0 vs 1 benchmarks won
Anthropic Claude 3 Haiku | Meta Muse Spark | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Meta |
| Release date | Mar 4 2024 | Apr 8 2026 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 77.4% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 33.3% | 89.5%Best |
Multimodal MMMUTests the AI on understanding images and text together across many college subjects. Higher is better. | — | 80.4% |
| Timeline | ||
| Release gap | Claude 3 Haiku shipped 765 days before Muse Spark | |
Muse Spark leads Claude 3 Haiku on 1 of the 1 benchmark they both report (GPQA Diamond). Claude 3 Haiku shipped 765 days before Muse Spark, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On GPQA Diamond, Muse Spark leads at 89.5% vs Claude 3 Haiku at 33.3%.