Up to four models
Claude Opus 5.5 vs Kimi K3.1 Pro
On the index (GPT-4 = 100), Claude Opus 5.5 scores 195 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 Opus 5.5
195178–211
WeightsClosed
ReleasedSep 2026
Price in / out$4.0 / $20
Context1M
Core tests taken6 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 Opus 5.5 leads Kimi K3.1 Pro by 16 points, ahead on 3 of 4 shared core tests, at 3.5× the price.
Test by testthird-party results
Claude Opus 5.5Kimi K3.1 Pro
Every result as a table
| Test | Claude Opus 5.5 | Kimi K3.1 Pro |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 94.1% | 94.2% |
| SimpleQA Verified | 72.2% | 62.2% |
| Maths | ||
| FrontierMath (tiers 1-3) | 91.2% | 78.3% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| ProofBench v1.1 | 100.0% | 91.0% |
| Chess puzzles | 67.0% | 45.0% |
| FrontierMath (tier 4) | 95.0% | 65.8% |
| Coding | ||
| Terminal-Bench 4.0 | 65.1% | 63.6% |
| IOI | 95.1% | 81.9% |
| Vibe Code Bench v1.1 | 90.3% | 84.9% |
| Agents | ||
| APEX-Agents | 73.5% | 65.5% |
| BioMysteryBench | 79.3% | 75.6% |
| SRE Bench | 33.6% | 27.1% |
| Terminal-Bench-Science | 47.1% | 31.4% |
| DTBench | 98.9% | 93.3% |
| Furniture assembly | 83.3% | 55.8% |
| LMCA | 68.2% | 57.6% |
| Mystery game puzzles | 71.0% | 42.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 9.2% | 11.7% |
| Legal Research Bench | 50.5% | 37.5% |
| Tax Agent Bench | 44.5% | 24.9% |
| Novel problems | ||
| MysteryMechanism | 49.5% | 26.1% |
Tests at least two of these models have taken. Bold rows are the core tests.