Claude 3.5 Sonnet
ECI#151
130Claude 3.5 Sonnet is a closed-weights model from Anthropic, released June 20, 2024. It has an ECI score of 130 and ranks 151st of 249 tracked models. At the time of its release, it ranked 1st of 67 tracked models. At $3/Mtok for input tokens and $15/Mtok for output tokens, it is more expensive per token than similarly-capable models.
Input price$3 / 1M tokens
Output price$15 / 1M tokens
ParametersUnknown
Training compute2.7e25 FLOP
Claude 3.5 Sonnet vs select alternatives
Reasoning
| Domain | Benchmark | Claude 3.5 Sonnet | |||
|---|---|---|---|---|---|
ECI scoreBest score 166 | 130 | 127 | 129 | 127 | |
| Ranking | #151 | #168 | #156 | #169 | |
| Conceptual reasoning | SimpleBenchBest score 81.9% | ||||
| Long context | ForecastBenchBest score 62.5 | 59.4 | 58.4 | 57.7 | 58.5 |
| Mathematics | MATH Level 5Best score 98.1% | ||||
OTIS Mock AIME 2024-2025Best score 100.0% | |||||
| Multimodal | Video-MMEBest score 79.7% | ||||
| Science | GPQA DiamondBest score 95.8% | ||||
| Software engineering | METR Time HorizonsBest score 1044.8 | 11.4 | 4.0 | — | — |
WeirdML (v2)Best score 92.9% | |||||
CybenchBest score 93.0% |
