Model comparison
Grok 4.6 vs Kimi K2.7 Code
Grok 4.6 is the stronger model overall, scoring 56.9 to 43.3 on the Noometry Index. Kimi K2.7 Code costs 1.8× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Grok 4.6 scores higher in 5 categories and Kimi K2.7 Code in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 39.0.
- The biggest single-benchmark swing is DeepSWE: 67.5% for Grok 4.6 and 30.5% for Kimi K2.7 Code.
- Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Grok 4.6 accepts more context: 500K tokens versus 262K.
- Kimi K2.7 Code has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | Kimi K2.7 Code | |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 56.9 | 43.3 |
| Released | 2026-08-12 | 2026-06-12 |
| Weights | Proprietary | Open |
| Context window | 500K | 262K |
| Max output | 500K | 262K |
| Input $ / M tokens | $2 | $0.95 |
| Output $ / M tokens | $6 | $4 |
| Results tracked | 49 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.5 (#16), Kimi K2.7 Code: 42.9 (#95)
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| DeepSWE | 67.5% | 30.5% |
| FrontierCode | 48% | 30.1% |
| LMArena WebDev | 1617 | 1473 |
| SciCode | 56.5% | 47.5% |
| WeirdML | 67.3% | 54.1% |
| ALE-Bench | 1,508 | 886.23 |
| CursorBench | 41.4% | — |
| FrontierSWE | 25.3% | — |
| LMArena Coding | 1465 | — |
Agentic & Tool Use Grok 4.6 leads
Grok 4.6: 39.4 (#27), Kimi K2.7 Code: 24.0 (#122)
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| APEX-Agents | 65.3% | 37.6% |
| Vending-Bench 2 | 9,047 | 5,083 |
| GBAEval | — | 0.9% |
| GDP.pdf | 17.2% | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), Kimi K2.7 Code: 39.0 (#61)
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| SimpleBench | 75.9% | 57.9% |
| CritPt | 19.7% | 10% |
| Chess Puzzles | 40% | 21% |
| Epoch Capabilities Index | 156.44 | 149.97 |
| ARC-AGI-2 | 67.1% | — |
| NYT Connections (extended) | 80% | — |
| ARC-AGI-1 | 87.5% | — |
| EBR-Bench | 30.5% | — |
| LMArena Hard Prompts | 1447 | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 97.3% | — |
| LMCA | 48.5% | — |
| Surface Evolver Bench | — | 48.8% |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), Kimi K2.7 Code: 52.9 (#48)
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 54% |
| FrontierMath Tier 4 | 31.7% | 12.2% |
| OTIS Mock AIME 2024-2025 | 99.2% | 95.6% |
| ProofBench | 51% | — |
| LMArena Math | 1423 | — |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), Kimi K2.7 Code: 53.5 (#57)
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| GPQA Diamond | 94% | 87.9% |
| SimpleQA Verified | 49.3% | 36.5% |
| LMArena Expert | 1467 | — |
Multimodal Not comparable
Grok 4.6: 43.6 (#23), Kimi K2.7 Code: —
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Not comparable
Grok 4.6: 53.0 (#74), Kimi K2.7 Code: —
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1480 | — |
| LMArena French | 1461 | — |
| LMArena German | 1431 | — |
| LMArena Japanese | 1376 | — |
| LMArena Korean | 1397 | — |
| LMArena Russian | 1422 | — |
| LMArena Spanish | 1404 | — |
Instruction Following Not comparable
Grok 4.6: 75.4 (#63), Kimi K2.7 Code: —
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| LMArena Instruction Following | 1431 | — |
Long Context Not comparable
Grok 4.6: 44.5 (#66), Kimi K2.7 Code: —
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| LMArena Longer Query | 1454 | — |
Writing & Preference Not comparable
Grok 4.6: 62.3 (#80), Kimi K2.7 Code: —
| Benchmark | Grok 4.6 | Kimi K2.7 Code |
|---|---|---|
| LMArena Text | 1428 | — |
| LMArena Creative Writing | 1428 | — |
| LMArena Multi-Turn | 1425 | — |
Frequently asked questions
Is Grok 4.6 better than Kimi K2.7 Code?
Grok 4.6 is the stronger model overall, scoring 56.9 to 43.3 on the Noometry Index. Kimi K2.7 Code costs 1.8× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, Grok 4.6 or Kimi K2.7 Code?
Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Grok 4.6 or Kimi K2.7 Code better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 42.9 in the Noometry coding category.
Which has the bigger context window?
Grok 4.6 does, with 500K tokens against 262K.
How many benchmarks do Grok 4.6 and Kimi K2.7 Code share?
17 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Kimi K2.7 Code has 19.