 on the Noometry Index.
Last verified . 25 shared benchmarks.
Summary
- They share 25 benchmarks with published results for both. Grok 3 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 39.6 to 13.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for Grok 3 and 96.1% for Kimi K2.6.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Grok 3 | Kimi K2.6 | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 39.6 | 47.5 |
| Released | 2025-04-09 | 2026-04-20 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.95 |
| Output $ / M tokens | — | $4 |
| Results tracked | 40 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Grok 3: 41.5 (#113), Kimi K2.6: 50.5 (#41)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| WeirdML | 37.2% | 55.9% |
| LMArena Coding | 1432 | 1488 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Grok 3 leads
Grok 3: 30.2 (#69), Kimi K2.6: 21.8 (#128)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| BALROG | 29.5% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Grok 3: 13.8 (#322), Kimi K2.6: 39.6 (#51)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1470 |
| Epoch Capabilities Index | 138.34 | 151.03 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 5.5% | — |
| CritPt | — | 8% |
| Chess Puzzles | — | 26% |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 90.9% |
| LMCA | — | 37.3% |
Math Kimi K2.6 leads
Grok 3: 36.2 (#122), Kimi K2.6: 56.8 (#34)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 96.1% |
| LMArena Math | 1390 | 1475 |
| FrontierMath (Feb 2025 set) | 3.8% | 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% |
| ProofBench | — | 16% |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
Knowledge Kimi K2.6 leads
Grok 3: 46.0 (#76), Kimi K2.6: 53.9 (#48)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 75.8% | 90.8% |
| Vectara Hallucination Rate | 5.8% | 10.8% |
| LMArena Expert | 1420 | 1491 |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| GPQA (HELM) | 65% | — |
Multimodal Not comparable
Grok 3: —, Kimi K2.6: 31.8 (#95)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1282 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Grok 3: 52.5 (#81), Kimi K2.6: 55.1 (#35)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1411 | 1446 |
| LMArena Chinese | 1448 | 1521 |
| LMArena French | 1460 | 1471 |
| LMArena German | 1431 | 1449 |
| LMArena Japanese | 1389 | 1442 |
| LMArena Korean | 1374 | 1428 |
| LMArena Russian | 1416 | 1446 |
| LMArena Spanish | 1417 | 1463 |
Instruction Following Kimi K2.6 leads
Grok 3: 75.2 (#69), Kimi K2.6: 76.5 (#40)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1451 |
| IFEval | 88.4% | — |
Long Context Kimi K2.6 leads
Grok 3: 38.7 (#187), Kimi K2.6: 44.9 (#50)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1439 | 1468 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Kimi K2.6 leads
Grok 3: 56.0 (#136), Kimi K2.6: 68.7 (#25)
| Benchmark | Grok 3 | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1426 | 1455 |
| LMArena Creative Writing | 1414 | 1434 |
| EQ-Bench Creative Writing | 1186 | 1725 |
| LMArena Multi-Turn | 1424 | 1453 |
| Short-Story Creative Writing | 76.4% | — |
| WildBench | 84.9% | — |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Grok 3 better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.5 to 39.6 on the Noometry Index.
Is Grok 3 or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 41.5 in the Noometry coding category.
How many benchmarks do Grok 3 and Kimi K2.6 share?
25 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Kimi K2.6 has 51.