2 vs 0 benchmarks won
Anthropic Claude Sonnet 4.6 | Meta LLaMA 3.1 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Meta |
| Release date | Feb 17 2026 | Jul 23 2024 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 89.9% | — |
Software engineering SWE-Bench Verified | 79.6% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | LLaMA 3.1 shipped 574 days before Claude Sonnet 4.6 | |
Claude Sonnet 4.6 leads LLaMA 3.1 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). LLaMA 3.1 shipped 574 days before Claude Sonnet 4.6, so benchmark comparisons should account for the intervening progress.
LLaMA 3.1 is an open-source / open-weight model; Claude Sonnet 4.6 is proprietary.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.