Claude Haiku 4.5
Anthropic
- Chat / text
Anthropic
0 shared benchmarks are still too close to call, so the win stays conditional. This compare uses all public sources, with provider-official evidence labeled separately.
Unknown
| Intelligence Index AA · index Text · Chat / text | 1562.8% exact aliasverified runtime Row details
| 21n/a exact aliasverified runtimeContext only Row details
| n/a |
| GPQA AA · % Text · Reasoning / math / science | 64.6%46% exact aliasverified runtime Row details
| 85.7%n/a exact aliasverified runtimeContext only Row details
| n/a |
| Humanity's Last Exam AA · % Text · Reasoning / math / science | 4.2%19.2% exact aliasverified runtime Row details
| 29.6%n/a exact aliasverified runtimeContext only Row details
| n/a |
| CritPt AA · % Text · Reasoning / math / science | 0%50.1% exact aliasverified runtime Row details
| 8.9%n/a exact aliasverified runtimeContext only Row details
| n/a |
| AA-Omniscience accuracy AA · % Text · Chat / text | 14.4%25.5% exact aliasverified runtime Row details
| 18.6%n/a exact aliasverified runtimeContext only Row details
| n/a |
| AA-Omniscience non-hallucination AA · % Text · Chat / text | 74.3%96% exact aliasverified runtime Row details
| 67%n/a exact aliasverified runtimeContext only Row details
| n/a |
| Long Context Reasoning AA · % Document · Long context | 49.7%48.8% exact aliasverified runtime Row details
| 70%n/a exact aliasverified runtimeContext only Row details
| n/a |