Ember-1: benchmark results
Fireworks AI's Ember-1 (September 2026), Kimi K3 post-trained by Fireworks Research to reason in about 40% fewer tokens; a Research Preview on the Fireworks serverless API with no released weights. Provider: Fireworks AI. Released 2026-09-23. Access: API.
Aggregate Rating 1800 ± 16, rank #90 of 10556 rated models, from 29 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (DeepSWE 1.1) | 75.2 | Score (%) | 83.3 |
| LLM Stats Score | 41.94 | LLM Stats Score (conservative rating) | 83.1 |
| Vals AI Vibe Code Bench | 83.87 | Accuracy (%) | 82 |
| DuelLab GameBench 2 - Reasoning Variants | 63 | GameBench2 normalized score (0–100) | 73.5 |
| Gert Labs Rankings | 53.68 | GScore (%) | 73.5 |
| Vals AI Legal Research Bench | 44.71 | Accuracy (%) | 73.4 |
| Vals AI Harvey Legal Agent Bench | 9.17 | Accuracy (%) | 71.9 |
| Tinybird AI SQL Benchmark - Success Rate | 100 | Questions answered with a valid query within 3 retries (%) | 71.8 |
| ObviousBench | 97.22 | Answer pass³ (%) | 71.4 |
| Tinybird AI SQL Benchmark - Exactness | 51.73 | Result exactness vs human reference queries (0-100) | 70.6 |
| Vals AI Excel Modeling | 63.37 | Accuracy (%) | 64 |
| Vals AI Tax Agent Bench | 31.08 | Accuracy (%) | 62.4 |
Interactive version: theaggregate.ai/model?slug=ember-1 · How It Works · Data refreshed daily, snapshot 2026-11-17.