Model comparison
Grok-3 mini vs Kimi K2.6
Kimi K2.6 is the stronger model overall, scoring 47.7 to 41.2 on the Noometry Index.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and Kimi K2.6 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.6 leads 40.5 to 13.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 96.1% for Kimi K2.6.
- Kimi K2.6 has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Kimi K2.6 | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 41.2 | 47.7 |
| 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 | 35 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.6 leads
Grok-3 mini: 40.8 (#131), Kimi K2.6: 50.7 (#43)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| WeirdML | 42.6% | 55.9% |
| LMArena Coding | 1379 | 1488 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 49.3% | — |
| LMArena WebDev | — | 1509 |
| SciCode | — | 53.5% |
| ALE-Bench | — | 1,093 |
Agentic & Tool Use Not comparable
Grok-3 mini: —, Kimi K2.6: 21.9 (#137)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| OSWorld 2.0 | — | 4.6% |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| Vending-Bench 2 | — | 6,205 |
Reasoning Kimi K2.6 leads
Grok-3 mini: 13.6 (#334), Kimi K2.6: 40.5 (#55)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1470 |
| Epoch Capabilities Index | 140.35 | 151.05 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 87.2% |
| ARC-AGI-1 | 16.5% | — |
| 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 mini: 42.1 (#85), Kimi K2.6: 57.0 (#41)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 96.1% |
| LMArena Math | 1386 | 1475 |
| FrontierMath (Feb 2025 set) | 5.9% | 39% |
| FrontierMath (Tiers 1-3) | — | 57.2% |
| FrontierMath Tier 4 | — | 25.6% |
| MathArena Final-Answer Competitions | — | 72.9% |
| ProofBench | — | 16% |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge Kimi K2.6 leads
Grok-3 mini: 46.4 (#81), Kimi K2.6: 54.0 (#54)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 76.3% | 90.8% |
| LMArena Expert | 1395 | 1491 |
| SimpleQA Verified | — | 34.9% |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| Vectara Hallucination Rate | — | 10.8% |
| GPQA (HELM) | 67.5% | — |
Multimodal Not comparable
Grok-3 mini: —, Kimi K2.6: 31.6 (#103)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| LMArena Vision | — | 1283 |
| Blueprint-Bench 2 | — | 3.9% |
| Furniture Assembly | — | 21.7% |
| LMArena Document | — | 1451 |
Multilingual Kimi K2.6 leads
Grok-3 mini: 48.1 (#145), Kimi K2.6: 54.9 (#37)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1352 | 1446 |
| LMArena Chinese | 1387 | 1521 |
| LMArena French | 1357 | 1471 |
| LMArena German | 1349 | 1450 |
| LMArena Japanese | 1342 | 1443 |
| LMArena Korean | 1335 | 1427 |
| LMArena Russian | 1353 | 1446 |
| LMArena Spanish | 1381 | 1464 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Kimi K2.6: 76.3 (#43)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1451 |
| IFEval | 95.1% | — |
Long Context Kimi K2.6 leads
Grok-3 mini: 41.0 (#147), Kimi K2.6: 44.9 (#52)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1372 | 1468 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Kimi K2.6 leads
Grok-3 mini: 52.5 (#169), Kimi K2.6: 68.5 (#26)
| Benchmark | Grok-3 mini | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1370 | 1455 |
| LMArena Creative Writing | 1342 | 1434 |
| LMArena Multi-Turn | 1355 | 1453 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | — | 1725 |
| WildBench | 65.1% | — |
| EQ-Bench 4 | — | 1202 |
Frequently asked questions
Is Grok-3 mini better than Kimi K2.6?
Kimi K2.6 is the stronger model overall, scoring 47.7 to 41.2 on the Noometry Index.
Is Grok-3 mini or Kimi K2.6 better for coding?
Kimi K2.6 scores higher on coding benchmarks: 50.7 versus 40.8 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Kimi K2.6 share?
22 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Kimi K2.6 has 51.