Mercury 2: benchmark results
Inception's Mercury 2 diffusion LLM, generating via parallel refinement at over 1,000 tokens/s. Provider: Inception. Released 2026-02-24. Access: API.
Aggregate Rating 1603 ± 16, rank #433 of 1656 rated models, from 143 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Insecure Code Risk | 1.33 | Risk Score | 96.8 |
| Story Theory Bench | 99.1 | Score (%) | 94.1 |
| AA IFBench | 69.8 | Accuracy (%) | 84 |
| Tinybird AI SQL Benchmark - First-Attempt Success Rate | 98 | Questions answered with a valid query on the first attempt ( | 80.5 |
| SnakeBench | 28.1 | TrueSkill Rating | 80.4 |
| Enkrypt AI - Bias Risk | 69.51 | Risk Score | 78.5 |
| Enkrypt AI - Risk Score | 24.33 | Risk Score | 77 |
| Tinybird AI SQL Benchmark - Success Rate | 100 | Questions answered with a valid query within 3 retries (%) | 71.7 |
| AA Terminal-Bench Hard | 26.52 | Accuracy (%) | 68.1 |
| ObviousBench | 95.83 | Answer pass³ (%) | 65.8 |
| Tau2-Bench Telecom | 70.76 | Success Rate (%) | 64.8 |
| Enkrypt AI - Toxicity Risk | 2.36 | Risk Score | 63.4 |
Interactive version: theaggregate.ai/model?slug=mercury-2 · How It Works · Data refreshed daily, snapshot 2026-10-20.