Benchmark Almanac

Ember-1

Ember-1.

Fireworks AI Released September 23rd, 2026 Family Ember The lab's model card Compare with others
19
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Fireworks AI Sep 2026

Ember-1

Closed weights Flagship

No Epoch Capabilities Index score yet
  • Harvey LAB (Legal Agent Benchmark) 9.17% #23 /80
  • Vals Finance Agent v2 51.9% #38 /80
  • BioMysteryBench 67% #21 /30

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Math and science

BenchmarkScoreRankSource
ProofBench v1.1 61% #23 of 52 Official leaderboard
BioMysteryBench 67% #21 of 30 Official leaderboard
MysteryMechanism 22.5% #22 of 31 Official leaderboard

Coding

BenchmarkScoreRankSource
Vibe Code Bench 83.9% #23 of 120 Official leaderboard
Code Migration 32.5% #39 of 78 Official leaderboard
IOI v2 (Vals) 46.3% #31 of 45 Official leaderboard

Agents and tools

BenchmarkScoreRankSource
DuelLab GameBench 2 63.1 #31 of 57 Official leaderboard

Professional work

BenchmarkScoreRankSource
Legal Research Bench 44.7% #26 of 93 Official leaderboard
Harvey LAB (Legal Agent Benchmark) 9.17% #23 of 80 Official leaderboard
Tax Agent Bench 31.1% #31 of 84 Official leaderboard
Public Benefits Bench 66.2% #19 of 50 Official leaderboard
Excel Modeling Benchmark 63.4% #29 of 76 Official leaderboard
Vals Finance Agent v2 51.9% #38 of 80 Official leaderboard
Bedside Bench 89.1% #9 of 17 Official leaderboard
Vals Index v2.1 50.9% #29 of 49 Official leaderboard

Safety and security

BenchmarkScoreRankSource
CyberBench v1.1 (Vals) 69.5% #22 of 44 Official leaderboard
SecIT Bench 74.5% #16 of 26 Official leaderboard

Other

BenchmarkScoreRankSource
SAGE v1.1 (Vals) 86.4% #13 of 29 Official leaderboard
Vals Science Index 31.8% #18 of 25 Official leaderboard