‹ PublicAI Index
The LLM benchmark aggregator.
Ember 1
Other
Strongest in Biology research (#18 of 27), weakest in Reasoning (#96 of 189). Above par in 8 of 9 scopes. Among the models it meets almost everywhere, it finishes behind DeepSeek V4.1 Flash and Gemini 4 Argon and ahead of DeepSeek R1 and O1.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Coding54.5−11.9#38/1761/6
Agentic coding54.8−12.2#37/1691/5
Professional52.4−10.7#61/1871/2
Biology research45−26.1#18/271/1
Cybersecurity54.2−9.8#23/461/1
Legal55.2−11.2#38/1621/1
Finance52.7−9.8#76/1611/1
Reasoning50.5−14.3#96/1891/5
Mathematics50.7−13.3#82/1491/2
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Ember 1, left for the other.
§ 3 · Sources
Where the numbers come from
1 publication, 8 figures. Every one links to the page it was read from.
Vals · Legal Research Bench 44.71%Vals · Harvey Legal Agent Benchmark 9.17%Vals · Finance Agent 51.85%Vals · BioMysteryBench 67.04%Vals · CyberBench 69.52%Vals · Vibe Code Bench 83.87% (OpenHands)Vals · Code Migration 32.51%Vals · ProofBench 61%
Badge
[](https://publicai.io/model-index/m/ember-1)