Up to four models
Claude Sonnet 5.5 vs Kimi K3.1 Pro
On the index (GPT-4 = 100), Claude Sonnet 5.5 scores 187 and Kimi K3.1 Pro 179. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Sonnet 5.5
187171–203
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 of 9
Kimi K3.1 Pro
179163–195
WeightsOpen
ReleasedOct 2026
Price in / out$0.24 / $8.4
Context1.05M
Core tests taken4 of 9
Claude Sonnet 5.5 leads Kimi K3.1 Pro by 8 points, ahead on 4 of 4 shared core tests, at 1.8× the price.
Test by testthird-party results
Claude Sonnet 5.5Kimi K3.1 Pro
Every result as a table
| Test | Claude Sonnet 5.5 | Kimi K3.1 Pro |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 95.6% | 94.2% |
| SimpleQA Verified | 46.5% | 62.2% |
| Maths | ||
| FrontierMath (tiers 1-3) | 88.8% | 78.3% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| ProofBench v1.1 | 100.0% | 91.0% |
| Chess puzzles | 59.0% | 45.0% |
| FrontierMath (tier 4) | 80.5% | 65.8% |
| Coding | ||
| Terminal-Bench 4.0 | 64.1% | 63.6% |
| IOI | 83.1% | 81.9% |
| Vibe Code Bench v1.1 | 92.4% | 84.9% |
| Agents | ||
| APEX-Agents | 75.5% | 65.5% |
| BioMysteryBench | 81.1% | 75.6% |
| SRE Bench | 30.1% | 27.1% |
| Terminal-Bench-Science | 47.1% | 31.4% |
| DTBench | 97.3% | 93.3% |
| Furniture assembly | 75.0% | 55.8% |
| LMCA | 68.3% | 57.6% |
| Mystery game puzzles | 65.0% | 42.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 10.4% | 11.7% |
| Legal Research Bench | 48.1% | 37.5% |
| Tax Agent Bench | 42.0% | 24.9% |
| Novel problems | ||
| MysteryMechanism | 49.1% | 26.1% |
Tests at least two of these models have taken. Bold rows are the core tests.