Celeris-1 vs mercury-2.5-preview
Wins 0 of 5 areas
—
Wins 4 of 5 areas
Coding · Reasoning · Facts · Long documents
mercury-2.5-preview is the stronger all-rounder.Celeris-1 is cheaper.
Scores updated · 10 tests both models report · How we compare
Where each one wins
Tests won in each of the five areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- FactsGetting facts right instead of making them up02mercury-2.5-preview2 of 2 tests
- ReasoningHard problems that need careful thinking01mercury-2.5-preview1 of 2 tests · 1 tie
- CodingWriting and fixing software01mercury-2.5-preview1 of 1 test
- Long documentsFinding answers in very long texts01mercury-2.5-preview1 of 1 test
- AgentsCarrying out multi-step tasks on its own00Even0 each · 2 ties
Coding and long documents rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Celeris-1 costs 10% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where mercury-2.5-preview pulls ahead
- Reasons across sets of long documentsAA-LCR+33.7points ahead
- Code for real scientific research problemsSciCode+16.9points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+12.5points ahead
Where Celeris-1 pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 10 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Reasoningmercury-2.5-preview
- Humanity's Last Exammercury-2.5-preview by 56.811.8+5
- CritPttie00tie
Factsmercury-2.5-preview
- AA-Omniscience · Non-hallucinationmercury-2.5-preview by 12.57.219.7+12.5
- AA-Omniscience · Accuracymercury-2.5-preview by 11.71122.6+11.7
Long documentsmercury-2.5-preview
- AA-LCRmercury-2.5-preview by 33.73871.7+33.7
Other results2 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AA-Omnisciencemercury-2.5-preview by 32.1-71.6-39.5+32.1
- AA Intelligencemercury-2.5-preview by 66.312.3+6
Questions people ask
Which is better, Celeris-1 or mercury-2.5-preview?
mercury-2.5-preview wins four of the five areas where both have results: coding, reasoning, facts and long documents. Celeris-1 wins none, but costs 10% less. They are level on agents.
Which is better for coding?
mercury-2.5-preview. It wins the one coding test both models report.
Which is cheaper?
Celeris-1 costs $0.20 per million input tokens and $0.70 per million output tokens; mercury-2.5-preview costs $0.25 and $0.75. That makes Celeris-1 about 10% cheaper for the same work.
How do you compare the two?
We use the 10 benchmark tests both models have published scores on. The verdict counts the 8 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 2 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.