Up to four models
Grok 4.20 vs Kimi K2.5
On the index (GPT-4 = 100), Grok 4.20 scores 156 and Kimi K2.5 145. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Grok 4.20
156140–172
WeightsClosed
ReleasedFeb 2026
Price in / out$1.25 / $2.5
Context2M
Core tests taken4 of 9
Kimi K2.5
145130–161
WeightsOpen
ReleasedJan 2026
Price in / out$0.50 / $2.5
Context262K
Core tests taken5 of 9
Grok 4.20 leads Kimi K2.5 by 11 points, ahead on 2 of 3 shared core tests, at 1.6× the price.
Test by testthird-party results
Grok 4.20Kimi K2.5
Every result as a table
| Test | Grok 4.20 | Kimi K2.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 89.3% | 87.6% |
| GPQA Diamond (Vals AI) | 88.6% | 84.1% |
| MMLU Pro | 86.3% | 85.9% |
| MMMU Pro | 83.5% | 84.3% |
| CL-bench | 22.2% | 19.3% |
| SimpleQA Verified | 30.2% | 34.3% |
| Maths | ||
| AIME-style maths (OTIS mock) | 92.2% | 92.2% |
| Coding | ||
| Code Migration | 0.3% | 7.0% |
| LiveCodeBench | 84.3% | 83.9% |
| SWE-bench | 72.2% | 70.0% |
| Vibe Code Bench v1.1 | 4.1% | 17.5% |
| WeirdML | 52.3% | 45.6% |
| Professional work | ||
| Finance Agent (v2) | 28.5% | 35.8% |
| CorpFin v2 | 63.7% | 68.3% |
| EMB | 11.7% | 28.5% |
| Legal Research Bench | 13.9% | 15.9% |
| MedCode | 32.2% | 39.3% |
| MedScribe | 63.4% | 76.4% |
| MortgageTax | 45.4% | 66.5% |
| TaxEval v2 | 74.1% | 74.2% |
| Novel problems | ||
| ARC-AGI-2 | 65.1% | 11.8% |
| ARC-AGI-1 | 89.5% | 65.3% |
Tests at least two of these models have taken. Bold rows are the core tests.