Claude 3.5 Haiku (20241022): benchmark results

October 22, 2024 Claude 3.5 Haiku snapshot, tracked when sources report the dated API model. Provider: Anthropic. Released 2024-10-22. Access: API.

Unified ELO 1489 ± 1, rank #738 of 1392 rated models, from 228 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Enkrypt AI - Jailbreak Risk1.12Risk Score96.8
Enkrypt AI - Bias Risk43.41Risk Score95.8
Enkrypt AI - Safety Risk15.01Risk Score95.8
EuroEval Lithuanian NLU - ScaLA LT50.62Linguistic acceptability Score (%)95.6
EuroEval Faroese NLU - FoSent65.97Sentiment classification Score (%)92.2
EuroEval Finnish NLU - Scandisent FI92.47Sentiment classification Score (%)92.2
AILuminate Safety4Safety Grade (1-5)91.9
EuroEval Polish NLU - ScaLA PL53.53Linguistic acceptability Score (%)89.3
Enkrypt AI - Risk Score21.01Risk Score86.7
Enkrypt AI - Toxicity Risk0.64Risk Score86.6
UGI - Natural Intelligence37.98NatInt Score85.8
EuroEval Latvian NLU - Latvian Twitter Sentiment49.13Sentiment classification Score (%)84.9

Interactive version: theaggregate.ai/model?slug=claude-3-5-haiku-20241022 · How It Works · Data refreshed daily, snapshot 2026-09-05.