Claude Instant: benchmark results
Anthropic's fast, low-cost Claude 1-era API tier for high-throughput chat, classification, and summarization workloads. Provider: Anthropic. Released 2023-03-14. Access: API.
Unified ELO 1454 ± 1, rank #927 of 1392 rated models, from 15 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| NPHardEval - TSP D | 72.36 | Accuracy (%) | 90.9 |
| NPHardEval - TSP | 2 | Accuracy (%) | 86.4 |
| NPHardEval - SPP | 26 | Accuracy (%) | 81.8 |
| NPHardEval - MSP | 0.18 | Accuracy (%) | 77.3 |
| NPHardEval | 23.94 | Average Accuracy (%) | 72.7 |
| NPHardEval - EDP | 17.64 | Accuracy (%) | 72.7 |
| NPHardEval - GCP | 2.91 | Accuracy (%) | 54.5 |
| NPHardEval - SAS | 44.18 | Accuracy (%) | 54.5 |
| NPHardEval - GCP D | 50.18 | Accuracy (%) | 45.5 |
| NPHardEval - KSP | 0 | Accuracy (%) | 36.4 |
| BenchGecko Score | 84.6 | Composite Score | 26.3 |
| Klu LLM Leaderboard | 67 | Klu Index | 15 |
Interactive version: theaggregate.ai/model?slug=claude-instant · How It Works · Data refreshed daily, snapshot 2026-09-05.