Anthropic: Claude Opus 4.8 wins on more metrics (5 of 7), but the right pick depends on what you optimize for — see the breakdown below.
| Metric | Anthropic: Claude Opus 4.8 | Tencent: Hy3 |
|---|---|---|
| Intelligence Index | 55.7✓ | 41.2 |
| Coding Index | 74.3✓ | 58.8 |
| GPQA Diamond | 92%✓ | 90% |
| Design Arena Elo | 1283✓ | 1198 |
| Speed (tokens/sec) | — | — |
| Latency | — | — |
| Input price /M | $5.00 | $0.140✓ |
| Output price /M | $25.00 | $0.580✓ |
| Context window | 1M✓ | 262K |
| Capabilities | ReasoningToolsJSONVision | ReasoningToolsJSON |